Zhedong Zheng

Jianwu Fang, Lei-Lei Li, Kuan Yang et al.

Traffic accident prediction in driving videos aims to provide an early warning of the accident occurrence, and supports the decision making of safe driving systems. Previous works usually concentrate on the spatial-temporal correlation of object-level context, while they do not fit the inherent long-tailed data distribution well and are vulnerable to severe environmental change. In this work, we propose a Cognitive Accident Prediction (CAP) method that explicitly leverages human-inspired cognition of text description on the visual observation and the driver attention to facilitate model training. In particular, the text description provides a dense semantic description guidance for the primary context of the traffic scene, while the driver attention provides a traction to focus on the critical region closely correlating with safe driving. CAP is formulated by an attentive text-to-vision shift fusion module, an attentive scene context transfer module, and the driver attention guided accident prediction module. We leverage the attention mechanism in these modules to explore the core semantic cues for accident prediction. In order to train CAP, we extend an existing self-collected DADA-2000 dataset (with annotated driver attention for each frame) with further factual text descriptions for the visual observations before the accidents. Besides, we construct a new large-scale benchmark consisting of 11,727 in-the-wild accident videos with over 2.19 million frames (named as CAP-DATA) together with labeled fact-effect-reason-introspection description and temporal accident frame label. Based on extensive experiments, the superiority of CAP is validated compared with state-of-the-art approaches. The code, CAP-DATA, and all results will be released in \url{https://github.com/JWFanggit/LOTVS-CAP}.

Zhedong Zheng, Jiayin Zhu, Wei Ji et al.

This research aims to study a self-supervised 3D clothing reconstruction method, which recovers the geometry shape and texture of human clothing from a single image. Compared with existing methods, we observe that three primary challenges remain: (1) 3D ground-truth meshes of clothing are usually inaccessible due to annotation difficulties and time costs; (2) Conventional template-based methods are limited to modeling non-rigid objects, e.g., handbags and dresses, which are common in fashion images; (3) The inherent ambiguity compromises the model training, such as the dilemma between a large shape with a remote camera or a small shape with a close camera. In an attempt to address the above limitations, we propose a causality-aware self-supervised learning method to adaptively reconstruct 3D non-rigid objects from 2D images without 3D annotations. In particular, to solve the inherent ambiguity among four implicit variables, i.e., camera position, shape, texture, and illumination, we introduce an explainable structural causal map (SCM) to build our model. The proposed model structure follows the spirit of the causal map, which explicitly considers the prior template in the camera estimation and shape prediction. When optimization, the causality intervention tool, i.e., two expectation-maximization loops, is deeply embedded in our algorithm to (1) disentangle four encoders and (2) facilitate the prior template. Extensive experiments on two 2D fashion benchmarks (ATR and Market-HQ) show that the proposed method could yield high-fidelity 3D reconstruction. Furthermore, we also verify the scalability of the proposed method on a fine-grained bird dataset, i.e., CUB. The code is available at https://github.com/layumi/ 3D-Magic-Mirror .

Tingyu Wang, Zhedong Zheng, Yaoqi Sun et al.

Aerial-view geo-localization tends to determine an unknown position through matching the drone-view image with the geo-tagged satellite-view image. This task is mostly regarded as an image retrieval problem. The key underpinning this task is to design a series of deep neural networks to learn discriminative image descriptors. However, existing methods meet large performance drops under realistic weather, such as rain and fog, since they do not take the domain shift between the training data and multiple test environments into consideration. To minor this domain gap, we propose a Multiple-environment Self-adaptive Network (MuSe-Net) to dynamically adjust the domain shift caused by environmental changing. In particular, MuSe-Net employs a two-branch neural network containing one multiple-environment style extraction network and one self-adaptive feature extraction network. As the name implies, the multiple-environment style extraction network is to extract the environment-related style information, while the self-adaptive feature extraction network utilizes an adaptive modulation module to dynamically minimize the environment-related style gap. Extensive experiments on two widely-used benchmarks, i.e., University-1652 and CVUSA, demonstrate that the proposed MuSe-Net achieves a competitive result for geo-localization in multiple environments. Furthermore, we observe that the proposed method also shows great potential to the unseen extreme weather, such as mixing the fog, rain and snow.

Mu Chen, Zhedong Zheng, Yi Yang et al.

Unsupervised Domain Adaptation (UDA) aims to enhance the generalization of the learned model to other domains. The domain-invariant knowledge is transferred from the model trained on labeled source domain, e.g., video game, to unlabeled target domains, e.g., real-world scenarios, saving annotation expenses. Existing UDA methods for semantic segmentation usually focus on minimizing the inter-domain discrepancy of various levels, e.g., pixels, features, and predictions, for extracting domain-invariant knowledge. However, the primary intra-domain knowledge, such as context correlation inside an image, remains underexplored. In an attempt to fill this gap, we propose a unified pixel- and patch-wise self-supervised learning framework, called PiPa, for domain adaptive semantic segmentation that facilitates intra-image pixel-wise correlations and patch-wise semantic consistency against different contexts. The proposed framework exploits the inherent structures of intra-domain images, which: (1) explicitly encourages learning the discriminative pixel-wise features with intra-class compactness and inter-class separability, and (2) motivates the robust feature learning of the identical patch against different contexts or fluctuations. Extensive experiments verify the effectiveness of the proposed method, which obtains competitive accuracy on the two widely-used UDA benchmarks, i.e., 75.6 mIoU on GTA to Cityscapes and 68.2 mIoU on Synthia to Cityscapes. Moreover, our method is compatible with other UDA approaches to further improve the performance without introducing extra parameters.

Yiyang Chen, Zhedong Zheng, Wei Ji et al.

We investigate composed image retrieval with text feedback. Users gradually look for the target of interest by moving from coarse to fine-grained feedback. However, existing methods merely focus on the latter, i.e., fine-grained search, by harnessing positive and negative pairs during training. This pair-based paradigm only considers the one-to-one distance between a pair of specific points, which is not aligned with the one-to-many coarse-grained retrieval process and compromises the recall rate. In an attempt to fill this gap, we introduce a unified learning approach to simultaneously modeling the coarse- and fine-grained retrieval by considering the multi-grained uncertainty. The key idea underpinning the proposed method is to integrate fine- and coarse-grained retrieval as matching data points with small and large fluctuations, respectively. Specifically, our method contains two modules: uncertainty modeling and uncertainty regularization. (1) The uncertainty modeling simulates the multi-grained queries by introducing identically distributed fluctuations in the feature space. (2) Based on the uncertainty modeling, we further introduce uncertainty regularization to adapt the matching objective according to the fluctuation range. Compared with existing methods, the proposed strategy explicitly prevents the model from pushing away potential candidates in the early stage, and thus improves the recall rate. On the three public datasets, i.e., FashionIQ, Fashion200k, and Shoes, the proposed method has achieved +4.03%, +3.38%, and +2.40% Recall@50 accuracy over a strong baseline, respectively.

Leigang Qu, Meng Liu, Wenjie Wang et al.

Image-text retrieval aims to bridge the modality gap and retrieve cross-modal content based on semantic similarities. Prior work usually focuses on the pairwise relations (i.e., whether a data sample matches another) but ignores the higher-order neighbor relations (i.e., a matching structure among multiple data samples). Re-ranking, a popular post-processing practice, has revealed the superiority of capturing neighbor relations in single-modality retrieval tasks. However, it is ineffective to directly extend existing re-ranking algorithms to image-text retrieval. In this paper, we analyze the reason from four perspectives, i.e., generalization, flexibility, sparsity, and asymmetry, and propose a novel learnable pillar-based re-ranking paradigm. Concretely, we first select top-ranked intra- and inter-modal neighbors as pillars, and then reconstruct data samples with the neighbor relations between them and the pillars. In this way, each sample can be mapped into a multimodal pillar space only using similarities, ensuring generalization. After that, we design a neighbor-aware graph reasoning module to flexibly exploit the relations and excavate the sparse positive items within a neighborhood. We also present a structure alignment constraint to promote cross-modal collaboration and align the asymmetric modalities. On top of various base backbones, we carry out extensive experiments on two benchmark datasets, i.e., Flickr30K and MS-COCO, demonstrating the effectiveness, superiority, generalization, and transferability of our proposed re-ranking paradigm.

Han Yi, Zhedong Zheng, Xiangyu Xu et al.

Text-to-3D generation is to craft a 3D object according to a natural language description. This can significantly reduce the workload for manually designing 3D models and provide a more natural way of interaction for users. However, this problem remains challenging in recovering the fine-grained details effectively and optimizing a large-size 3D output efficiently. Inspired by the success of progressive learning, we propose a Multi-Scale Triplane Network (MTN) and a new progressive learning strategy. As the name implies, the Multi-Scale Triplane Network consists of four triplanes transitioning from low to high resolution. The low-resolution triplane could serve as an initial shape for the high-resolution ones, easing the optimization difficulty. To further enable the fine-grained details, we also introduce the progressive learning strategy, which explicitly demands the network to shift its focus of attention from simple coarse-grained patterns to difficult fine-grained patterns. Our experiment verifies that the proposed method performs favorably against existing methods. For even the most challenging descriptions, where most existing methods struggle to produce a viable shape, our proposed method consistently delivers. We aspire for our work to pave the way for automatic 3D prototyping via natural language descriptions.

Shuyu Yang, Yinan Zhou, Yaxiong Wang et al.

In this paper, we introduce a large Multi-Attribute and Language Search dataset for text-based person retrieval, called MALS, and explore the feasibility of performing pre-training on both attribute recognition and image-text matching tasks in one stone. In particular, MALS contains 1,510,330 image-text pairs, which is about 37.5 times larger than prevailing CUHK-PEDES, and all images are annotated with 27 attributes. Considering the privacy concerns and annotation costs, we leverage the off-the-shelf diffusion models to generate the dataset. To verify the feasibility of learning from the generated data, we develop a new joint Attribute Prompt Learning and Text Matching Learning (APTM) framework, considering the shared knowledge between attribute and text. As the name implies, APTM contains an attribute prompt learning stream and a text matching learning stream. (1) The attribute prompt learning leverages the attribute prompts for image-attribute alignment, which enhances the text matching learning. (2) The text matching learning facilitates the representation learning on fine-grained details, and in turn, boosts the attribute prompt learning. Extensive experiments validate the effectiveness of the pre-training on MALS, achieving state-of-the-art retrieval performance via APTM on three challenging real-world benchmarks. In particular, APTM achieves a consistent improvement of +6.96%, +7.68%, and +16.95% Recall@1 accuracy on CUHK-PEDES, ICFG-PEDES, and RSTPReid datasets by a clear margin, respectively.

Tingyu Wang, Zhedong Zheng, Zunjie Zhu et al.

Cross-view geo-localization aims to spot images of the same location shot from two platforms, e.g., the drone platform and the satellite platform. Existing methods usually focus on optimizing the distance between one embedding with others in the feature space, while neglecting the redundancy of the embedding itself. In this paper, we argue that the low redundancy is also of importance, which motivates the model to mine more diverse patterns. To verify this point, we introduce a simple yet effective regularization, i.e., Dynamic Weighted Decorrelation Regularization (DWDR), to explicitly encourage networks to learn independent embedding channels. As the name implies, DWDR regresses the embedding correlation coefficient matrix to a sparse matrix, i.e., the identity matrix, with dynamic weights. The dynamic weights are applied to focus on still correlated channels during training. Besides, we propose a cross-view symmetric sampling strategy, which keeps the example balance between different platforms. Albeit simple, the proposed method has achieved competitive results on three large-scale benchmarks, i.e., University-1652, CVUSA and CVACT. Moreover, under the harsh circumstance, e.g., the extremely short feature of 64 dimensions, the proposed method surpasses the baseline model by a clear margin.

Xuanmeng Zhang, Zhedong Zheng, Daiheng Gao et al.

3D-aware image synthesis aims to generate images of objects from multiple views by learning a 3D representation. However, one key challenge remains: existing approaches lack geometry constraints, hence usually fail to generate multi-view consistent images. To address this challenge, we propose Multi-View Consistent Generative Adversarial Networks (MVCGAN) for high-quality 3D-aware image synthesis with geometry constraints. By leveraging the underlying 3D geometry information of generated images, i.e., depth and camera transformation matrix, we explicitly establish stereo correspondence between views to perform multi-view joint optimization. In particular, we enforce the photometric consistency between pairs of views and integrate a stereo mixup mechanism into the training process, encouraging the model to reason about the correct 3D shape. Besides, we design a two-stage training strategy with feature-level multi-view joint optimization to improve the image quality. Extensive experiments on three datasets demonstrate that MVCGAN achieves the state-of-the-art performance for 3D-aware image synthesis.

Yucheng Suo, Zhedong Zheng, Xiaohan Wang et al.

Sign language is the window for people differently-abled to express their feelings as well as emotions. However, it remains challenging for people to learn sign language in a short time. To address this real-world challenge, in this work, we study the motion transfer system, which can transfer the user photo to the sign language video of specific words. In particular, the appearance content of the output video comes from the provided user image, while the motion of the video is extracted from the specified tutorial video. We observe two primary limitations in adopting the state-of-the-art motion transfer methods to sign language generation:(1) Existing motion transfer works ignore the prior geometrical knowledge of the human body. (2) The previous image animation methods only take image pairs as input in the training stage, which could not fully exploit the temporal information within videos. In an attempt to address the above-mentioned limitations, we propose Structure-aware Temporal Consistency Network (STCNet) to jointly optimize the prior structure of human with the temporal consistency for sign language video generation. There are two main contributions in this paper. (1) We harness a fine-grained skeleton detector to provide prior knowledge of the body keypoints. In this way, we ensure the keypoint movement in a valid range and make the model become more explainable and robust. (2) We introduce two cycle-consistency losses, i.e., short-term cycle loss and long-term cycle loss, which are conducted to assure the continuity of the generated video. We optimize the two losses and keypoint detector network in an end-to-end manner.

Xiaolong Shen, Zhedong Zheng, Yi Yang

The goal of sign language recognition (SLR) is to help those who are hard of hearing or deaf overcome the communication barrier. Most existing approaches can be typically divided into two lines, i.e., Skeleton-based and RGB-based methods, but both the two lines of methods have their limitations. Skeleton-based methods do not consider facial expressions, while RGB-based approaches usually ignore the fine-grained hand structure. To overcome both limitations, we propose a new framework called Spatial-temporal Part-aware network~(StepNet), based on RGB parts. As its name suggests, it is made up of two modules: Part-level Spatial Modeling and Part-level Temporal Modeling. Part-level Spatial Modeling, in particular, automatically captures the appearance-based properties, such as hands and faces, in the feature space without the use of any keypoint-level annotations. On the other hand, Part-level Temporal Modeling implicitly mines the long-short term context to capture the relevant attributes over time. Extensive experiments demonstrate that our StepNet, thanks to spatial-temporal modules, achieves competitive Top-1 Per-instance accuracy on three commonly-used SLR benchmarks, i.e., 56.89% on WLASL, 77.2% on NMFs-CSL, and 77.1% on BOBSL. Additionally, the proposed method is compatible with the optical flow input and can produce superior performance if fused. For those who are hard of hearing, we hope that our work can act as a preliminary step.

Xu Zhang, Zhedong Zheng, Linchao Zhu et al.

Composed image retrieval extends content-based image retrieval systems by enabling users to search using reference images and captions that describe their intention. Despite great progress in developing image-text compositors to extract discriminative visual-linguistic features, we identify a hitherto overlooked issue, triplet ambiguity, which impedes robust feature extraction. Triplet ambiguity refers to a type of semantic ambiguity that arises between the reference image, the relative caption, and the target image. It is mainly due to the limited representation of the annotated text, resulting in many noisy triplets where multiple visually dissimilar candidate images can be matched to an identical reference pair (i.e., a reference image + a relative caption). To address this challenge, we propose the Consensus Network (Css-Net), inspired by the psychological concept that groups outperform individuals. Css-Net comprises two core components: (1) a consensus module with four diverse compositors, each generating distinct image-text embeddings, fostering complementary feature extraction and mitigating dependence on any single, potentially biased compositor; (2) a Kullback-Leibler divergence loss that encourages learning of inter-compositor interactions to promote consensual outputs. During evaluation, the decisions of the four compositors are combined through a weighting scheme, enhancing overall agreement. On benchmark datasets, particularly FashionIQ, Css-Net demonstrates marked improvements. Notably, it achieves significant recall gains, with a 2.77% increase in R@10 and 6.67% boost in R@50, underscoring its competitiveness in addressing the fundamental limitations of existing methods.

Mu Chen, Zhedong Zheng, Yi Yang

Scene segmentation via unsupervised domain adaptation (UDA) enables the transfer of knowledge acquired from source synthetic data to real-world target data, which largely reduces the need for manual pixel-level annotations in the target domain. To facilitate domain-invariant feature learning, existing methods typically mix data from both the source domain and target domain by simply copying and pasting the pixels. Such vanilla methods are usually sub-optimal since they do not take into account how well the mixed layouts correspond to real-world scenarios. Real-world scenarios are with an inherent layout. We observe that semantic categories, such as sidewalks, buildings, and sky, display relatively consistent depth distributions, and could be clearly distinguished in a depth map. Based on such observation, we propose a depth-aware framework to explicitly leverage depth estimation to mix the categories and facilitate the two complementary tasks, i.e., segmentation and depth learning in an end-to-end manner. In particular, the framework contains a Depth-guided Contextual Filter (DCF) forndata augmentation and a cross-task encoder for contextual learning. DCF simulates the real-world layouts, while the cross-task encoder further adaptively fuses the complementing features between two tasks. Besides, it is worth noting that several public datasets do not provide depth annotation. Therefore, we leverage the off-the-shelf depth estimation network to generate the pseudo depth. Extensive experiments show that our proposed methods, even with pseudo depth, achieve competitive performance on two widely-used bench-marks, i.e. 77.7 mIoU on GTA to Cityscapes and 69.3 mIoU on Synthia to Cityscapes.

Meng Chu, Zhedong Zheng, Wei Ji et al.

Navigating drones through natural language commands remains challenging due to the dearth of accessible multi-modal datasets and the stringent precision requirements for aligning visual and textual data. To address this pressing need, we introduce GeoText-1652, a new natural language-guided geo-localization benchmark. This dataset is systematically constructed through an interactive human-computer process leveraging Large Language Model (LLM) driven annotation techniques in conjunction with pre-trained vision models. GeoText-1652 extends the established University-1652 image dataset with spatial-aware text annotations, thereby establishing one-to-one correspondences between image, text, and bounding box elements. We further introduce a new optimization objective to leverage fine-grained spatial associations, called blending spatial matching, for region-level spatial relation matching. Extensive experiments reveal that our approach maintains a competitive recall rate comparing other prevailing cross-modality methods. This underscores the promising potential of our approach in elevating drone control and navigation through the seamless integration of natural language commands in real-world scenarios.

Shuyu Yang, Yaxiong Wang, Li Zhu et al.

Text-based person search aims to retrieve specific individuals across camera networks using natural language descriptions. However, current benchmarks often exhibit biases towards common actions like walking or standing, neglecting the critical need for identifying abnormal behaviors in real-world scenarios. To meet such demands, we propose a new task, text-based person anomaly search, locating pedestrians engaged in both routine or anomalous activities via text. To enable the training and evaluation of this new task, we construct a large-scale image-text Pedestrian Anomaly Behavior (PAB) benchmark, featuring a broad spectrum of actions, e.g., running, performing, playing soccer, and the corresponding anomalies, e.g., lying, being hit, and falling of the same identity. The training set of PAB comprises 1,013,605 synthesized image-text pairs of both normalities and anomalies, while the test set includes 1,978 real-world image-text pairs. To validate the potential of PAB, we introduce a cross-modal pose-aware framework, which integrates human pose patterns with identity-based hard negative pair sampling. Extensive experiments on the proposed benchmark show that synthetic training data facilitates the fine-grained behavior retrieval, and the proposed pose-aware method arrives at 84.93% recall@1 accuracy, surpassing other competitive methods. The dataset, model, and code are available at https://github.com/Shuyu-XJTU/CMP.

Hang Yu, Jiahao Wen, Zhedong Zheng

Text-based person retrieval aims to identify specific individuals within an image database using textual descriptions. Due to the high cost of annotation and privacy protection, researchers resort to synthesized data for the paradigm of pretraining and fine-tuning. However, these generated data often exhibit domain biases in both images and textual annotations, which largely compromise the scalability of the pre-trained model. Therefore, we introduce a domain-agnostic pretraining framework based on Cross-modality Adaptive Meta-Learning (CAMeL) to enhance the model generalization capability during pretraining to facilitate the subsequent downstream tasks. In particular, we develop a series of tasks that reflect the diversity and complexity of real-world scenarios, and introduce a dynamic error sample memory unit to memorize the history for errors encountered within multiple tasks. To further ensure multi-task adaptation, we also adopt an adaptive dual-speed update strategy, balancing fast adaptation to new tasks and slow weight updates for historical tasks. Albeit simple, our proposed model not only surpasses existing state-of-the-art methods on real-world benchmarks, including CUHK-PEDES, ICFG-PEDES, and RSTPReid, but also showcases robustness and scalability in handling biased synthetic images and noisy text annotations. Our code is available at https://github.com/Jahawn-Wen/CAMeL-reID.

Ruiyang Zhang, Hu Zhang, Hang Yu et al.

The unsupervised 3D object detection is to accurately detect objects in unstructured environments with no explicit supervisory signals. This task, given sparse LiDAR point clouds, often results in compromised performance for detecting distant or small objects due to the inherent sparsity and limited spatial resolution. In this paper, we are among the early attempts to integrate LiDAR data with 2D images for unsupervised 3D detection and introduce a new method, dubbed LiDAR-2D Self-paced Learning (LiSe). We argue that RGB images serve as a valuable complement to LiDAR data, offering precise 2D localization cues, particularly when scarce LiDAR points are available for certain objects. Considering the unique characteristics of both modalities, our framework devises a self-paced learning pipeline that incorporates adaptive sampling and weak model aggregation strategies. The adaptive sampling strategy dynamically tunes the distribution of pseudo labels during training, countering the tendency of models to overfit easily detected samples, such as nearby and large-sized objects. By doing so, it ensures a balanced learning trajectory across varying object scales and distances. The weak model aggregation component consolidates the strengths of models trained under different pseudo label distributions, culminating in a robust and powerful final model. Experimental evaluations validate the efficacy of our proposed LiSe method, manifesting significant improvements of +7.1% AP$_{BEV}$ and +3.4% AP$_{3D}$ on nuScenes, and +8.3% AP$_{BEV}$ and +7.4% AP$_{3D}$ on Lyft compared to existing techniques.

Yule Zhu, Ping Liu, Zhedong Zheng et al.

Diffusion models have recently enabled precise and photorealistic facial editing across a wide range of semantic attributes. Beyond single-step modifications, a growing class of applications now demands the ability to analyze and track sequences of progressive edits, such as stepwise changes to hair, makeup, or accessories. However, sequential editing introduces significant challenges in edit attribution and detection robustness, further complicated by the lack of large-scale, finely annotated benchmarks tailored explicitly for this task. We introduce SEED, a large-scale Sequentially Edited facE Dataset constructed via state-of-the-art diffusion models. SEED contains over 90,000 facial images with one to four sequential attribute modifications, generated using diverse diffusion-based editing pipelines (LEdits, SDXL, SD3). Each image is annotated with detailed edit sequences, attribute masks, and prompts, facilitating research on sequential edit tracking, visual provenance analysis, and manipulation robustness assessment. To benchmark this task, we propose FAITH, a frequency-aware transformer-based model that incorporates high-frequency cues to enhance sensitivity to subtle sequential changes. Comprehensive experiments, including systematic comparisons of multiple frequency-domain methods, demonstrate the effectiveness of FAITH and the unique challenges posed by SEED. SEED offers a challenging and flexible resource for studying progressive diffusion-based edits at scale. Dataset and code will be publicly released at: https://github.com/Zeus1037/SEED.

Bingwen Hu, Heng Liu, Zhedong Zheng et al.

Convolutional Neural Networks (CNNs) have significantly advanced Image Super-Resolution (SR), yet most CNN-based methods rely solely on pixel-based transformations, often leading to artifacts and blurring, particularly under severe downsampling rates (\eg, 8$\times$ or 16$\times$). The recently developed text-guided SR approaches leverage textual descriptions to enhance their detail restoration capabilities but frequently struggle with effectively performing alignment, resulting in semantic inconsistencies. To address these challenges, we propose a multi-modal semantic enhancement framework that integrates textual semantics with visual features, effectively mitigating semantic mismatches and detail losses in highly degraded low-resolution (LR) images. Our method enables realistic, high-quality SR to be performed at large upscaling factors, with a maximum scaling ratio of 16$\times$. The framework integrates both text and image inputs using the prompt predictor, the Text-Image Fusion Block (TIFBlock), and the Iterative Refinement Module, leveraging Contrastive Language-Image Pretraining (CLIP) features to guide a progressive enhancement process with fine-grained alignment. This synergy produces high-resolution outputs with sharp textures and strong semantic coherence, even at substantial scaling factors. Extensive comparative experiments and ablation studies validate the effectiveness of our approach. Furthermore, by leveraging textual semantics, our method offers a degree of super-resolution editability, allowing for controlled enhancements while preserving semantic consistency. The code is available at https://github.com/hengliusky/CLIP-SR.

Shuai Bai, Zhedong Zheng, Xiaohan Wang et al.

Vehicle search is one basic task for the efficient traffic management in terms of the AI City. Most existing practices focus on the image-based vehicle matching, including vehicle re-identification and vehicle tracking. In this paper, we apply one new modality, i.e., the language description, to search the vehicle of interest and explore the potential of this task in the real-world scenario. The natural language-based vehicle search poses one new challenge of fine-grained understanding of both vision and language modalities. To connect language and vision, we propose to jointly train the state-of-the-art vision models with the transformer-based language model in an end-to-end manner. Except for the network structure design and the training strategy, several optimization objectives are also re-visited in this work. The qualitative and quantitative experiments verify the effectiveness of the proposed method. Our proposed method has achieved the 1st place on the 5th AI City Challenge, yielding competitive performance 18.69% MRR accuracy on the private test set. We hope this work can pave the way for the future study on using language description effectively and efficiently for real-world vehicle retrieval systems. The code will be available at https://github.com/ShuaiBai623/AIC2021-T5-CLV.

Zhedong Zheng, Nenggan Zheng, Yi Yang

People live in a 3D world. However, existing works on person re-identification (re-id) mostly consider the semantic representation learning in a 2D space, intrinsically limiting the understanding of people. In this work, we address this limitation by exploring the prior knowledge of the 3D body structure. Specifically, we project 2D images to a 3D space and introduce a novel parameter-efficient Omni-scale Graph Network (OG-Net) to learn the pedestrian representation directly from 3D point clouds. OG-Net effectively exploits the local information provided by sparse 3D points and takes advantage of the structure and appearance information in a coherent manner. With the help of 3D geometry information, we can learn a new type of deep re-id feature free from noisy variants, such as scale and viewpoint. To our knowledge, we are among the first attempts to conduct person re-identification in the 3D space. We demonstrate through extensive experiments that the proposed method (1) eases the matching difficulty in the traditional 2D space, (2) exploits the complementary information of 2D appearance and 3D structure, (3) achieves competitive results with limited parameters on four large-scale person re-id datasets, and (4) has good scalability to unseen datasets. Our code, models and generated 3D human data are publicly available at https://github.com/layumi/person-reid-3d .

Yawei Luo, Zhedong Zheng, Liang Zheng et al.

In human parsing, the pixel-wise classification loss has drawbacks in its low-level local inconsistency and high-level semantic inconsistency. The introduction of the adversarial network tackles the two problems using a single discriminator. However, the two types of parsing inconsistency are generated by distinct mechanisms, so it is difficult for a single discriminator to solve them both. To address the two kinds of inconsistencies, this paper proposes the Macro-Micro Adversarial Net (MMAN). It has two discriminators. One discriminator, Macro D, acts on the low-resolution label map and penalizes semantic inconsistency, e.g., misplaced body parts. The other discriminator, Micro D, focuses on multiple patches of the high-resolution label map to address the local inconsistency, e.g., blur and hole. Compared with traditional adversarial networks, MMAN not only enforces local and semantic consistency explicitly, but also avoids the poor convergence problem of adversarial networks when handling high resolution images. In our experiment, we validate that the two discriminators are complementary to each other in improving the human parsing accuracy. The proposed framework is capable of producing competitive parsing performance compared with the state-of-the-art methods, i.e., mIoU=46.81% and 59.91% on LIP and PASCAL-Person-Part, respectively. On a relatively small dataset PPSS, our pre-trained model demonstrates impressive generalization ability. The code is publicly available at https://github.com/RoyalVane/MMAN.

Zhedong Zheng, Liang Zheng, Yi Yang

The main contribution of this paper is a simple semi-supervised pipeline that only uses the original training set without collecting extra data. It is challenging in 1) how to obtain more training data only from the training set and 2) how to use the newly generated data. In this work, the generative adversarial network (GAN) is used to generate unlabeled samples. We propose the label smoothing regularization for outliers (LSRO). This method assigns a uniform label distribution to the unlabeled images, which regularizes the supervised model and improves the baseline. We verify the proposed method on a practical problem: person re-identification (re-ID). This task aims to retrieve a query person from other cameras. We adopt the deep convolutional generative adversarial network (DCGAN) for sample generation, and a baseline convolutional neural network (CNN) for representation learning. Experiments show that adding the GAN-generated data effectively improves the discriminative ability of learned CNN embeddings. On three large-scale datasets, Market-1501, CUHK03 and DukeMTMC-reID, we obtain +4.37%, +1.6% and +2.46% improvement in rank-1 precision over the baseline CNN, respectively. We additionally apply the proposed method to fine-grained bird recognition and achieve a +0.6% improvement over a strong baseline. The code is available at https://github.com/layumi/Person-reID_GAN.

Ruiyang Zhang, Hu Zhang, Zhedong Zheng

Given the higher information load processed by large vision-language models (LVLMs) compared to single-modal LLMs, detecting LVLM hallucinations requires more human and time expense, and thus rise a wider safety concerns. In this paper, we introduce VL-Uncertainty, the first uncertainty-based framework for detecting hallucinations in LVLMs. Different from most existing methods that require ground-truth or pseudo annotations, VL-Uncertainty utilizes uncertainty as an intrinsic metric. We measure uncertainty by analyzing the prediction variance across semantically equivalent but perturbed prompts, including visual and textual data. When LVLMs are highly confident, they provide consistent responses to semantically equivalent queries. However, when uncertain, the responses of the target LVLM become more random. Considering semantically similar answers with different wordings, we cluster LVLM responses based on their semantic content and then calculate the cluster distribution entropy as the uncertainty measure to detect hallucination. Our extensive experiments on 10 LVLMs across four benchmarks, covering both free-form and multi-choice tasks, show that VL-Uncertainty significantly outperforms strong baseline methods in hallucination detection.

Jintao Sun, Hao Fei, Zhedong Zheng et al.

In text-based person search endeavors, data generation has emerged as a prevailing practice, addressing concerns over privacy preservation and the arduous task of manual annotation. Although the number of synthesized data can be infinite in theory, the scientific conundrum persists that how much generated data optimally fuels subsequent model training. We observe that only a subset of the data in these constructed datasets plays a decisive role. Therefore, we introduce a new Filtering-WoRA paradigm, which contains a filtering algorithm to identify this crucial data subset and WoRA (Weighted Low-Rank Adaptation) learning strategy for light fine-tuning. The filtering algorithm is based on the cross-modality relevance to remove the lots of coarse matching synthesis pairs. As the number of data decreases, we do not need to fine-tune the entire model. Therefore, we propose a WoRA learning strategy to efficiently update a minimal portion of model parameters. WoRA streamlines the learning process, enabling heightened efficiency in extracting knowledge from fewer, yet potent, data instances. Extensive experimentation validates the efficacy of pretraining, where our model achieves advanced and efficient retrieval performance on challenging real-world benchmarks. Notably, on the CUHK-PEDES dataset, we have achieved a competitive mAP of 67.02% while reducing model training time by 19.82%.

Guiyu Zhang, Huan-ang Gao, Zijian Jiang et al.

In this paper, we focus on the task of conditional image generation, where an image is synthesized according to user instructions. The critical challenge underpinning this task is ensuring both the fidelity of the generated images and their semantic alignment with the provided conditions. To tackle this issue, previous studies have employed supervised perceptual losses derived from pre-trained models, i.e., reward models, to enforce alignment between the condition and the generated result. However, we observe one inherent shortcoming: considering the diversity of synthesized images, the reward model usually provides inaccurate feedback when encountering newly generated data, which can undermine the training process. To address this limitation, we propose an uncertainty-aware reward modeling, called Ctrl-U, including uncertainty estimation and uncertainty-aware regularization, designed to reduce the adverse effects of imprecise feedback from the reward model. Given the inherent cognitive uncertainty within reward models, even images generated under identical conditions often result in a relatively large discrepancy in reward loss. Inspired by the observation, we explicitly leverage such prediction variance as an uncertainty indicator. Based on the uncertainty estimation, we regularize the model training by adaptively rectifying the reward. In particular, rewards with lower uncertainty receive higher loss weights, while those with higher uncertainty are given reduced weights to allow for larger variability. The proposed uncertainty regularization facilitates reward fine-tuning through consistency construction. Extensive experiments validate the effectiveness of our methodology in improving the controllability and generation quality, as well as its scalability across diverse conditional scenarios. Codes are publicly available at https://grenoble-zhang.github.io/Ctrl-U-Page/.

Jingchun Lian, Lingyu Liu, Yaxiong Wang et al.

Image forgery localization, which centers on identifying tampered pixels within an image, has seen significant advancements. Traditional approaches often model this challenge as a variant of image segmentation, treating the binary segmentation of forged areas as the end product. We argue that the basic binary forgery mask is inadequate for explaining model predictions. It doesn't clarify why the model pinpoints certain areas and treats all forged pixels the same, making it hard to spot the most fake-looking parts. In this study, we mitigate the aforementioned limitations by generating salient region-focused interpretation for the forgery images. To support this, we craft a Multi-Modal Tramper Tracing (MMTT) dataset, comprising facial images manipulated using deepfake techniques and paired with manual, interpretable textual annotations. To harvest high-quality annotation, annotators are instructed to meticulously observe the manipulated images and articulate the typical characteristics of the forgery regions. Subsequently, we collect a dataset of 128,303 image-text pairs. Leveraging the MMTT dataset, we develop ForgeryTalker, an architecture designed for concurrent forgery localization and interpretation. ForgeryTalker first trains a forgery prompter network to identify the pivotal clues within the explanatory text. Subsequently, the region prompter is incorporated into multimodal large language model for finetuning to achieve the dual goals of localization and interpretation. Extensive experiments conducted on the MMTT dataset verify the superior performance of our proposed model. The dataset, code as well as pretrained checkpoints will be made publicly available to facilitate further research and ensure the reproducibility of our results.

Yinan Zhou, Yaxiong Wang, Haokun Lin et al.

Composed Image Retrieval (CIR) aims to search an image of interest using a combination of a reference image and modification text as the query. Despite recent advancements, this task remains challenging due to limited training data and laborious triplet annotation processes. To address this issue, this paper proposes to synthesize the training triplets to augment the training resource for the CIR problem. Specifically, we commence by training a modification text generator exploiting large-scale multimodal models and scale up the CIR learning throughout both the pretraining and fine-tuning stages. During pretraining, we leverage the trained generator to directly create Modification Text-oriented Synthetic Triplets(MTST) conditioned on pairs of images. For fine-tuning, we first synthesize reverse modification text to connect the target image back to the reference image. Subsequently, we devise a two-hop alignment strategy to incrementally close the semantic gap between the multimodal pair and the target image. We initially learn an implicit prototype utilizing both the original triplet and its reversed version in a cycle manner, followed by combining the implicit prototype feature with the modification text to facilitate accurate alignment with the target image. Extensive experiments validate the efficacy of the generated triplets and confirm that our proposed methodology attains competitive recall on both the CIRR and FashionIQ benchmarks.

Quan Chen, Tingyu Wang, Rongfeng Lu et al.

UAV Geo-Localization faces significant challenges due to the drastic appearance discrepancy between dronecaptured images and satellite views. Existing methods typically assume a consistent scaling factor across views and rely on predefined partition alignment to extract viewpoint-invariant representations through part-level feature construction. However, this scaling assumption often fails in real-world scenarios, where variations in drone flight states lead to scale mismatches between cross-view images, resulting in severe performance degradation. To address this issue, we propose a scale-adaptive partition learning framework that leverages known drone flight height to predict scale factors and dynamically adjust feature extraction. Our key contribution is a height-aware adjustment strategy, which calculates the relative height ratio between drone and satellite views, dynamically adjusting partition sizes to explicitly align semantic information between partition pairs. This strategy is integrated into a Scale-adaptive Local Partition Network (SaLPN), building upon an existing square partition strategy to extract both finegrained and global features. Additionally, we propose a saliencyguided refinement strategy to enhance part-level features, further improving retrieval accuracy. Extensive experiments validate that our height-aware, scale-adaptive approach achieves stateof-the-art geo-localization accuracy in various scale-inconsistent scenarios and exhibits strong robustness against scale variations. The code will be made publicly available.

Zheng Tang, Shuo Wang, David C. Anastasiu et al.

The ninth AI City Challenge continues to advance real-world applications of computer vision and AI in transportation, industrial automation, and public safety. The 2025 edition featured four tracks and saw a 17% increase in participation, with 245 teams from 15 countries registered on the evaluation server. Public release of challenge datasets led to over 30,000 downloads to date. Track 1 focused on multi-class 3D multi-camera tracking, involving people, humanoids, autonomous mobile robots, and forklifts, using detailed calibration and 3D bounding box annotations. Track 2 tackled video question answering in traffic safety, with multi-camera incident understanding enriched by 3D gaze labels. Track 3 addressed fine-grained spatial reasoning in dynamic warehouse environments, requiring AI systems to interpret RGB-D inputs and answer spatial questions that combine perception, geometry, and language. Both Track 1 and Track 3 datasets were generated in NVIDIA Omniverse. Track 4 emphasized efficient road object detection from fisheye cameras, supporting lightweight, real-time deployment on edge devices. The evaluation framework enforced submission limits and used a partially held-out test set to ensure fair benchmarking. Final rankings were revealed after the competition concluded, fostering reproducibility and mitigating overfitting. Several teams achieved top-tier results, setting new benchmarks in multiple tasks.

Jiacheng Wang, Zhedong Zheng, Wei Xu et al.

Given a single image of a target object, image-to-3D generation aims to reconstruct its texture and geometric shape. Recent methods often utilize intermediate media, such as multi-view images or videos, to bridge the gap between input image and the 3D target, thereby guiding the generation of both shape and texture. However, inconsistencies in the generated multi-view snapshots frequently introduce noise and artifacts along object boundaries, undermining the 3D reconstruction process. To address this challenge, we leverage 3D Gaussian Splatting (3DGS) for 3D reconstruction, and explicitly integrate uncertainty-aware learning into the reconstruction process. By capturing the stochasticity between two Gaussian models, we estimate an uncertainty map, which is subsequently used for uncertainty-aware regularization to rectify the impact of inconsistencies. Specifically, we optimize both Gaussian models simultaneously, calculating the uncertainty map by evaluating the discrepancies between rendered images from identical viewpoints. Based on the uncertainty map, we apply adaptive pixel-wise loss weighting to regularize the models, reducing reconstruction intensity in high-uncertainty regions. This approach dynamically detects and mitigates conflicts in multi-view labels, leading to smoother results and effectively reducing artifacts. Extensive experiments show the effectiveness of our method in improving 3D generation quality by reducing inconsistencies and artifacts.

Shuyu Yang, Yilun Wang, Yaxiong Wang et al.

Video anomaly retrieval aims to localize anomalous events in videos using natural language queries to facilitate public safety. However, existing datasets suffer from severe limitations: (1) data scarcity due to the long-tail nature of real-world anomalies, and (2) privacy constraints that impede large-scale collection. To address the aforementioned issues in one go, we introduce SVTA (Synthetic Video-Text Anomaly benchmark), the first large-scale dataset for cross-modal anomaly retrieval, leveraging generative models to overcome data availability challenges. Specifically, we collect and generate video descriptions via the off-the-shelf LLM (Large Language Model) covering 68 anomaly categories, e.g., throwing, stealing, and shooting. These descriptions encompass common long-tail events. We adopt these texts to guide the video generative model to produce diverse and high-quality videos. Finally, our SVTA involves 41,315 videos (1.36M frames) with paired captions, covering 30 normal activities, e.g., standing, walking, and sports, and 68 anomalous events, e.g., falling, fighting, theft, explosions, and natural disasters. We adopt three widely-used video-text retrieval baselines to comprehensively test our SVTA, revealing SVTA's challenging nature and its effectiveness in evaluating a robust cross-modal retrieval method. SVTA eliminates privacy risks associated with real-world anomaly collection while maintaining realistic scenarios. The dataset demo is available at: [https://svta-mm.github.io/SVTA.github.io/].

Haidong Xu, Meishan Zhang, Hao Ju et al.

Enabling digital humans to express rich emotions has significant applications in dialogue systems, gaming, and other interactive scenarios. While recent advances in talking head synthesis have achieved impressive results in lip synchronization, they tend to overlook the rich and dynamic nature of facial expressions. To fill this critical gap, we introduce an end-to-end text-to-expression model that explicitly focuses on emotional dynamics. Our model learns expressive facial variations in a continuous latent space and generates expressions that are diverse, fluid, and emotionally coherent. To support this task, we introduce EmoAva, a large-scale and high-quality dataset containing 15,000 text-3D expression pairs. Extensive experiments on both existing datasets and EmoAva demonstrate that our method significantly outperforms baselines across multiple evaluation metrics, marking a significant advancement in the field.

Ruiyang Zhang, Hu Zhang, Hao Fei et al.

Large Multimodal Models (LMMs), harnessing the complementarity among diverse modalities, are often considered more robust than pure Language Large Models (LLMs); yet do LMMs know what they do not know? There are three key open questions remaining: (1) how to evaluate the uncertainty of diverse LMMs in a unified manner, (2) how to prompt LMMs to show its uncertainty, and (3) how to quantify uncertainty for downstream tasks. In an attempt to address these challenges, we introduce Uncertainty-o: (1) a model-agnostic framework designed to reveal uncertainty in LMMs regardless of their modalities, architectures, or capabilities, (2) an empirical exploration of multimodal prompt perturbations to uncover LMM uncertainty, offering insights and findings, and (3) derive the formulation of multimodal semantic uncertainty, which enables quantifying uncertainty from multimodal responses. Experiments across 18 benchmarks spanning various modalities and 10 LMMs (both open- and closed-source) demonstrate the effectiveness of Uncertainty-o in reliably estimating LMM uncertainty, thereby enhancing downstream tasks such as hallucination detection, hallucination mitigation, and uncertainty-aware Chain-of-Thought reasoning.

Yiyao Huang, Zhedong Zheng, Yu Ziwei et al.

Pre-defined 3D object templates are widely used in 3D reconstruction of hand-object interactions. However, they often require substantial manual efforts to capture or source, and inherently restrict the adaptability of models to unconstrained interaction scenarios, e.g., heavily-occluded objects. To overcome this bottleneck, we propose a new Text-Instructed Generation and Refinement (TIGeR) framework, harnessing the power of intuitive text-driven priors to steer the object shape refinement and pose estimation. We use a two-stage framework: a text-instructed prior generation and vision-guided refinement. As the name implies, we first leverage off-the-shelf models to generate shape priors according to the text description without tedious 3D crafting. Considering the geometric gap between the synthesized prototype and the real object interacted with the hand, we further calibrate the synthesized prototype via 2D-3D collaborative attention. TIGeR achieves competitive performance, i.e., 1.979 and 5.468 object Chamfer distance on the widely-used Dex-YCB and Obman datasets, respectively, surpassing existing template-free methods. Notably, the proposed framework shows robustness to occlusion, while maintaining compatibility with heterogeneous prior sources, e.g., retrieved hand-crafted prototypes, in practical deployment scenarios.

Jintao Sun, Hu Zhang, Gangyi Ding et al.

Modern end-to-end autonomous driving systems suffer from a critical limitation: their planners lack mechanisms to enforce temporal consistency between predicted trajectories and evolving scene dynamics. This absence of self-supervision allows early prediction errors to compound catastrophically over time. We introduce Echo Planning, a novel self-correcting framework that establishes a closed-loop Current - Future - Current (CFC) cycle to harmonize trajectory prediction with scene coherence. Our key insight is that plausible future trajectories must be bi-directionally consistent, ie, not only generated from current observations but also capable of reconstructing them. The CFC mechanism first predicts future trajectories from the Bird's-Eye-View (BEV) scene representation, then inversely maps these trajectories back to estimate the current BEV state. By enforcing consistency between the original and reconstructed BEV representations through a cycle loss, the framework intrinsically penalizes physically implausible or misaligned trajectories. Experiments on nuScenes demonstrate state-of-the-art performance, reducing L2 error by 0.04 m and collision rate by 0.12% compared to one-shot planners. Crucially, our method requires no additional supervision, leveraging the CFC cycle as an inductive bias for robust planning. This work offers a deployable solution for safety-critical autonomous systems.

Lingyu Liu, Yaxiong Wang, Li Zhu et al.

We introduce a training-free framework specifically designed to bring real-world static paintings to life through image-to-video (I2V) synthesis, addressing the persistent challenge of aligning these motions with textual guidance while preserving fidelity to the original artworks. Existing I2V methods, primarily trained on natural video datasets, often struggle to generate dynamic outputs from static paintings. It remains challenging to generate motion while maintaining visual consistency with real-world paintings. This results in two distinct failure modes: either static outputs due to limited text-based motion interpretation or distorted dynamics caused by inadequate alignment with real-world artistic styles. We leverage the advanced text-image alignment capabilities of pre-trained image models to guide the animation process. Our approach introduces synthetic proxy images through two key innovations: (1) Dual-path score distillation: We employ a dual-path architecture to distill motion priors from both real and synthetic data, preserving static details from the original painting while learning dynamic characteristics from synthetic frames. (2) Hybrid latent fusion: We integrate hybrid features extracted from real paintings and synthetic proxy images via spherical linear interpolation in the latent space, ensuring smooth transitions and enhancing temporal consistency. Experimental evaluations confirm that our approach significantly improves semantic alignment with text prompts while faithfully preserving the unique characteristics and integrity of the original paintings. Crucially, by achieving enhanced dynamic effects without requiring any model training or learnable parameters, our framework enables plug-and-play integration with existing I2V methods, making it an ideal solution for animating real-world paintings. More animated examples can be found on our project website.

Jianwu Fang, Lei-Lei Li, Zhedong Zheng et al.

Traffic Accident Anticipation (TAA) in traffic scenes is a challenging problem for achieving zero fatalities in the future. Current approaches typically treat TAA as a supervised learning task needing the laborious annotation of accident occurrence duration. However, the inherent long-tailed, uncertain, and fast-evolving nature of traffic scenes has the problem that real causal parts of accidents are difficult to identify and are easily dominated by data bias, resulting in a background confounding issue. Thus, we propose an Attentive Video Diffusion (AVD) model that synthesizes additional accident video clips by generating the causal part in dashcam videos, i.e., from normal clips to accident clips. AVD aims to generate causal video frames based on accident or accident-free text prompts while preserving the style and content of frames for TAA after video generation. This approach can be trained using datasets collected from various driving scenes without any extra annotations. Additionally, AVD facilitates an Equivariant TAA (EQ-TAA) with an equivariant triple loss for an anchor accident-free video clip, along with the generated pair of contrastive pseudo-normal and pseudo-accident clips. Extensive experiments have been conducted to evaluate the performance of AVD and EQ-TAA, and competitive performance compared to state-of-the-art methods has been obtained.

Lidong Zeng, Zhedong Zheng, Yinwei Wei et al.

This paper delves into the text-guided image editing task, focusing on modifying a reference image according to user-specified textual feedback to embody specific attributes. Despite recent advancements, a persistent challenge remains that the single-round generation often overlooks crucial details, particularly in the realm of fine-grained changes like shoes or sleeves. This issue compounds over multiple rounds of interaction, severely limiting customization quality. In an attempt to address this challenge, we introduce a new self-supervised regularization, \ie, multi-round regularization, which is compatible with existing methods. Specifically, the multi-round regularization encourages the model to maintain consistency across different modification orders. It builds upon the observation that the modification order generally should not affect the final result. Different from traditional one-round generation, the mechanism underpinning the proposed method is the error amplification of initially minor inaccuracies in capturing intricate details. Qualitative and quantitative experiments affirm that the proposed method achieves high-fidelity editing quality, especially the local modification, in both single-round and multiple-round generation, while also showcasing robust generalization to irregular text inputs. The effectiveness of our semantic alignment with textual feedback is further substantiated by the retrieval improvements on FahisonIQ and Fashion200k.

Yuxia Wu, Tianhao Dai, Zhedong Zheng et al.

Existing task-oriented conversational search systems heavily rely on domain ontologies with pre-defined slots and candidate value sets. In practical applications, these prerequisites are hard to meet, due to the emerging new user requirements and ever-changing scenarios. To mitigate these issues for better interaction performance, there are efforts working towards detecting out-of-vocabulary values or discovering new slots under unsupervised or semi-supervised learning paradigm. However, overemphasizing on the conversation data patterns alone induces these methods to yield noisy and arbitrary slot results. To facilitate the pragmatic utility, real-world systems tend to provide a stringent amount of human labelling quota, which offers an authoritative way to obtain accurate and meaningful slot assignments. Nonetheless, it also brings forward the high requirement of utilizing such quota efficiently. Hence, we formulate a general new slot discovery task in an information extraction fashion and incorporate it into an active learning framework to realize human-in-the-loop learning. Specifically, we leverage existing language tools to extract value candidates where the corresponding labels are further leveraged as weak supervision signals. Based on these, we propose a bi-criteria selection scheme which incorporates two major strategies, namely, uncertainty-based sampling and diversity-based sampling to efficiently identify terms of interest. We conduct extensive experiments on several public datasets and compare with a bunch of competitive baselines to demonstrate the effectiveness of our method. We have made the code and data used in this paper publicly available.

Chao Sun, Zhedong Zheng, Xiaohan Wang et al.

The manual annotation for large-scale point clouds costs a lot of time and is usually unavailable in harsh real-world scenarios. Inspired by the great success of the pre-training and fine-tuning paradigm in both vision and language tasks, we argue that pre-training is one potential solution for obtaining a scalable model to 3D point cloud downstream tasks as well. In this paper, we, therefore, explore a new self-supervised learning method, called Mixing and Disentangling (MD), for 3D point cloud representation learning. As the name implies, we mix two input shapes and demand the model learning to separate the inputs from the mixed shape. We leverage this reconstruction task as the pretext optimization objective for self-supervised learning. There are two primary advantages: 1) Compared to prevailing image datasets, eg, ImageNet, point cloud datasets are de facto small. The mixing process can provide a much larger online training sample pool. 2) On the other hand, the disentangling process motivates the model to mine the geometric prior knowledge, eg, key points. To verify the effectiveness of the proposed pretext task, we build one baseline network, which is composed of one encoder and one decoder. During pre-training, we mix two original shapes and obtain the geometry-aware embedding from the encoder, then an instance-adaptive decoder is applied to recover the original shapes from the embedding. Albeit simple, the pre-trained encoder can capture the key points of an unseen point cloud and surpasses the encoder trained from scratch on downstream tasks. The proposed method has improved the empirical performance on both ModelNet-40 and ShapeNet-Part datasets in terms of point cloud classification and segmentation tasks. We further conduct ablation studies to explore the effect of each component and verify the generalization of our proposed strategy by harnessing different backbones.

Bingwen Hu, Ping Liu, Zhedong Zheng et al.

Image-based virtual try-on is challenging in fitting a target in-shop clothes into a reference person under diverse human poses. Previous works focus on preserving clothing details ( e.g., texture, logos, patterns ) when transferring desired clothes onto a target person under a fixed pose. However, the performances of existing methods significantly dropped when extending existing methods to multi-pose virtual try-on. In this paper, we propose an end-to-end Semantic Prediction Guidance multi-pose Virtual Try-On Network (SPG-VTON), which could fit the desired clothing into a reference person under arbitrary poses. Concretely, SPG-VTON is composed of three sub-modules. First, a Semantic Prediction Module (SPM) generates the desired semantic map. The predicted semantic map provides more abundant guidance to locate the desired clothes region and produce a coarse try-on image. Second, a Clothes Warping Module (CWM) warps in-shop clothes to the desired shape according to the predicted semantic map and the desired pose. Specifically, we introduce a conductible cycle consistency loss to alleviate the misalignment in the clothes warping process. Third, a Try-on Synthesis Module (TSM) combines the coarse result and the warped clothes to generate the final virtual try-on image, preserving details of the desired clothes and under the desired pose. Besides, we introduce a face identity loss to refine the facial appearance and maintain the identity of the final virtual try-on result at the same time. We evaluate the proposed method on the most massive multi-pose dataset (MPV) and the DeepFashion dataset. The qualitative and quantitative experiments show that SPG-VTON is superior to the state-of-the-art methods and is robust to the data noise, including background and accessory changes, i.e., hats and handbags, showing good scalability to the real-world scenario.

Kezhou Lin, Xiaohan Wang, Zhedong Zheng et al.

Obtaining viewer responses from videos can be useful for creators and streaming platforms to analyze the video performance and improve the future user experience. In this report, we present our method for 2021 Evoked Expression from Videos Challenge. In particular, our model utilizes both audio and image modalities as inputs to predict emotion changes of viewers. To model long-range emotion changes, we use a GRU-based model to predict one sparse signal with 1Hz. We observe that the emotion changes are smooth. Therefore, the final dense prediction is obtained via linear interpolating the signal, which is robust to the prediction fluctuation. Albeit simple, the proposed method has achieved pearson's correlation score of 0.04430 on the final private test set.

Zhedong Zheng, Yi Yang

Domain adaptation is to transfer the shared knowledge learned from the source domain to a new environment, i.e., target domain. One common practice is to train the model on both labeled source-domain data and unlabeled target-domain data. Yet the learned models are usually biased due to the strong supervision of the source domain. Most researchers adopt the early-stopping strategy to prevent over-fitting, but when to stop training remains a challenging problem since the lack of the target-domain validation set. In this paper, we propose one efficient bootstrapping method, called Adaboost Student, explicitly learning complementary models during training and liberating users from empirical early stopping. Adaboost Student combines the deep model learning with the conventional training strategy, i.e., adaptive boosting, and enables interactions between learned models and the data sampler. We adopt one adaptive data sampler to progressively facilitate learning on hard samples and aggregate "weak" models to prevent over-fitting. Extensive experiments show that (1) Without the need to worry about the stopping time, AdaBoost Student provides one robust solution by efficient complementary model learning during training. (2) AdaBoost Student is orthogonal to most domain adaptation methods, which can be combined with existing approaches to further improve the state-of-the-art performance. We have achieved competitive results on three widely-used scene segmentation domain adaptation benchmarks.

Chuchu Han, Zhedong Zheng, Changxin Gao et al.

The goal of person search is to localize and match query persons from scene images. For high efficiency, one-step methods have been developed to jointly handle the pedestrian detection and identification sub-tasks using a single network. There are two major challenges in the current one-step approaches. One is the mutual interference between the optimization objectives of multiple sub-tasks. The other is the sub-optimal identification feature learning caused by small batch size when end-to-end training. To overcome these problems, we propose a decoupled and memory-reinforced network (DMRNet). Specifically, to reconcile the conflicts of multiple objectives, we simplify the standard tightly coupled pipelines and establish a deeply decoupled multi-task learning framework. Further, we build a memory-reinforced mechanism to boost the identification feature learning. By queuing the identification features of recently accessed instances into a memory bank, the mechanism augments the similarity pair construction for pairwise metric learning. For better encoding consistency of the stored features, a slow-moving average of the network is applied for extracting these features. In this way, the dual networks reinforce each other and converge to robust solution states. Experimentally, the proposed method obtains 93.2% and 46.9% mAP on CUHK-SYSU and PRW datasets, which exceeds all the existing one-step methods.

Xuanmeng Zhang, Minyue Jiang, Zhedong Zheng et al.

The re-ranking approach leverages high-confidence retrieved samples to refine retrieval results, which have been widely adopted as a post-processing tool for image retrieval tasks. However, we notice one main flaw of re-ranking, i.e., high computational complexity, which leads to an unaffordable time cost for real-world applications. In this paper, we revisit re-ranking and demonstrate that re-ranking can be reformulated as a high-parallelism Graph Neural Network (GNN) function. In particular, we divide the conventional re-ranking process into two phases, i.e., retrieving high-quality gallery samples and updating features. We argue that the first phase equals building the k-nearest neighbor graph, while the second phase can be viewed as spreading the message within the graph. In practice, GNN only needs to concern vertices with the connected edges. Since the graph is sparse, we can efficiently update the vertex features. On the Market-1501 dataset, we accelerate the re-ranking processing from 89.2s to 9.4ms with one K40m GPU, facilitating the real-time post-processing. Similarly, we observe that our method achieves comparable or even better retrieval results on the other four image retrieval benchmarks, i.e., VeRi-776, Oxford-5k, Paris-6k and University-1652, with limited time cost. Our code is publicly available.

Tingyu Wang, Zhedong Zheng, Chenggang Yan et al.

Cross-view geo-localization is to spot images of the same geographic target from different platforms, e.g., drone-view cameras and satellites. It is challenging in the large visual appearance changes caused by extreme viewpoint variations. Existing methods usually concentrate on mining the fine-grained feature of the geographic target in the image center, but underestimate the contextual information in neighbor areas. In this work, we argue that neighbor areas can be leveraged as auxiliary information, enriching discriminative clues for geolocalization. Specifically, we introduce a simple and effective deep neural network, called Local Pattern Network (LPN), to take advantage of contextual information in an end-to-end manner. Without using extra part estimators, LPN adopts a square-ring feature partition strategy, which provides the attention according to the distance to the image center. It eases the part matching and enables the part-wise representation learning. Owing to the square-ring partition design, the proposed LPN has good scalability to rotation variations and achieves competitive results on three prevailing benchmarks, i.e., University-1652, CVUSA and CVACT. Besides, we also show the proposed LPN can be easily embedded into other frameworks to further boost performance.

Zhedong Zheng, Tao Ruan, Yunchao Wei et al.

One fundamental challenge of vehicle re-identification (re-id) is to learn robust and discriminative visual representation, given the significant intra-class vehicle variations across different camera views. As the existing vehicle datasets are limited in terms of training images and viewpoints, we propose to build a unique large-scale vehicle dataset (called VehicleNet) by harnessing four public vehicle datasets, and design a simple yet effective two-stage progressive approach to learning more robust visual representation from VehicleNet. The first stage of our approach is to learn the generic representation for all domains (i.e., source vehicle datasets) by training with the conventional classification loss. This stage relaxes the full alignment between the training and testing domains, as it is agnostic to the target vehicle domain. The second stage is to fine-tune the trained model purely based on the target vehicle set, by minimizing the distribution discrepancy between our VehicleNet and any target domain. We discuss our proposed multi-source dataset VehicleNet and evaluate the effectiveness of the two-stage progressive representation learning through extensive experiments. We achieve the state-of-art accuracy of 86.07% mAP on the private test set of AICity Challenge, and competitive results on two other public vehicle re-id datasets, i.e., VeRi-776 and VehicleID. We hope this new VehicleNet dataset and the learned robust representations can pave the way for vehicle re-id in the real-world environments.

Zhedong Zheng, Yi Yang

This paper focuses on the unsupervised domain adaptation of transferring the knowledge from the source domain to the target domain in the context of semantic segmentation. Existing approaches usually regard the pseudo label as the ground truth to fully exploit the unlabeled target-domain data. Yet the pseudo labels of the target-domain data are usually predicted by the model trained on the source domain. Thus, the generated labels inevitably contain the incorrect prediction due to the discrepancy between the training domain and the test domain, which could be transferred to the final adapted model and largely compromises the training process. To overcome the problem, this paper proposes to explicitly estimate the prediction uncertainty during training to rectify the pseudo label learning for unsupervised semantic segmentation adaptation. Given the input image, the model outputs the semantic segmentation prediction as well as the uncertainty of the prediction. Specifically, we model the uncertainty via the prediction variance and involve the uncertainty into the optimization objective. To verify the effectiveness of the proposed method, we evaluate the proposed method on two prevalent synthetic-to-real semantic segmentation benchmarks, i.e., GTA5 -> Cityscapes and SYNTHIA -> Cityscapes, as well as one cross-city benchmark, i.e., Cityscapes -> Oxford RobotCar. We demonstrate through extensive experiments that the proposed approach (1) dynamically sets different confidence thresholds according to the prediction variance, (2) rectifies the learning from noisy pseudo labels, and (3) achieves significant improvements over the conventional pseudo label learning and yields competitive performance on all three benchmarks.