Jian Wang

Xiaohu Huang, Hao Zhou, Jian Wang et al.

In the field of skeleton-based action recognition, current top-performing graph convolutional networks (GCNs) exploit intra-sequence context to construct adaptive graphs for feature aggregation. However, we argue that such context is still \textit{local} since the rich cross-sequence relations have not been explicitly investigated. In this paper, we propose a graph contrastive learning framework for skeleton-based action recognition (\textit{SkeletonGCL}) to explore the \textit{global} context across all sequences. In specific, SkeletonGCL associates graph learning across sequences by enforcing graphs to be class-discriminative, \emph{i.e.,} intra-class compact and inter-class dispersed, which improves the GCN capacity to distinguish various action patterns. Besides, two memory banks are designed to enrich cross-sequence context from two complementary levels, \emph{i.e.,} instance and semantic levels, enabling graph contrastive learning in multiple context scales. Consequently, SkeletonGCL establishes a new training paradigm, and it can be seamlessly incorporated into current GCNs. Without loss of generality, we combine SkeletonGCL with three GCNs (2S-ACGN, CTR-GCN, and InfoGCN), and achieve consistent improvements on NTU60, NTU120, and NW-UCLA benchmarks. The source code will be available at \url{https://github.com/OliverHxh/SkeletonGCL}.

Huan Liu, Qiang Chen, Zichang Tan et al.

In this paper, we study the problem of end-to-end multi-person pose estimation. State-of-the-art solutions adopt the DETR-like framework, and mainly develop the complex decoder, e.g., regarding pose estimation as keypoint box detection and combining with human detection in ED-Pose, hierarchically predicting with pose decoder and joint (keypoint) decoder in PETR. We present a simple yet effective transformer approach, named Group Pose. We simply regard $K$-keypoint pose estimation as predicting a set of $N\times K$ keypoint positions, each from a keypoint query, as well as representing each pose with an instance query for scoring $N$ pose predictions. Motivated by the intuition that the interaction, among across-instance queries of different types, is not directly helpful, we make a simple modification to decoder self-attention. We replace single self-attention over all the $N\times(K+1)$ queries with two subsequent group self-attentions: (i) $N$ within-instance self-attention, with each over $K$ keypoint queries and one instance query, and (ii) $(K+1)$ same-type across-instance self-attention, each over $N$ queries of the same type. The resulting decoder removes the interaction among across-instance type-different queries, easing the optimization and thus improving the performance. Experimental results on MS COCO and CrowdPose show that our approach without human box supervision is superior to previous methods with complex decoders, and even is slightly better than ED-Pose that uses human box supervision. $\href{https://github.com/Michel-liu/GroupPose-Paddle}{\rm Paddle}$ and $\href{https://github.com/Michel-liu/GroupPose}{\rm PyTorch}$ code are available.

Guowei Chen, Yi Liu, Jian Wang et al.

Natural image matting is a fundamental and challenging computer vision task. It has many applications in image editing and composition. Recently, deep learning-based approaches have achieved great improvements in image matting. However, most of them require a user-supplied trimap as an auxiliary input, which limits the matting applications in the real world. Although some trimap-free approaches have been proposed, the matting quality is still unsatisfactory compared to trimap-based ones. Without the trimap guidance, the matting models suffer from foreground-background ambiguity easily, and also generate blurry details in the transition area. In this work, we propose PP-Matting, a trimap-free architecture that can achieve high-accuracy natural image matting. Our method applies a high-resolution detail branch (HRDB) that extracts fine-grained details of the foreground with keeping feature resolution unchanged. Also, we propose a semantic context branch (SCB) that adopts a semantic segmentation subtask. It prevents the detail prediction from local ambiguity caused by semantic context missing. In addition, we conduct extensive experiments on two well-known benchmarks: Composition-1k and Distinctions-646. The results demonstrate the superiority of PP-Matting over previous methods. Furthermore, we provide a qualitative evaluation of our method on human matting which shows its outstanding performance in the practical application. The code and pre-trained models will be available at PaddleSeg: https://github.com/PaddlePaddle/PaddleSeg.

Hiroyasu Akada, Jian Wang, Soshi Shimada et al.

We present UnrealEgo, i.e., a new large-scale naturalistic dataset for egocentric 3D human pose estimation. UnrealEgo is based on an advanced concept of eyeglasses equipped with two fisheye cameras that can be used in unconstrained environments. We design their virtual prototype and attach them to 3D human models for stereo view capture. We next generate a large corpus of human motions. As a consequence, UnrealEgo is the first dataset to provide in-the-wild stereo images with the largest variety of motions among existing egocentric datasets. Furthermore, we propose a new benchmark method with a simple but effective idea of devising a 2D keypoint estimation module for stereo inputs to improve 3D human pose estimation. The extensive experiments show that our approach outperforms the previous state-of-the-art methods qualitatively and quantitatively. UnrealEgo and our source codes are available on our project web page.

Jian Wang, Lingjie Liu, Weipeng Xu et al.

Egocentric 3D human pose estimation with a single head-mounted fisheye camera has recently attracted attention due to its numerous applications in virtual and augmented reality. Existing methods still struggle in challenging poses where the human body is highly occluded or is closely interacting with the scene. To address this issue, we propose a scene-aware egocentric pose estimation method that guides the prediction of the egocentric pose with scene constraints. To this end, we propose an egocentric depth estimation network to predict the scene depth map from a wide-view egocentric fisheye camera while mitigating the occlusion of the human body with a depth-inpainting network. Next, we propose a scene-aware pose estimation network that projects the 2D image features and estimated depth map of the scene into a voxel space and regresses the 3D pose with a V2V network. The voxel-based feature representation provides the direct geometric connection between 2D image features and scene geometry, and further facilitates the V2V network to constrain the predicted pose based on the estimated scene geometry. To enable the training of the aforementioned networks, we also generated a synthetic dataset, called EgoGTA, and an in-the-wild dataset based on EgoPW, called EgoPW-Scene. The experimental results of our new evaluation sequences show that the predicted 3D egocentric poses are accurate and physically plausible in terms of human-scene interaction, demonstrating that our method outperforms the state-of-the-art methods both quantitatively and qualitatively.

Jian Wang, Zhe Cao, Diogo Luvizon et al.

In this work, we explore egocentric whole-body motion capture using a single fisheye camera, which simultaneously estimates human body and hand motion. This task presents significant challenges due to three factors: the lack of high-quality datasets, fisheye camera distortion, and human body self-occlusion. To address these challenges, we propose a novel approach that leverages FisheyeViT to extract fisheye image features, which are subsequently converted into pixel-aligned 3D heatmap representations for 3D human body pose prediction. For hand tracking, we incorporate dedicated hand detection and hand pose estimation networks for regressing 3D hand poses. Finally, we develop a diffusion-based whole-body motion prior model to refine the estimated whole-body motion while accounting for joint uncertainties. To train these networks, we collect a large synthetic dataset, EgoWholeBody, comprising 840,000 high-quality egocentric images captured across a diverse range of whole-body motion sequences. Quantitative and qualitative evaluations demonstrate the effectiveness of our method in producing high-quality whole-body motion estimates from a single egocentric camera.

Yang Bai, Desen Zhou, Songyang Zhang et al.

Action Quality Assessment(AQA) is important for action understanding and resolving the task poses unique challenges due to subtle visual differences. Existing state-of-the-art methods typically rely on the holistic video representations for score regression or ranking, which limits the generalization to capture fine-grained intra-class variation. To overcome the above limitation, we propose a temporal parsing transformer to decompose the holistic feature into temporal part-level representations. Specifically, we utilize a set of learnable queries to represent the atomic temporal patterns for a specific action. Our decoding process converts the frame representations to a fixed number of temporally ordered part representations. To obtain the quality score, we adopt the state-of-the-art contrastive regression based on the part representations. Since existing AQA datasets do not provide temporal part-level labels or partitions, we propose two novel loss functions on the cross attention responses of the decoder: a ranking loss to ensure the learnable queries to satisfy the temporal order in cross attention and a sparsity loss to encourage the part representations to be more discriminative. Extensive experiments show that our proposed method outperforms prior work on three public AQA benchmarks by a considerable margin.

Youming Deng, Yansheng Li, Yongjun Zhang et al.

As far as Scene Graph Generation (SGG), coarse and fine predicates mix in the dataset due to the crowd-sourced labeling, and the long-tail problem is also pronounced. Given this tricky situation, many existing SGG methods treat the predicates equally and learn the model under the supervision of mixed-granularity predicates in one stage, leading to relatively coarse predictions. In order to alleviate the negative impact of the suboptimum mixed-granularity annotation and long-tail effect problems, this paper proposes a novel Hierarchical Memory Learning (HML) framework to learn the model from simple to complex, which is similar to the human beings' hierarchical memory learning process. After the autonomous partition of coarse and fine predicates, the model is first trained on the coarse predicates and then learns the fine predicates. In order to realize this hierarchical learning pattern, this paper, for the first time, formulates the HML framework using the new Concept Reconstruction (CR) and Model Reconstruction (MR) constraints. It is worth noticing that the HML framework can be taken as one general optimization strategy to improve various SGG models, and significant improvement can be achieved on the SGG benchmark (i.e., Visual Genome).

Zhongwei Qiu, Yang Qiansheng, Jian Wang et al.

Existing methods of multi-person video 3D human Pose and Shape Estimation (PSE) typically adopt a two-stage strategy, which first detects human instances in each frame and then performs single-person PSE with temporal model. However, the global spatio-temporal context among spatial instances can not be captured. In this paper, we propose a new end-to-end multi-person 3D Pose and Shape estimation framework with progressive Video Transformer, termed PSVT. In PSVT, a spatio-temporal encoder (STE) captures the global feature dependencies among spatial objects. Then, spatio-temporal pose decoder (STPD) and shape decoder (STSD) capture the global dependencies between pose queries and feature tokens, shape queries and feature tokens, respectively. To handle the variances of objects as time proceeds, a novel scheme of progressive decoding is used to update pose and shape queries at each frame. Besides, we propose a novel pose-guided attention (PGA) for shape decoder to better predict shape parameters. The two components strengthen the decoder of PSVT to improve performance. Extensive experiments on the four datasets show that PSVT achieves stage-of-the-art results.

Tailin Chen, Desen Zhou, Jian Wang et al.

In this paper, we study the problem of one-shot skeleton-based action recognition, which poses unique challenges in learning transferable representation from base classes to novel classes, particularly for fine-grained actions. Existing meta-learning frameworks typically rely on the body-level representations in spatial dimension, which limits the generalisation to capture subtle visual differences in the fine-grained label space. To overcome the above limitation, we propose a part-aware prototypical representation for one-shot skeleton-based action recognition. Our method captures skeleton motion patterns at two distinctive spatial levels, one for global contexts among all body joints, referred to as body level, and the other attends to local spatial regions of body parts, referred to as the part level. We also devise a class-agnostic attention mechanism to highlight important parts for each action class. Specifically, we develop a part-aware prototypical graph network consisting of three modules: a cascaded embedding module for our dual-level modelling, an attention-based part fusion module to fuse parts and generate part-aware prototypes, and a matching module to perform classification with the part-aware representations. We demonstrate the effectiveness of our method on two public skeleton-based action recognition datasets: NTU RGB+D 120 and NW-UCLA.

Zhongwei Qiu, Qiansheng Yang, Jian Wang et al.

One of the mainstream schemes for 2D human pose estimation (HPE) is learning keypoints heatmaps by a neural network. Existing methods typically improve the quality of heatmaps by customized architectures, such as high-resolution representation and vision Transformers. In this paper, we propose \textbf{DiffusionPose}, a new scheme that formulates 2D HPE as a keypoints heatmaps generation problem from noised heatmaps. During training, the keypoints are diffused to random distribution by adding noises and the diffusion model learns to recover ground-truth heatmaps from noised heatmaps with respect to conditions constructed by image feature. During inference, the diffusion model generates heatmaps from initialized heatmaps in a progressive denoising way. Moreover, we further explore improving the performance of DiffusionPose with conditions from human structural information. Extensive experiments show the prowess of our DiffusionPose, with improvements of 1.6, 1.2, and 1.2 mAP on widely-used COCO, CrowdPose, and AI Challenge datasets, respectively.

Zhanghao Sun, Jian Wang, Yicheng Wu et al.

Flash illumination is widely used in imaging under low-light environments. However, illumination intensity falls off with propagation distance quadratically, which poses significant challenges for flash imaging at a long distance. We propose a new flash technique, named ``patterned flash'', for flash imaging at a long distance. Patterned flash concentrates optical power into a dot array. Compared with the conventional uniform flash where the signal is overwhelmed by the noise everywhere, patterned flash provides stronger signals at sparsely distributed points across the field of view to ensure the signals at those points stand out from the sensor noise. This enables post-processing to resolve important objects and details. Additionally, the patterned flash projects texture onto the scene, which can be treated as a structured light system for depth perception. Given the novel system, we develop a joint image reconstruction and depth estimation algorithm with a convolutional neural network. We build a hardware prototype and test the proposed flash technique on various scenes. The experimental results demonstrate that our patterned flash has significantly better performance at long distances in low-light environments.

Zhichao Liu, Leshan Wang, Desen Zhou et al.

Recognizing human actions from untrimmed videos is an important task in activity understanding, and poses unique challenges in modeling long-range temporal relations. Recent works adopt a predict-and-refine strategy which converts an initial prediction to action segments for global context modeling. However, the generated segment representations are often noisy and exhibit inaccurate segment boundaries, over-segmentation and other problems. To deal with these issues, we propose an attention based approach which we call \textit{temporal segment transformer}, for joint segment relation modeling and denoising. The main idea is to denoise segment representations using attention between segment and frame representations, and also use inter-segment attention to capture temporal correlations between segments. The refined segment representations are used to predict action labels and adjust segment boundaries, and a final action segmentation is produced based on voting from segment masks. We show that this novel architecture achieves state-of-the-art accuracy on the popular 50Salads, GTEA and Breakfast benchmarks. We also conduct extensive ablations to demonstrate the effectiveness of different components of our design.

Jian Wang, Liang Qiao, Shichong Zhou et al.

Deep learning (DL) has proven highly effective for ultrasound-based computer-aided diagnosis (CAD) of breast cancers. In an automaticCAD system, lesion detection is critical for the following diagnosis. However, existing DL-based methods generally require voluminous manually-annotated region of interest (ROI) labels and class labels to train both the lesion detection and diagnosis models. In clinical practice, the ROI labels, i.e. ground truths, may not always be optimal for the classification task due to individual experience of sonologists, resulting in the issue of coarse annotation that limits the diagnosis performance of a CAD model. To address this issue, a novel Two-Stage Detection and Diagnosis Network (TSDDNet) is proposed based on weakly supervised learning to enhance diagnostic accuracy of the ultrasound-based CAD for breast cancers. In particular, all the ROI-level labels are considered as coarse labels in the first training stage, and then a candidate selection mechanism is designed to identify optimallesion areas for both the fully and partially annotated samples. It refines the current ROI-level labels in the fully annotated images and the detected ROIs in the partially annotated samples with a weakly supervised manner under the guidance of class labels. In the second training stage, a self-distillation strategy further is further proposed to integrate the detection network and classification network into a unified framework as the final CAD model for joint optimization, which then further improves the diagnosis performance. The proposed TSDDNet is evaluated on a B-mode ultrasound dataset, and the experimental results show that it achieves the best performance on both lesion detection and diagnosis tasks, suggesting promising application potential.

Mengchu Xu, Yuxuan Zhang, Jian Wang

Sparse phase retrieval aims to recover a $k$-sparse signal from $m$ phaseless measurements. While the theoretically optimal sample complexity for successful recovery is $Ω(k \log n)$, existing algorithms can only achieve this bound for signals with specific structural assumptions, leading to a notable gap between theory and practice. To bridge this gap, we introduce an efficient initialization algorithm, termed generalized Exponential Spectral Pursuit (gESP). We prove that gESP can significantly expand the family of signals that are guaranteed to be recovered with the optimal sample complexity, thereby extending the scope of theoretical optimality to a much broader class of signals. Extensive simulations validate our theoretical findings and demonstrate that gESP consistently outperforms the state-of-the-art methods across diverse signal types.

Chaoyu Chen, Xin Yang, Rusi Chen et al.

Ultrasound (US) image segmentation is an active research area that requires real-time and highly accurate analysis in many scenarios. The detect-to-segment (DTS) frameworks have been recently proposed to balance accuracy and efficiency. However, existing approaches may suffer from inadequate contour encoding or fail to effectively leverage the encoded results. In this paper, we introduce a novel Fourier-anchor-based DTS framework called Fourier Feature Pyramid Network (FFPN) to address the aforementioned issues. The contributions of this paper are two fold. First, the FFPN utilizes Fourier Descriptors to adequately encode contours. Specifically, it maps Fourier series with similar amplitudes and frequencies into the same layer of the feature map, thereby effectively utilizing the encoded Fourier information. Second, we propose a Contour Sampling Refinement (CSR) module based on the contour proposals and refined features produced by the FFPN. This module extracts rich features around the predicted contours to further capture detailed information and refine the contours. Extensive experimental results on three large and challenging datasets demonstrate that our method outperforms other DTS methods in terms of accuracy and efficiency. Furthermore, our framework can generalize well to other detection or segmentation tasks.

Zhongwei Qiu, Qiansheng Yang, Jian Wang et al.

Multi-person 3D pose estimation is a challenging task because of occlusion and depth ambiguity, especially in the cases of crowd scenes. To solve these problems, most existing methods explore modeling body context cues by enhancing feature representation with graph neural networks or adding structural constraints. However, these methods are not robust for their single-root formulation that decoding 3D poses from a root node with a pre-defined graph. In this paper, we propose GR-M3D, which models the \textbf{M}ulti-person \textbf{3D} pose estimation with dynamic \textbf{G}raph \textbf{R}easoning. The decoding graph in GR-M3D is predicted instead of pre-defined. In particular, It firstly generates several data maps and enhances them with a scale and depth aware refinement module (SDAR). Then multiple root keypoints and dense decoding paths for each person are estimated from these data maps. Based on them, dynamic decoding graphs are built by assigning path weights to the decoding paths, while the path weights are inferred from those enhanced data maps. And this process is named dynamic graph reasoning (DGR). Finally, the 3D poses are decoded according to dynamic decoding graphs for each detected person. GR-M3D can adjust the structure of the decoding graph implicitly by adopting soft path weights according to input data, which makes the decoding graphs be adaptive to different input persons to the best extent and more capable of handling occlusion and depth ambiguity than previous methods. We empirically show that the proposed bottom-up approach even outperforms top-down methods and achieves state-of-the-art results on three 3D pose datasets.

Zhongwei Qiu, Qiansheng Yang, Jian Wang et al.

Video 3D human pose estimation aims to localize the 3D coordinates of human joints from videos. Recent transformer-based approaches focus on capturing the spatiotemporal information from sequential 2D poses, which cannot model the contextual depth feature effectively since the visual depth features are lost in the step of 2D pose estimation. In this paper, we simplify the paradigm into an end-to-end framework, Instance-guided Video Transformer (IVT), which enables learning spatiotemporal contextual depth information from visual features effectively and predicts 3D poses directly from video frames. In particular, we firstly formulate video frames as a series of instance-guided tokens and each token is in charge of predicting the 3D pose of a human instance. These tokens contain body structure information since they are extracted by the guidance of joint offsets from the human center to the corresponding body joints. Then, these tokens are sent into IVT for learning spatiotemporal contextual depth. In addition, we propose a cross-scale instance-guided attention mechanism to handle the variational scales among multiple persons. Finally, the 3D poses of each person are decoded from instance-guided tokens by coordinate regression. Experiments on three widely-used 3D pose estimation benchmarks show that the proposed IVT achieves state-of-the-art performances.

Xinxin Zhou, Jingru Feng, Jian Wang et al.

Load forecasting is very essential in the analysis and grid planning of power systems. For this reason, we first propose a household load forecasting method based on federated deep learning and non-intrusive load monitoring (NILM). For all we know, this is the first research on federated learning (FL) in household load forecasting based on NILM. In this method, the integrated power is decomposed into individual device power by non-intrusive load monitoring, and the power of individual appliances is predicted separately using a federated deep learning model. Finally, the predicted power values of individual appliances are aggregated to form the total power prediction. Specifically, by separately predicting the electrical equipment to obtain the predicted power, it avoids the error caused by the strong time dependence in the power signal of a single device. And in the federated deep learning prediction model, the household owners with the power data share the parameters of the local model instead of the local power data, guaranteeing the privacy of the household user data. The case results demonstrate that the proposed approach provides a better prediction effect than the traditional methodology that directly predicts the aggregated signal as a whole. In addition, experiments in various federated learning environments are designed and implemented to validate the validity of this methodology.

Donghui Hu, Yu Zhang, Cong Yu et al.

Image steganography is the art and science of using images as cover for covert communications. With the development of neural networks, traditional image steganography is more likely to be detected by deep learning-based steganalysis. To improve upon this, we propose image steganography network based on style transfer, and the embedding of secret messages can be disguised as image stylization. We embed secret information while transforming the content image style. In latent space, the secret information is integrated into the latent representation of the cover image to generate the stego images, which are indistinguishable from normal stylized images. It is an end-to-end unsupervised model without pre-training. Extensive experiments on the benchmark dataset demonstrate the reliability, quality and security of stego images generated by our steganographic network.

Yunpeng Qu, Zhilin Lu, Rui Zeng et al.

Automatic Modulation Recognition (AMR) plays a crucial role in wireless communication systems. Deep learning AMR strategies have achieved tremendous success in recent years. Modulated signals exhibit long temporal dependencies, and extracting global features is crucial in identifying modulation schemes. Traditionally, human experts analyze patterns in constellation diagrams to classify modulation schemes. Classical convolutional-based networks, due to their limited receptive fields, excel at extracting local features but struggle to capture global relationships. To address this limitation, we introduce a novel hybrid deep framework named TLDNN, which incorporates the architectures of the transformer and long short-term memory (LSTM). We utilize the self-attention mechanism of the transformer to model the global correlations in signal sequences while employing LSTM to enhance the capture of temporal dependencies. To mitigate the impact like RF fingerprint features and channel characteristics on model generalization, we propose data augmentation strategies known as segment substitution (SS) to enhance the model's robustness to modulation-related features. Experimental results on widely-used datasets demonstrate that our method achieves state-of-the-art performance and exhibits significant advantages in terms of complexity. Our proposed framework serves as a foundational backbone that can be extended to different datasets. We have verified the effectiveness of our augmentation approach in enhancing the generalization of the models, particularly in few-shot scenarios. Code is available at \url{https://github.com/AMR-Master/TLDNN}.

Surjya Ray, Pratik Mehta, Hongen Zhang et al.

The precipitous rise and adoption of Large Language Models (LLMs) have shattered expectations with the fastest adoption rate of any consumer-facing technology in history. Healthcare, a field that traditionally uses NLP techniques, was bound to be affected by this meteoric rise. In this paper, we gauge the extent of the impact by evaluating the performance of LLMs for the task of medical coding on real-life noisy data. We conducted several experiments on MIMIC III and IV datasets with encoder-based LLMs, such as BERT. Furthermore, we developed Segmented Harmonic Loss, a new loss function to address the extreme class imbalance that we found to prevail in most medical data in a multi-label scenario by segmenting and decoupling co-occurring classes of the dataset with a new segmentation algorithm. We also devised a technique based on embedding similarity to tackle noisy data. Our experimental results show that when trained with the proposed loss, the LLMs achieve significant performance gains even on noisy long-tailed datasets, outperforming the F1 score of the state-of-the-art by over ten percentage points.

Jian Wang, Lijun He, Yixing Yong et al.

Modern autonomous driving (AD) systems leverage 3D object detection to perceive foreground objects in 3D environments for subsequent prediction and planning. Visual 3D detection based on RGB cameras provides a cost-effective solution compared to the LiDAR paradigm. While achieving promising detection accuracy, current deep neural network-based models remain highly susceptible to adversarial examples. The underlying safety concerns motivate us to investigate realistic adversarial attacks in AD scenarios. Previous work has demonstrated the feasibility of placing adversarial posters on the road surface to induce hallucinations in the detector. However, the unnatural appearance of the posters makes them easily noticeable by humans, and their fixed content can be readily targeted and defended. To address these limitations, we propose the AdvRoad to generate diverse road-style adversarial posters. The adversaries have naturalistic appearances resembling the road surface while compromising the detector to perceive non-existent objects at the attack locations. We employ a two-stage approach, termed Road-Style Adversary Generation and Scenario-Associated Adaptation, to maximize the attack effectiveness on the input scene while ensuring the natural appearance of the poster, allowing the attack to be carried out stealthily without drawing human attention. Extensive experiments show that AdvRoad generalizes well to different detectors, scenes, and spoofing locations. Moreover, physical attacks further demonstrate the practical threats in real-world environments.

Zhiyin Shao, Xinyu Zhang, Changxing Ding et al.

The pre-training task is indispensable for the text-to-image person re-identification (T2I-ReID) task. However, there are two underlying inconsistencies between these two tasks that may impact the performance; i) Data inconsistency. A large domain gap exists between the generic images/texts used in public pre-trained models and the specific person data in the T2I-ReID task. This gap is especially severe for texts, as general textual data are usually unable to describe specific people in fine-grained detail. ii) Training inconsistency. The processes of pre-training of images and texts are independent, despite cross-modality learning being critical to T2I-ReID. To address the above issues, we present a new unified pre-training pipeline (UniPT) designed specifically for the T2I-ReID task. We first build a large-scale text-labeled person dataset "LUPerson-T", in which pseudo-textual descriptions of images are automatically generated by the CLIP paradigm using a divide-conquer-combine strategy. Benefiting from this dataset, we then utilize a simple vision-and-language pre-training framework to explicitly align the feature space of the image and text modalities during pre-training. In this way, the pre-training task and the T2I-ReID task are made consistent with each other on both data and training levels. Without the need for any bells and whistles, our UniPT achieves competitive Rank-1 accuracy of, ie, 68.50%, 60.09%, and 51.85% on CUHK-PEDES, ICFG-PEDES and RSTPReid, respectively. Both the LUPerson-T dataset and code are available at https;//github.com/ZhiyinShao-H/UniPT.

Hiroyasu Akada, Jian Wang, Vladislav Golyanik et al.

While head-mounted devices are becoming more compact, they provide egocentric views with significant self-occlusions of the device user. Hence, existing methods often fail to accurately estimate complex 3D poses from egocentric views. In this work, we propose a new transformer-based framework to improve egocentric stereo 3D human pose estimation, which leverages the scene information and temporal context of egocentric stereo videos. Specifically, we utilize 1) depth features from our 3D scene reconstruction module with uniformly sampled windows of egocentric stereo frames, and 2) human joint queries enhanced by temporal features of the video inputs. Our method is able to accurately estimate human poses even in challenging scenarios, such as crouching and sitting. Furthermore, we introduce two new benchmark datasets, i.e., UnrealEgo2 and UnrealEgo-RW (RealWorld). The proposed datasets offer a much larger number of egocentric stereo views with a wider variety of human motions than the existing datasets, allowing comprehensive evaluation of existing and upcoming methods. Our extensive experiments show that the proposed approach significantly outperforms previous methods. We will release UnrealEgo2, UnrealEgo-RW, and trained models on our project page.

Jusheng Zhang, Zimeng Huang, Yijia Fan et al.

As scaling large language models faces prohibitive costs, multi-agent systems emerge as a promising alternative, though challenged by static knowledge assumptions and coordination inefficiencies. We introduces Knowledge-Aware Bayesian Bandits (KABB), a novel framework that enhances multi-agent system coordination through semantic understanding and dynamic adaptation. The framework features three key innovations: a three-dimensional knowledge distance model for deep semantic understanding, a dual-adaptation mechanism for continuous expert optimization, and a knowledge-aware Thompson Sampling strategy for efficient expert selection. Extensive evaluation demonstrates KABB achieves an optimal cost-performance balance, maintaining high performance while keeping computational demands relatively low in multi-agent coordination.

Qingpei Guo, Furong Xu, Hanxiao Zhang et al.

Vision-language foundation models like CLIP have revolutionized the field of artificial intelligence. Nevertheless, VLM models supporting multi-language, e.g., in both Chinese and English, have lagged due to the relative scarcity of large-scale pretraining datasets. Toward this end, we introduce a comprehensive bilingual (Chinese-English) dataset BM-6B with over 6 billion image-text pairs, aimed at enhancing multimodal foundation models to well understand images in both languages. To handle such a scale of dataset, we propose a novel grouped aggregation approach for image-text contrastive loss computation, which reduces the communication overhead and GPU memory demands significantly, facilitating a 60% increase in training speed. We pretrain a series of bilingual image-text foundation models with an enhanced fine-grained understanding ability on BM-6B, the resulting models, dubbed as $M^2$-Encoders (pronounced "M-Square"), set new benchmarks in both languages for multimodal retrieval and classification tasks. Notably, Our largest $M^2$-Encoder-10B model has achieved top-1 accuracies of 88.5% on ImageNet and 80.7% on ImageNet-CN under a zero-shot classification setting, surpassing previously reported SoTA methods by 2.2% and 21.1%, respectively. The $M^2$-Encoder series represents one of the most comprehensive bilingual image-text foundation models to date, so we are making it available to the research community for further exploration and development.

Jian Wang, Yue Zhuo

The visual anomaly diagnosis can automatically analyze the defective products, which has been widely applied in industrial quality inspection. The anomaly classification can classify the defective products into different categories. However, the anomaly samples are hard to access in practice, which impedes the training of canonical machine learning models. This paper studies a practical issue that anomaly samples for training are extremely scarce, i.e., few-shot learning (FSL). Utilizing the sufficient normal samples, we propose PatchProto networks for few-shot anomaly classification. Different from classical FSL methods, PatchProto networks only extract CNN features of defective regions of interest, which serves as the prototypes for few-shot learning. Compared with basic few-shot classifier, the experiment results on MVTec-AD dataset show PatchProto networks significantly improve the few-shot anomaly classification accuracy.

Hiroyasu Akada, Jian Wang, Vladislav Golyanik et al.

Egocentric 3D human pose estimation has been actively studied using cameras installed in front of a head-mounted device (HMD). While frontal placement is the optimal and the only option for some tasks, such as hand tracking, it remains unclear if the same holds for full-body tracking due to self-occlusion and limited field-of-view coverage. Notably, even the state-of-the-art methods often fail to estimate accurate 3D poses in many scenarios, such as when HMD users tilt their heads upward -- a common motion in human activities. A key limitation of existing HMD designs is their neglect of the back of the body, despite its potential to provide crucial 3D reconstruction cues. Hence, this paper investigates the usefulness of rear cameras for full-body tracking. We also show that simply adding rear views to the frontal inputs is not optimal for existing methods due to their dependence on individual 2D joint detectors without effective multi-view integration. To address this issue, we propose a new transformer-based method that refines 2D joint heatmap estimation with multi-view information and heatmap uncertainty, thereby improving 3D pose tracking. Also, we introduce two new large-scale datasets, Ego4View-Syn and Ego4View-RW, for a rear-view evaluation. Our experiments show that the new camera configurations with back views provide superior support for 3D pose tracking compared to only frontal placements. The proposed method achieves significant improvement over the current state of the art (>10% on MPJPE). The source code, trained models, and datasets are available on our project page at https://4dqv.mpi-inf.mpg.de/EgoRear/.

HongXin Xie, JianDe Sun, Yi Shao et al.

Olfactory perception plays a critical role in both human and organismal interactions, yet understanding of its underlying mechanisms and influencing factors remain insufficient. Molecular structures influence odor perception through intricate biochemical interactions, and accurately quantifying structure-odor relationships presents significant challenges. The Quantitative Structure-Odor Relationship (QSOR) task, which involves predicting the associations between molecular structures and their corresponding odors, seeks to address these challenges. To this end, we propose a method for QSOR, utilizing Graph Attention Networks to model molecular structures and capture both local and global features. Unlike conventional QSOR approaches reliant on predefined descriptors, our method leverages diverse molecular feature extraction techniques to automatically learn comprehensive representations. This integration enhances the model's capacity to handle complex molecular information, improves prediction accuracy. Our approach demonstrates clear advantages in QSOR prediction tasks, offering valuable insights into the application of deep learning in cheminformatics.

Yuhan Zhu, Jian Wang, Bing Li et al.

With the development of cloud-native technologies, microservice-based software systems face challenges in accurately localizing root causes when failures occur. Additionally, the cloud-edge collaborative environment introduces more difficulties, such as unstable networks and high latency across network segments. Accurately identifying the root cause of microservices in a cloud-edge collaborative environment has thus become an urgent problem. In this paper, we propose MicroCERCL, a novel approach that pinpoints root causes at the kernel and application level in the cloud-edge collaborative environment. Our key insight is that failures propagate through direct invocations and indirect resource-competition dependencies in a cloud-edge collaborative environment characterized by instability and high latency. This will become more complex in the hybrid deployment that simultaneously involves multiple microservice systems. Leveraging this insight, we extract valid contents from kernel-level logs to prioritize localizing the kernel-level root cause. Moreover, we construct a heterogeneous dynamic topology stack and train a graph neural network model to accurately localize the application-level root cause without relying on historical data. Notably, we released the first benchmark hybrid deployment microservice system in a cloud-edge collaborative environment (the largest and most complex within our knowledge). Experiments conducted on the dataset collected from the benchmark show that MicroCERCL can accurately localize the root cause of microservice systems in such environments, significantly outperforming state-of-the-art approaches with an increase of at least 24.1% in top-1 accuracy.

Yi Zhang, Xiaoyu Shi, Dasong Li et al.

Diffusion Probabilistic Models (DPMs) have recently shown remarkable performance in image generation tasks, which are capable of generating highly realistic images. When adopting DPMs for image restoration tasks, the crucial aspect lies in how to integrate the conditional information to guide the DPMs to generate accurate and natural output, which has been largely overlooked in existing works. In this paper, we present a unified conditional framework based on diffusion models for image restoration. We leverage a lightweight UNet to predict initial guidance and the diffusion model to learn the residual of the guidance. By carefully designing the basic module and integration module for the diffusion model block, we integrate the guidance and other auxiliary conditional information into every block of the diffusion model to achieve spatially-adaptive generation conditioning. To handle high-resolution images, we propose a simple yet effective inter-step patch-splitting strategy to produce arbitrary-resolution images without grid artifacts. We evaluate our conditional framework on three challenging tasks: extreme low-light denoising, deblurring, and JPEG restoration, demonstrating its significant improvements in perceptual quality and the generalization to restoration tasks.

Jian Wang, Lingjie Liu, Weipeng Xu et al.

Egocentric 3D human pose estimation with a single fisheye camera has drawn a significant amount of attention recently. However, existing methods struggle with pose estimation from in-the-wild images, because they can only be trained on synthetic data due to the unavailability of large-scale in-the-wild egocentric datasets. Furthermore, these methods easily fail when the body parts are occluded by or interacting with the surrounding scene. To address the shortage of in-the-wild data, we collect a large-scale in-the-wild egocentric dataset called Egocentric Poses in the Wild (EgoPW). This dataset is captured by a head-mounted fisheye camera and an auxiliary external camera, which provides an additional observation of the human body from a third-person perspective during training. We present a new egocentric pose estimation method, which can be trained on the new dataset with weak external supervision. Specifically, we first generate pseudo labels for the EgoPW dataset with a spatio-temporal optimization method by incorporating the external-view supervision. The pseudo labels are then used to train an egocentric pose estimation network. To facilitate the network training, we propose a novel learning strategy to supervise the egocentric features with the high-quality features extracted by a pretrained external-view pose estimation model. The experiments show that our method predicts accurate 3D poses from a single in-the-wild egocentric image and outperforms the state-of-the-art methods both quantitatively and qualitatively.

Guangdong Xue, Qin Chang, Jian Wang et al.

A major limitation of fuzzy or neuro-fuzzy systems is their failure to deal with high-dimensional datasets. This happens primarily due to the use of T-norm, particularly, product or minimum (or a softer version of it). Thus, there are hardly any work dealing with datasets with dimensions more than hundred or so. Here, we propose a neuro-fuzzy framework that can handle datasets with dimensions even more than 7000! In this context, we propose an adaptive softmin (Ada-softmin) which effectively overcomes the drawbacks of ``numeric underflow" and ``fake minimum" that arise for existing fuzzy systems while dealing with high-dimensional problems. We call it an Adaptive Takagi-Sugeno-Kang (AdaTSK) fuzzy system. We then equip the AdaTSK system to perform feature selection and rule extraction in an integrated manner. In this context, a novel gate function is introduced and embedded only in the consequent parts, which can determine the useful features and rules, in two successive phases of learning. Unlike conventional fuzzy rule bases, we design an enhanced fuzzy rule base (En-FRB), which maintains adequate rules but does not grow the number of rules exponentially with dimension that typically happens for fuzzy neural networks. The integrated Feature Selection and Rule Extraction AdaTSK (FSRE-AdaTSK) system consists of three sequential phases: (i) feature selection, (ii) rule extraction, and (iii) fine tuning. The effectiveness of the FSRE-AdaTSK is demonstrated on 19 datasets of which five are in more than 2000 dimension including two with dimension greater than 7000. This may be the first time fuzzy systems are realized for classification involving more than 7000 input features.

Fangzhou Mu, Jian Wang, Yicheng Wu et al.

Visual content creation has spurred a soaring interest given its applications in mobile photography and AR / VR. Style transfer and single-image 3D photography as two representative tasks have so far evolved independently. In this paper, we make a connection between the two, and address the challenging task of 3D photo stylization - generating stylized novel views from a single image given an arbitrary style. Our key intuition is that style transfer and view synthesis have to be jointly modeled for this task. To this end, we propose a deep model that learns geometry-aware content features for stylization from a point cloud representation of the scene, resulting in high-quality stylized images that are consistent across views. Further, we introduce a novel training protocol to enable the learning using only 2D images. We demonstrate the superiority of our method via extensive qualitative and quantitative studies, and showcase key applications of our method in light of the growing demand for 3D content creation from 2D image assets.

Zhenchao Jin, Tao Gong, Dongdong Yu et al.

This paper studies the context aggregation problem in semantic image segmentation. The existing researches focus on improving the pixel representations by aggregating the contextual information within individual images. Though impressive, these methods neglect the significance of the representations of the pixels of the corresponding class beyond the input image. To address this, this paper proposes to mine the contextual information beyond individual images to further augment the pixel representations. We first set up a feature memory module, which is updated dynamically during training, to store the dataset-level representations of various categories. Then, we learn class probability distribution of each pixel representation under the supervision of the ground-truth segmentation. At last, the representation of each pixel is augmented by aggregating the dataset-level representations based on the corresponding class probability distribution. Furthermore, by utilizing the stored dataset-level representations, we also propose a representation consistent learning strategy to make the classification head better address intra-class compactness and inter-class dispersion. The proposed method could be effortlessly incorporated into existing segmentation frameworks (e.g., FCN, PSPNet, OCRNet and DeepLabV3) and brings consistent performance improvements. Mining contextual information beyond image allows us to report state-of-the-art performance on various benchmarks: ADE20K, LIP, Cityscapes and COCO-Stuff.

Tailin Chen, Desen Zhou, Jian Wang et al.

The task of skeleton-based action recognition remains a core challenge in human-centred scene understanding due to the multiple granularities and large variation in human motion. Existing approaches typically employ a single neural representation for different motion patterns, which has difficulty in capturing fine-grained action classes given limited training data. To address the aforementioned problems, we propose a novel multi-granular spatio-temporal graph network for skeleton-based action classification that jointly models the coarse- and fine-grained skeleton motion patterns. To this end, we develop a dual-head graph network consisting of two interleaved branches, which enables us to extract features at two spatio-temporal resolutions in an effective and efficient manner. Moreover, our network utilises a cross-head communication strategy to mutually enhance the representations of both heads. We conducted extensive experiments on three large-scale datasets, namely NTU RGB+D 60, NTU RGB+D 120, and Kinetics-Skeleton, and achieves the state-of-the-art performance on all the benchmarks, which validates the effectiveness of our method.

Yuhao Huang, Xin Yang, Yuxin Zou et al.

Nodule segmentation from breast ultrasound images is challenging yet essential for the diagnosis. Weakly-supervised segmentation (WSS) can help reduce time-consuming and cumbersome manual annotation. Unlike existing weakly-supervised approaches, in this study, we propose a novel and general WSS framework called Flip Learning, which only needs the box annotation. Specifically, the target in the label box will be erased gradually to flip the classification tag, and the erased region will be considered as the segmentation result finally. Our contribution is three-fold. First, our proposed approach erases on superpixel level using a Multi-agent Reinforcement Learning framework to exploit the prior boundary knowledge and accelerate the learning process. Second, we design two rewards: classification score and intensity distribution reward, to avoid under- and over-segmentation, respectively. Third, we adopt a coarse-to-fine learning strategy to reduce the residual errors and improve the segmentation performance. Extensively validated on a large dataset, our proposed approach achieves competitive performance and shows great potential to narrow the gap between fully-supervised and weakly-supervised learning.

Mingfu Xue, Yinghao Wu, Zhiyu Wu et al.

Recent researches show that deep learning model is susceptible to backdoor attacks. Many defenses against backdoor attacks have been proposed. However, existing defense works require high computational overhead or backdoor attack information such as the trigger size, which is difficult to satisfy in realistic scenarios. In this paper, a novel backdoor detection method based on adversarial examples is proposed. The proposed method leverages intentional adversarial perturbations to detect whether an image contains a trigger, which can be applied in both the training stage and the inference stage (sanitize the training set in training stage and detect the backdoor instances in inference stage). Specifically, given an untrusted image, the adversarial perturbation is added to the image intentionally. If the prediction of the model on the perturbed image is consistent with that on the unperturbed image, the input image will be considered as a backdoor instance. Compared with most existing defense works, the proposed adversarial perturbation based method requires low computational resources and maintains the visual quality of the images. Experimental results show that, the backdoor detection rate of the proposed defense method is 99.63%, 99.76% and 99.91% on Fashion-MNIST, CIFAR-10 and GTSRB datasets, respectively. Besides, the proposed method maintains the visual quality of the image as the l2 norm of the added perturbation are as low as 2.8715, 3.0513 and 2.4362 on Fashion-MNIST, CIFAR-10 and GTSRB datasets, respectively. In addition, it is also demonstrated that the proposed method can achieve high defense performance against backdoor attacks under different attack settings (trigger transparency, trigger size and trigger pattern). Compared with the existing defense work (STRIP), the proposed method has better detection performance on all the three datasets, and is more efficient than STRIP.

Jian Wang, Lingjie Liu, Weipeng Xu et al.

Egocentric 3D human pose estimation using a single fisheye camera has become popular recently as it allows capturing a wide range of daily activities in unconstrained environments, which is difficult for traditional outside-in motion capture with external cameras. However, existing methods have several limitations. A prominent problem is that the estimated poses lie in the local coordinate system of the fisheye camera, rather than in the world coordinate system, which is restrictive for many applications. Furthermore, these methods suffer from limited accuracy and temporal instability due to ambiguities caused by the monocular setup and the severe occlusion in a strongly distorted egocentric perspective. To tackle these limitations, we present a new method for egocentric global 3D body pose estimation using a single head-mounted fisheye camera. To achieve accurate and temporally stable global poses, a spatio-temporal optimization is performed over a sequence of frames by minimizing heatmap reprojection errors and enforcing local and global body motion priors learned from a mocap dataset. Experimental results show that our approach outperforms state-of-the-art methods both quantitatively and qualitatively.

Zechen Bai, Zhigang Wang, Jian Wang et al.

Unsupervised domain adaptation (UDA) methods for person re-identification (re-ID) aim at transferring re-ID knowledge from labeled source data to unlabeled target data. Although achieving great success, most of them only use limited data from a single-source domain for model pre-training, making the rich labeled data insufficiently exploited. To make full use of the valuable labeled data, we introduce the multi-source concept into UDA person re-ID field, where multiple source datasets are used during training. However, because of domain gaps, simply combining different datasets only brings limited improvement. In this paper, we try to address this problem from two perspectives, \ie{} domain-specific view and domain-fusion view. Two constructive modules are proposed, and they are compatible with each other. First, a rectification domain-specific batch normalization (RDSBN) module is explored to simultaneously reduce domain-specific characteristics and increase the distinctiveness of person features. Second, a graph convolutional network (GCN) based multi-domain information fusion (MDIF) module is developed, which minimizes domain distances by fusing features of different domains. The proposed method outperforms state-of-the-art UDA person re-ID methods by a large margin, and even achieves comparable performance to the supervised approaches without any post-processing techniques.

Zi Wang, Di Guo, Zhangren Tu et al.

The non-uniform sampling is a powerful approach to enable fast acquisition but requires sophisticated reconstruction algorithms. Faithful reconstruction from partial sampled exponentials is highly expected in general signal processing and many applications. Deep learning has shown astonishing potential in this field but many existing problems, such as lack of robustness and explainability, greatly limit its applications. In this work, by combining merits of the sparse model-based optimization method and data-driven deep learning, we propose a deep learning architecture for spectra reconstruction from undersampled data, called MoDern. It follows the iterative reconstruction in solving a sparse model to build the neural network and we elaborately design a learnable soft-thresholding to adaptively eliminate the spectrum artifacts introduced by undersampling. Extensive results on both synthetic and biological data show that MoDern enables more robust, high-fidelity, and ultra-fast reconstruction than the state-of-the-art methods. Remarkably, MoDern has a small number of network parameters and is trained on solely synthetic data while generalizing well to biological data in various scenarios. Furthermore, we extend it to an open-access and easy-to-use cloud computing platform (XCloud-MoDern), contributing a promising strategy for further development of biological applications.

Yi-Fei PU, Jian Wang

This paper offers a novel mathematical approach, the modified Fractional-order Steepest Descent Method (FSDM) for training BackPropagation Neural Networks (BPNNs); this differs from the majority of the previous approaches and as such. A promising mathematical method, fractional calculus, has the potential to assume a prominent role in the applications of neural networks and cybernetics because of its inherent strengths such as long-term memory, nonlocality, and weak singularity. Therefore, to improve the optimization performance of classic first-order BPNNs, in this paper we study whether it could be possible to modified FSDM and generalize classic first-order BPNNs to modified FSDM based Fractional-order Backpropagation Neural Networks (FBPNNs). Motivated by this inspiration, this paper proposes a state-of-the-art application of fractional calculus to implement a modified FSDM based FBPNN whose reverse incremental search is in the negative directions of the approximate fractional-order partial derivatives of the square error. At first, the theoretical concept of a modified FSDM based FBPNN is described mathematically. Then, the mathematical proof of the fractional-order global optimal convergence, an assumption of the structure, and the fractional-order multi-scale global optimization of a modified FSDM based FBPNN are analysed in detail. Finally, we perform comparative experiments and compare a modified FSDM based FBPNN with a classic first-order BPNN, i.e., an example function approximation, fractional-order multi-scale global optimization, and two comparative performances with real data. The more efficient optimal searching capability of the fractional-order multi-scale global optimization of a modified FSDM based FBPNN to determine the global optimal solution is the major advantage being superior to a classic first-order BPNN.

Jian Wang, Yacong Geng, Jiqiang Liu

An adaptive quantum image encryption method based on wavelet transform is designed. Since the characteristic of most information is centralized in the low frequency part after performing the wavelet transform, it reserves the image low frequency information only, so as to reduce the encryption workload. Then it encrypts the low frequency information by the random key stream generated by logistic map, the encryption process is realized by implementing XOR operation. In the decryption process, it carries out zero filling operations for high frequency coefficient to recover the decryption images which are equal to the plain images. At the same time, the relevant quantum logical circuit is designed. Statistical simulation and theoretical analysis demonstrate that the proposed quantum image encryption algorithm has higher security and lower computational complexity. So it is adaptive to the scenes that need to encrypt a large number of images during network transmission.

Ankit Goyal, Jian Wang, Jia Deng

In this paper, we study the problem of geometric reasoning in the context of question-answering. We introduce Dynamic Spatial Memory Network (DSMN), a new deep network architecture designed for answering questions that admit latent visual representations. DSMN learns to generate and reason over such representations. Further, we propose two synthetic benchmarks, FloorPlanQA and ShapeIntersection, to evaluate the geometric reasoning capability of QA systems. Experimental results validate the effectiveness of our proposed DSMN for visual thinking tasks.