Xin Li

Xin Li, Dongze Lian, Zhihe Lu et al.

Adapter-style efficient transfer learning (ETL) has shown excellent performance in the tuning of vision-language models (VLMs) under the low-data regime, where only a few additional parameters are introduced to excavate the task-specific knowledge based on the general and powerful representation of VLMs. However, most adapter-style works face two limitations: (i) modeling task-specific knowledge with a single modality only; and (ii) overlooking the exploitation of the inter-class relationships in downstream tasks, thereby leading to sub-optimal solutions. To mitigate that, we propose an effective adapter-style tuning strategy, dubbed GraphAdapter, which performs the textual adapter by explicitly modeling the dual-modality structure knowledge (i.e., the correlation of different semantics/classes in textual and visual modalities) with a dual knowledge graph. In particular, the dual knowledge graph is established with two sub-graphs, i.e., a textual knowledge sub-graph, and a visual knowledge sub-graph, where the nodes and edges represent the semantics/classes and their correlations in two modalities, respectively. This enables the textual feature of each prompt to leverage the task-specific structure knowledge from both textual and visual modalities, yielding a more effective classifier for downstream tasks. Extensive experimental results on 11 benchmark datasets reveal that our GraphAdapter significantly outperforms previous adapter-based methods. The code will be released at https://github.com/lixinustc/GraphAdapter

Ren Yang, Radu Timofte, Xin Li et al.

This paper reviews the Challenge on Super-Resolution of Compressed Image and Video at AIM 2022. This challenge includes two tracks. Track 1 aims at the super-resolution of compressed image, and Track~2 targets the super-resolution of compressed video. In Track 1, we use the popular dataset DIV2K as the training, validation and test sets. In Track 2, we propose the LDV 3.0 dataset, which contains 365 videos, including the LDV 2.0 dataset (335 videos) and 30 additional videos. In this challenge, there are 12 teams and 2 teams that submitted the final results to Track 1 and Track 2, respectively. The proposed methods and solutions gauge the state-of-the-art of super-resolution on compressed image and video. The proposed LDV 3.0 dataset is available at https://github.com/RenYang-home/LDV_dataset. The homepage of this challenge is at https://github.com/RenYang-home/AIM22_CompressSR.

Ao Luo, Fan Yang, Xin Li et al.

Optical flow, or the estimation of motion fields from image sequences, is one of the fundamental problems in computer vision. Unlike most pixel-wise tasks that aim at achieving consistent representations of the same category, optical flow raises extra demands for obtaining local discrimination and smoothness, which yet is not fully explored by existing approaches. In this paper, we push Gaussian Attention (GA) into the optical flow models to accentuate local properties during representation learning and enforce the motion affinity during matching. Specifically, we introduce a novel Gaussian-Constrained Layer (GCL) which can be easily plugged into existing Transformer blocks to highlight the local neighborhood that contains fine-grained structural information. Moreover, for reliable motion analysis, we provide a new Gaussian-Guided Attention Module (GGAM) which not only inherits properties from Gaussian distribution to instinctively revolve around the neighbor fields of each point but also is empowered to put the emphasis on contextually related regions during matching. Our fully-equipped model, namely Gaussian Attention Flow network (GAFlow), naturally incorporates a series of novel Gaussian-based modules into the conventional optical flow framework for reliable motion analysis. Extensive experiments on standard optical flow datasets consistently demonstrate the exceptional performance of the proposed approach in terms of both generalization ability evaluation and online benchmark testing. Code is available at https://github.com/LA30/GAFlow.

Bingchen Li, Xin Li, Yiting Lu et al.

Compressed Image Super-resolution has achieved great attention in recent years, where images are degraded with compression artifacts and low-resolution artifacts. Since the complex hybrid distortions, it is hard to restore the distorted image with the simple cooperation of super-resolution and compression artifacts removing. In this paper, we take a step forward to propose the Hierarchical Swin Transformer (HST) network to restore the low-resolution compressed image, which jointly captures the hierarchical feature representations and enhances each-scale representation with Swin transformer, respectively. Moreover, we find that the pretraining with Super-resolution (SR) task is vital in compressed image super-resolution. To explore the effects of different SR pretraining, we take the commonly-used SR tasks (e.g., bicubic and different real super-resolution simulations) as our pretraining tasks, and reveal that SR plays an irreplaceable role in the compressed image super-resolution. With the cooperation of HST and pre-training, our HST achieves the fifth place in AIM 2022 challenge on the low-quality compressed image super-resolution track, with the PSNR of 23.51dB. Extensive experiments and ablation studies have validated the effectiveness of our proposed methods. The code and models are available at https://github.com/USTC-IMCL/HST-for-Compressed-Image-SR.

Xin Li, Bingchen Li, Xin Jin et al.

In recent years, we have witnessed the great advancement of Deep neural networks (DNNs) in image restoration. However, a critical limitation is that they cannot generalize well to real-world degradations with different degrees or types. In this paper, we are the first to propose a novel training strategy for image restoration from the causality perspective, to improve the generalization ability of DNNs for unknown degradations. Our method, termed Distortion Invariant representation Learning (DIL), treats each distortion type and degree as one specific confounder, and learns the distortion-invariant representation by eliminating the harmful confounding effect of each degradation. We derive our DIL with the back-door criterion in causality by modeling the interventions of different distortions from the optimization perspective. Particularly, we introduce counterfactual distortion augmentation to simulate the virtual distortion types and degrees as the confounders. Then, we instantiate the intervention of each distortion with a virtual model updating based on corresponding distorted images, and eliminate them from the meta-learning perspective. Extensive experiments demonstrate the effectiveness of our DIL on the generalization capability for unseen distortion types and degrees. Our code will be available at https://github.com/lixinustc/Causal-IR-DIL.

Zhihong Pan, Baopu Li, Dongliang He et al. · amazon-science

Deep learning based single image super-resolution models have been widely studied and superb results are achieved in upscaling low-resolution images with fixed scale factor and downscaling degradation kernel. To improve real world applicability of such models, there are growing interests to develop models optimized for arbitrary upscaling factors. Our proposed method is the first to treat arbitrary rescaling, both upscaling and downscaling, as one unified process. Using joint optimization of both directions, the proposed model is able to learn upscaling and downscaling simultaneously and achieve bidirectional arbitrary image rescaling. It improves the performance of current arbitrary upscaling models by a large margin while at the same time learns to maintain visual perception quality in downscaled images. The proposed model is further shown to be robust in cycle idempotence test, free of severe degradations in reconstruction accuracy when the downscaling-to-upscaling cycle is applied repetitively. This robustness is beneficial for image rescaling in the wild when this cycle could be applied to one image for multiple times. It also performs well on tests with arbitrary large scales and asymmetric scales, even when the model is not trained with such tasks. Extensive experiments are conducted to demonstrate the superior performance of our model.

Jun Cen, Siteng Huang, Yuqian Yuan et al. · pku

We introduce RynnVLA-002, a unified Vision-Language-Action (VLA) and world model. The world model leverages action and visual inputs to predict future image states, learning the underlying physics of the environment to refine action generation. Conversely, the VLA model produces subsequent actions from image observations, enhancing visual understanding and supporting the world model's image generation. The unified framework of RynnVLA-002 enables joint learning of environmental dynamics and action planning. Our experiments show that RynnVLA-002 surpasses individual VLA and world models, demonstrating their mutual enhancement. We evaluate RynnVLA-002 in both simulation and real-world robot tasks. RynnVLA-002 achieves 97.4% success rate on the LIBERO simulation benchmark without pretraining, while in real-world LeRobot experiments, its integrated world model boosts the overall success rate by 50%.

Xuan-Bac Nguyen, Xudong Liu, Xin Li et al.

This work presents our solutions to the Algonauts Project 2023 Challenge. The primary objective of the challenge revolves around employing computational models to anticipate brain responses captured during participants' observation of intricate natural visual scenes. The goal is to predict brain responses across the entire visual brain, as it is the region where the most reliable responses to images have been observed. We constructed an image-based brain encoder through a two-step training process to tackle this challenge. Initially, we created a pretrained encoder using data from all subjects. Next, we proceeded to fine-tune individual subjects. Each step employed different training strategies, such as different loss functions and objectives, to introduce diversity. Ultimately, our solution constitutes an ensemble of multiple unique encoders. The code is available at https://github.com/uark-cviu/Algonauts2023

Lin Zhang, Xin Li, Dongliang He et al.

It is widely agreed that reference-based super-resolution (RefSR) achieves superior results by referring to similar high quality images, compared to single image super-resolution (SISR). Intuitively, the more references, the better performance. However, previous RefSR methods have all focused on single-reference image training, while multiple reference images are often available in testing or practical applications. The root cause of such training-testing mismatch is the absence of publicly available multi-reference SR training datasets, which greatly hinders research efforts on multi-reference super-resolution. To this end, we construct a large-scale, multi-reference super-resolution dataset, named LMR. It contains 112,142 groups of 300x300 training images, which is 10x of the existing largest RefSR dataset. The image size is also much larger. More importantly, each group is equipped with 5 reference images with different similarity levels. Furthermore, we propose a new baseline method for multi-reference super-resolution: MRefSR, including a Multi-Reference Attention Module (MAM) for feature fusion of an arbitrary number of reference images, and a Spatial Aware Filtering Module (SAFM) for the fused feature selection. The proposed MRefSR achieves significant improvements over state-of-the-art approaches on both quantitative and qualitative evaluations. Our code and data would be made available soon.

Thanh-Dat Truong, Quoc-Huy Bui, Chi Nhan Duong et al.

Human action recognition has recently become one of the popular research topics in the computer vision community. Various 3D-CNN based methods have been presented to tackle both the spatial and temporal dimensions in the task of video action recognition with competitive results. However, these methods have suffered some fundamental limitations such as lack of robustness and generalization, e.g., how does the temporal ordering of video frames affect the recognition results? This work presents a novel end-to-end Transformer-based Directed Attention (DirecFormer) framework for robust action recognition. The method takes a simple but novel perspective of Transformer-based approach to understand the right order of sequence actions. Therefore, the contributions of this work are three-fold. Firstly, we introduce the problem of ordered temporal learning issues to the action recognition problem. Secondly, a new Directed Attention mechanism is introduced to understand and provide attentions to human actions in the right order. Thirdly, we introduce the conditional dependency in action sequence modeling that includes orders and classes. The proposed approach consistently achieves the state-of-the-art (SOTA) results compared with the recent action recognition methods, on three standard large-scale benchmarks, i.e. Jester, Kinetics-400 and Something-Something-V2.

Xin Li, Mingqiang Wei, Songcan Chen

Self-supervised learning is attracting wide attention in point cloud processing. However, it is still not well-solved to gain discriminative and transferable features of point clouds for efficient training on downstream tasks, due to their natural sparsity and irregularity. We propose PointSmile, a reconstruction-free self-supervised learning paradigm by maximizing curriculum mutual information (CMI) across the replicas of point cloud objects. From the perspective of how-and-what-to-learn, PointSmile is designed to imitate human curriculum learning, i.e., starting with an easy curriculum and gradually increasing the difficulty of that curriculum. To solve "how-to-learn", we introduce curriculum data augmentation (CDA) of point clouds. CDA encourages PointSmile to learn from easy samples to hard ones, such that the latent space can be dynamically affected to create better embeddings. To solve "what-to-learn", we propose to maximize both feature- and class-wise CMI, for better extracting discriminative features of point clouds. Unlike most of existing methods, PointSmile does not require a pretext task, nor does it require cross-modal data to yield rich latent representations. We demonstrate the effectiveness and robustness of PointSmile in downstream tasks including object classification and segmentation. Extensive results show that our PointSmile outperforms existing self-supervised methods, and compares favorably with popular fully-supervised methods on various standard architectures.

Naga VS Raviteja Chappa, Pha Nguyen, Alexander H Nelson et al.

In this paper, we propose a new, simple, and effective Self-supervised Spatio-temporal Transformers (SPARTAN) approach to Group Activity Recognition (GAR) using unlabeled video data. Given a video, we create local and global Spatio-temporal views with varying spatial patch sizes and frame rates. The proposed self-supervised objective aims to match the features of these contrasting views representing the same video to be consistent with the variations in spatiotemporal domains. To the best of our knowledge, the proposed mechanism is one of the first works to alleviate the weakly supervised setting of GAR using the encoders in video transformers. Furthermore, using the advantage of transformer models, our proposed approach supports long-term relationship modeling along spatio-temporal dimensions. The proposed SPARTAN approach performs well on two group activity recognition benchmarks, including NBA and Volleyball datasets, by surpassing the state-of-the-art results by a significant margin in terms of MCA and MPCA metrics.

Lin Zhang, Xin Li, Dongliang He et al.

Reference-based image super-resolution (RefSR) is a promising SR branch and has shown great potential in overcoming the limitations of single image super-resolution. While previous state-of-the-art RefSR methods mainly focus on improving the efficacy and robustness of reference feature transfer, it is generally overlooked that a well reconstructed SR image should enable better SR reconstruction for its similar LR images when it is referred to as. Therefore, in this work, we propose a reciprocal learning framework that can appropriately leverage such a fact to reinforce the learning of a RefSR network. Besides, we deliberately design a progressive feature alignment and selection module for further improving the RefSR task. The newly proposed module aligns reference-input images at multi-scale feature spaces and performs reference-aware feature selection in a progressive manner, thus more precise reference features can be transferred into the input features and the network capability is enhanced. Our reciprocal learning paradigm is model-agnostic and it can be applied to arbitrary RefSR models. We empirically show that multiple recent state-of-the-art RefSR models can be consistently improved with our reciprocal learning paradigm. Furthermore, our proposed model together with the reciprocal learning strategy sets new state-of-the-art performances on multiple benchmarks.

Naga VS Raviteja Chappa, Pha Nguyen, Alexander H Nelson et al.

This paper introduces a novel approach to Social Group Activity Recognition (SoGAR) using Self-supervised Transformers network that can effectively utilize unlabeled video data. To extract spatio-temporal information, we created local and global views with varying frame rates. Our self-supervised objective ensures that features extracted from contrasting views of the same video were consistent across spatio-temporal domains. Our proposed approach is efficient in using transformer-based encoders to alleviate the weakly supervised setting of group activity recognition. By leveraging the benefits of transformer models, our approach can model long-term relationships along spatio-temporal dimensions. Our proposed SoGAR method achieved state-of-the-art results on three group activity recognition benchmarks, namely JRDB-PAR, NBA, and Volleyball datasets, surpassing the current numbers in terms of F1-score, MCA, and MPCA metrics.

Syeda Nyma Ferdous, Xin Li, Siwei Lyu

Object Re-IDentification (ReID), one of the most significant problems in biometrics and surveillance systems, has been extensively studied by image processing and computer vision communities in the past decades. Learning a robust and discriminative feature representation is a crucial challenge for object ReID. The problem is even more challenging in ReID based on Unmanned Aerial Vehicle (UAV) as the images are characterized by continuously varying camera parameters (e.g., view angle, altitude, etc.) of a flying drone. To address this challenge, multiscale feature representation has been considered to characterize images captured from UAV flying at different altitudes. In this work, we propose a multitask learning approach, which employs a new multiscale architecture without convolution, Pyramid Vision Transformer (PVT), as the backbone for UAV-based object ReID. By uncertainty modeling of intraclass variations, our proposed model can be jointly optimized using both uncertainty-aware object ID and camera ID information. Experimental results are reported on PRAI and VRAI, two ReID data sets from aerial surveillance, to verify the effectiveness of our proposed approach

Honghu Pan, Yongyong Chen, Yunqi He et al.

Compared to visible-to-visible (V2V) person re-identification (ReID), the visible-to-infrared (V2I) person ReID task is more challenging due to the lack of sufficient training samples and the large cross-modality discrepancy. To this end, we propose Flow2Flow, a unified framework that could jointly achieve training sample expansion and cross-modality image generation for V2I person ReID. Specifically, Flow2Flow learns bijective transformations from both the visible image domain and the infrared domain to a shared isotropic Gaussian domain with an invertible visible flow-based generator and an infrared one, respectively. With Flow2Flow, we are able to generate pseudo training samples by the transformation from latent Gaussian noises to visible or infrared images, and generate cross-modality images by transformations from existing-modality images to latent Gaussian noises to missing-modality images. For the purpose of identity alignment and modality alignment of generated images, we develop adversarial training strategies to train Flow2Flow. Specifically, we design an image encoder and a modality discriminator for each modality. The image encoder encourages the generated images to be similar to real images of the same identity via identity adversarial training, and the modality discriminator makes the generated images modal-indistinguishable from real images via modality adversarial training. Experimental results on SYSU-MM01 and RegDB demonstrate that both training sample expansion and cross-modality image generation can significantly improve V2I ReID accuracy.

Mindi Ruan, Xiangxu Yu, Na Zhang et al.

How can we teach a computer to recognize 10,000 different actions? Deep learning has evolved from supervised and unsupervised to self-supervised approaches. In this paper, we present a new contrastive learning-based framework for decision tree-based classification of actions, including human-human interactions (HHI) and human-object interactions (HOI). The key idea is to translate the original multi-class action recognition into a series of binary classification tasks on a pre-constructed decision tree. Under the new framework of contrastive learning, we present the design of an interaction adjacent matrix (IAM) with skeleton graphs as the backbone for modeling various action-related attributes such as periodicity and symmetry. Through the construction of various pretext tasks, we obtain a series of binary classification nodes on the decision tree that can be combined to support higher-level recognition tasks. Experimental justification for the potential of our approach in real-world applications ranges from interaction recognition to symmetry detection. In particular, we have demonstrated the promising performance of video-based autism spectrum disorder (ASD) diagnosis on the CalTech interview video database.

Chuanbo Hu, Shan Jia, Fan Zhang et al.

Global Positioning Systems (GPS) have played a crucial role in various navigation applications. Nevertheless, localizing the perfect destination within the last few meters remains an important but unresolved problem. Limited by the GPS positioning accuracy, navigation systems always show users a vicinity of a destination, but not its exact location. Street view images (SVI) in maps as an immersive media technology have served as an aid to provide the physical environment for human last-meters wayfinding. However, due to the large diversity of geographic context and acquisition conditions, the captured SVI always contains various distracting objects (e.g., pedestrians and vehicles), which will distract human visual attention from efficiently finding the destination in the last few meters. To address this problem, we highlight the importance of reducing visual distraction in image-based wayfinding by proposing a saliency-guided image inpainting framework. It aims at redirecting human visual attention from distracting objects to destination-related objects for more efficient and accurate wayfinding in the last meters. Specifically, a context-aware distracting object detection method driven by deep salient object detection has been designed to extract distracting objects from three semantic levels in SVI. Then we employ a large-mask inpainting method with fast Fourier convolutions to remove the detected distracting objects. Experimental results with both qualitative and quantitative analysis show that our saliency-guided inpainting method can not only achieve great perceptual quality in street view images but also redirect the human's visual attention to focus more on static location-related objects than distracting ones. The human-based evaluation also justified the effectiveness of our method in improving the efficiency of locating the target destination.

Lei Yu, Jintao Fei, Xinyi Liu et al.

Video-based physiology, exemplified by remote photoplethysmography (rPPG), extracts physiological signals such as pulse and respiration by analyzing subtle changes in video recordings. This non-contact, real-time monitoring method holds great potential for home settings. Despite the valuable contributions of public benchmark datasets to this technology, there is currently no dataset specifically designed for passive home monitoring. Existing datasets are often limited to close-up, static, frontal recordings and typically include only 1-2 physiological signals. To advance video-based physiology in real home settings, we introduce the MHAD dataset. It comprises 1,440 videos from 40 subjects, capturing 6 typical activities from 3 angles in a real home environment. Additionally, 5 physiological signals were recorded, making it a comprehensive video-based physiology dataset. MHAD is compatible with the rPPG-toolbox and has been validated using several unsupervised and supervised methods. Our dataset is publicly available at https://github.com/jdh-algo/MHAD-Dataset.

Ren Yang, Radu Timofte, Jing Liu et al.

This paper reviews the first NTIRE challenge on quality enhancement of compressed video, with a focus on the proposed methods and results. In this challenge, the new Large-scale Diverse Video (LDV) dataset is employed. The challenge has three tracks. Tracks 1 and 2 aim at enhancing the videos compressed by HEVC at a fixed QP, while Track 3 is designed for enhancing the videos compressed by x265 at a fixed bit-rate. Besides, the quality enhancement of Tracks 1 and 3 targets at improving the fidelity (PSNR), and Track 2 targets at enhancing the perceptual quality. The three tracks totally attract 482 registrations. In the test phase, 12 teams, 8 teams and 11 teams submitted the final results of Tracks 1, 2 and 3, respectively. The proposed methods and solutions gauge the state-of-the-art of video quality enhancement. The homepage of the challenge: https://github.com/RenYang-home/NTIRE21_VEnh

Qiang Zhou, Xin Li

In this paper, we introduce the STN-Homography model to directly estimate the homography matrix between image pair. Different most CNN-based homography estimation methods which use an alternative 4-point homography parameterization, we use prove that, after coordinate normalization, the variance of elements of coordinate normalized $3\times3$ homography matrix is very small and suitable to be regressed well with CNN. Based on proposed STN-Homography, we use a hierarchical architecture which stacks several STN-Homography models and successively reduce the estimation error. Effectiveness of the proposed method is shown through experiments on MSCOCO dataset, in which it significantly outperforms the state-of-the-art. The average processing time of our hierarchical STN-Homography with 1 stage is only 4.87 ms on the GPU, and the processing time for hierarchical STN-Homography with 3 stages is 17.85 ms. The code will soon be open sourced.

Yuming Jiang, Siteng Huang, Shengke Xue et al. · pku

This paper presents RynnVLA-001, a vision-language-action(VLA) model built upon large-scale video generative pretraining from human demonstrations. We propose a novel two-stage pretraining methodology. The first stage, Ego-Centric Video Generative Pretraining, trains an Image-to-Video model on 12M ego-centric manipulation videos to predict future frames conditioned on an initial frame and a language instruction. The second stage, Human-Centric Trajectory-Aware Modeling, extends this by jointly predicting future keypoint trajectories, thereby effectively bridging visual frame prediction with action prediction. Furthermore, to enhance action representation, we propose ActionVAE, a variational autoencoder that compresses sequences of actions into compact latent embeddings, reducing the complexity of the VLA output space. When finetuned on the same downstream robotics datasets, RynnVLA-001 achieves superior performance over state-of-the-art baselines, demonstrating that the proposed pretraining strategy provides a more effective initialization for VLA models.

Xin Li, Xiaotao Zheng, Zhihong Xia

XNet is a single-layer neural network architecture that leverages Cauchy integral-based activation functions for high-order function approximation. Through theoretical analysis, we show that the Cauchy activation functions used in XNet can achieve arbitrary-order polynomial convergence, fundamentally outperforming traditional MLPs and Kolmogorov-Arnold Networks (KANs) that rely on increased depth or B-spline activations. Our extensive experiments on function approximation, PDE solving, and reinforcement learning demonstrate XNet's superior performance - reducing approximation error by up to 50000 times and accelerating training by up to 10 times compared to existing approaches. These results establish XNet as a highly efficient architecture for both scientific computing and AI applications.

Guangwenjie Zou, Liang Yao, Fan Liu et al.

Since high resolution remote sensing image classification often requires a relatively high computation complexity, lightweight models tend to be practical and efficient. Model pruning is an effective method for model compression. However, existing methods rarely take into account the specificity of remote sensing images, resulting in significant accuracy loss after pruning. To this end, we propose an effective structural pruning approach for remote sensing image classification. Specifically, a pruning strategy that amplifies the differences in channel importance of the model is introduced. Then an adaptive mining loss function is designed for the fine-tuning process of the pruned model. Finally, we conducted experiments on two remote sensing classification datasets. The experimental results demonstrate that our method achieves minimal accuracy loss after compressing remote sensing classification models, achieving state-of-the-art (SoTA) performance.

Bingchen Li, Xin Li, Yiting Lu et al.

We present the first loss agent, dubbed LossAgent, for low-level image processing tasks, e.g., image super-resolution and restoration, intending to achieve any customized optimization objectives of low-level image processing in different practical applications. Notably, not all optimization objectives, such as complex hand-crafted perceptual metrics, text description, and intricate human feedback, can be instantiated with existing low-level losses, e.g., MSE loss, which presents a crucial challenge in optimizing image processing networks in an end-to-end manner. To eliminate this, our LossAgent introduces the powerful large language model (LLM) as the loss agent, where the rich textual understanding of prior knowledge empowers the loss agent with the potential to understand complex optimization objectives, trajectory, and state feedback from external environments in the optimization process of the low-level image processing networks. In particular, we establish the loss repository by incorporating existing loss functions that support the end-to-end optimization for low-level image processing. Then, we design the optimization-oriented prompt engineering for the loss agent to actively and intelligently decide the compositional weights for each loss in the repository at each optimization interaction, thereby achieving the required optimization trajectory for any customized optimization objectives. Extensive experiments on three typical low-level image processing tasks and multiple optimization objectives have shown the effectiveness and applicability of our proposed LossAgent.

Xijun Wang, Xin Li, Bingchen Li et al.

Diffusion models have significantly advanced video super-resolution (VSR) by enhancing perceptual quality, largely through elaborately designed temporal modeling to ensure inter-frame consistency. However, existing methods usually suffer from limited temporal coherence and prohibitively high computational costs (e.g., typically requiring over 8 NVIDIA A100-80G GPUs), especially for long videos. In this work, we propose LiftVSR, an efficient VSR framework that leverages and elevates the image-wise diffusion prior from PixArt-$α$, achieving state-of-the-art results using only 4$\times$RTX 4090 GPUs. To balance long-term consistency and efficiency, we introduce a hybrid temporal modeling mechanism that decomposes temporal learning into two complementary components: (i) Dynamic Temporal Attention (DTA) for fine-grained temporal modeling within short frame segment ($\textit{i.e.}$, low complexity), and (ii) Attention Memory Cache (AMC) for long-term temporal modeling across segments ($\textit{i.e.}$, consistency). Specifically, DTA identifies multiple token flows across frames within multi-head query and key tokens to warp inter-frame contexts in the value tokens. AMC adaptively aggregates historical segment information via a cache unit, ensuring long-term coherence with minimal overhead. To further stabilize the cache interaction during inference, we introduce an asymmetric sampling strategy that mitigates feature mismatches arising from different diffusion sampling steps. Extensive experiments on several typical VSR benchmarks have demonstrated that LiftVSR achieves impressive performance with significantly lower computational costs.

Le Dong, Qixuan Cao, Lei Pu et al.

ERVD: An Efficient and Robust ViT-Based Distillation Framework for Remote Sensing Image Retrieval

Thanh-Dat Truong, Xin Li, Bhiksha Raj et al.

The Vision-Language Foundation Model has recently shown outstanding performance in various perception learning tasks. The outstanding performance of the vision-language model mainly relies on large-scale pre-training datasets and different data augmentation techniques. However, the domain generalization problem of the vision-language foundation model needs to be addressed. This problem has limited the generalizability of the vision-language foundation model to unknown data distributions. In this paper, we introduce a new simple but efficient Diffusion Sampling approach to Domain Generalization (ED-SAM) to improve the generalizability of the vision-language foundation model. Our theoretical analysis in this work reveals the critical role and relation of the diffusion model to domain generalization in the vision-language foundation model. Then, based on the insightful analysis, we introduce a new simple yet effective Transport Transformation to diffusion sampling method. It can effectively generate adversarial samples to improve the generalizability of the foundation model against unknown data distributions. The experimental results on different scales of vision-language pre-training datasets, including CC3M, CC12M, and LAION400M, have consistently shown State-of-the-Art performance and scalability of the proposed ED-SAM approach compared to the other recent methods.

Tianlong Ma, Xingjiao Wu, Xin Li et al.

Document layout analysis (DLA) plays an important role in information extraction and document understanding. At present, document layout analysis has reached a milestone achievement, however, document layout analysis of non-Manhattan is still a challenge. In this paper, we propose an image layer modeling method to tackle this challenge. To measure the proposed image layer modeling method, we propose a manually-labeled non-Manhattan layout fine-grained segmentation dataset named FPD. As far as we know, FPD is the first manually-labeled non-Manhattan layout fine-grained segmentation dataset. To effectively extract fine-grained features of documents, we propose an edge embedding network named L-E^3Net. Experimental results prove that our proposed image layer modeling method can better deal with the fine-grained segmented document of the non-Manhattan layout.

Chuanbo Hu, Minglei Yin, Bin Liu et al.

Social media such as Instagram and Twitter have become important platforms for marketing and selling illicit drugs. Detection of online illicit drug trafficking has become critical to combat the online trade of illicit drugs. However, the legal status often varies spatially and temporally; even for the same drug, federal and state legislation can have different regulations about its legality. Meanwhile, more drug trafficking events are disguised as a novel form of advertising commenting leading to information heterogeneity. Accordingly, accurate detection of illicit drug trafficking events (IDTEs) from social media has become even more challenging. In this work, we conduct the first systematic study on fine-grained detection of IDTEs on Instagram. We propose to take a deep multimodal multilabel learning (DMML) approach to detect IDTEs and demonstrate its effectiveness on a newly constructed dataset called multimodal IDTE(MM-IDTE). Specifically, our model takes text and image data as the input and combines multimodal information to predict multiple labels of illicit drugs. Inspired by the success of BERT, we have developed a self-supervised multimodal bidirectional transformer by jointly fine-tuning pretrained text and image encoders. We have constructed a large-scale dataset MM-IDTE with manually annotated multiple drug labels to support fine-grained detection of illicit drugs. Extensive experimental results on the MM-IDTE dataset show that the proposed DMML methodology can accurately detect IDTEs even in the presence of special characters and style changes attempting to evade detection.

Chuanbo Hu, Minglei Yin, Bin Liu et al.

Illicit drug trafficking via social media sites such as Instagram has become a severe problem, thus drawing a great deal of attention from law enforcement and public health agencies. How to identify illicit drug dealers from social media data has remained a technical challenge due to the following reasons. On the one hand, the available data are limited because of privacy concerns with crawling social media sites; on the other hand, the diversity of drug dealing patterns makes it difficult to reliably distinguish drug dealers from common drug users. Unlike existing methods that focus on posting-based detection, we propose to tackle the problem of illicit drug dealer identification by constructing a large-scale multimodal dataset named Identifying Drug Dealers on Instagram (IDDIG). Totally nearly 4,000 user accounts, of which over 1,400 are drug dealers, have been collected from Instagram with multiple data sources including post comments, post images, homepage bio, and homepage images. We then design a quadruple-based multimodal fusion method to combine the multiple data sources associated with each user account for drug dealer identification. Experimental results on the constructed IDDIG dataset demonstrate the effectiveness of the proposed method in identifying drug dealers (almost 95% accuracy). Moreover, we have developed a hashtag-based community detection technique for discovering evolving patterns, especially those related to geography and drug types.

Bi'an Du, Xiang Gao, Wei Hu et al.

Point clouds have attracted increasing attention. Significant progress has been made in methods for point cloud analysis, which often requires costly human annotation as supervision. To address this issue, we propose a novel self-contrastive learning for self-supervised point cloud representation learning, aiming to capture both local geometric patterns and nonlocal semantic primitives based on the nonlocal self-similarity of point clouds. The contributions are two-fold: on the one hand, instead of contrasting among different point clouds as commonly employed in contrastive learning, we exploit self-similar point cloud patches within a single point cloud as positive samples and otherwise negative ones to facilitate the task of contrastive learning. On the other hand, we actively learn hard negative samples that are close to positive samples for discriminative feature learning. Experimental results show that the proposed method achieves state-of-the-art performance on widely used benchmark datasets for self-supervised point cloud segmentation and transfer learning for classification.

Qian Ning, Weisheng Dong, Xin Li et al.

Neural architecture search (NAS) has recently reshaped our understanding on various vision tasks. Similar to the success of NAS in high-level vision tasks, it is possible to find a memory and computationally efficient solution via NAS with highly competent denoising performance. However, the optimization gap between the super-network and the sub-architectures has remained an open issue in both low-level and high-level vision. In this paper, we present a novel approach to filling in this gap by connecting model-guided design with NAS (MoD-NAS) and demonstrate its application into image denoising. Specifically, we propose to construct a new search space under model-guided framework and develop more stable and efficient differential search strategies. MoD-NAS employs a highly reusable width search strategy and a densely connected search block to automatically select the operations of each layer as well as network width and depth via gradient descent. During the search process, the proposed MoG-NAS is capable of avoiding mode collapse due to the smoother search space designed under the model-guided framework. Experimental results on several popular datasets show that our MoD-NAS has achieved even better PSNR performance than current state-of-the-art methods with fewer parameters, lower number of flops, and less amount of testing time.

Xuan Xu, Xin Xiong, Jinge Wang et al.

Video super-resolution, which attempts to reconstruct high-resolution video frames from their corresponding low-resolution versions, has received increasingly more attention in recent years. Most existing approaches opt to use deformable convolution to temporally align neighboring frames and apply traditional spatial attention mechanism (convolution based) to enhance reconstructed features. However, such spatial-only strategies cannot fully utilize temporal dependency among video frames. In this paper, we propose a novel deep learning based VSR algorithm, named Deformable Kernel Spatial Attention Network (DKSAN). Thanks to newly designed Deformable Kernel Convolution Alignment (DKC_Align) and Deformable Kernel Spatial Attention (DKSA) modules, DKSAN can better exploit both spatial and temporal redundancies to facilitate the information propagation across different layers. We have tested DKSAN on AIM2020 Video Extreme Super-Resolution Challenge to super-resolve videos with a scale factor as large as 16. Experimental results demonstrate that our proposed DKSAN can achieve both better subjective and objective performance compared with the existing state-of-the-art EDVR on Vid3oC and IntVID datasets.

Yingxue Pang, Xin Li, Xin Jin et al.

Single image super-resolution (SISR) aims to recover the high-resolution (HR) image from its low-resolution (LR) input image. With the development of deep learning, SISR has achieved great progress. However, It is still a challenge to restore the real-world LR image with complicated authentic degradations. Therefore, we propose FAN, a frequency aggregation network, to address the real-world image super-resolu-tion problem. Specifically, we extract different frequencies of the LR image and pass them to a channel attention-grouped residual dense network (CA-GRDB) individually to output corresponding feature maps. And then aggregating these residual dense feature maps adaptively to recover the HR image with enhanced details and textures. We conduct extensive experiments quantitatively and qualitatively to verify that our FAN performs well on the real image super-resolution task of AIM 2020 challenge. According to the released final results, our team SR-IM achieves the fourth place on the X4 track with PSNR of 31.1735 and SSIM of 0.8728.

Dario Fuoli, Zhiwu Huang, Shuhang Gu et al.

This paper reviews the video extreme super-resolution challenge associated with the AIM 2020 workshop at ECCV 2020. Common scaling factors for learned video super-resolution (VSR) do not go beyond factor 4. Missing information can be restored well in this region, especially in HR videos, where the high-frequency content mostly consists of texture details. The task in this challenge is to upscale videos with an extreme factor of 16, which results in more serious degradations that also affect the structural integrity of the videos. A single pixel in the low-resolution (LR) domain corresponds to 256 pixels in the high-resolution (HR) domain. Due to this massive information loss, it is hard to accurately restore the missing information. Track 1 is set up to gauge the state-of-the-art for such a demanding task, where fidelity to the ground truth is measured by PSNR and SSIM. Perceptually higher quality can be achieved in trade-off for fidelity by generating plausible high-frequency content. Track 2 therefore aims at generating visually pleasing results, which are ranked according to human perception, evaluated by a user study. In contrast to single image super-resolution (SISR), VSR can benefit from additional information in the temporal domain. However, this also imposes an additional requirement, as the generated frames need to be consistent along time.

Qian Ning, Weisheng Dong, Guangming Shi et al.

Deep neural networks (DNNs) based methods have achieved great success in single image super-resolution (SISR). However, existing state-of-the-art SISR techniques are designed like black boxes lacking transparency and interpretability. Moreover, the improvement in visual quality is often at the price of increased model complexity due to black-box design. In this paper, we present and advocate an explainable approach toward SISR named model-guided deep unfolding network (MoG-DUN). Targeting at breaking the coherence barrier, we opt to work with a well-established image prior named nonlocal auto-regressive model and use it to guide our DNN design. By integrating deep denoising and nonlocal regularization as trainable modules within a deep learning framework, we can unfold the iterative process of model-based SISR into a multi-stage concatenation of building blocks with three interconnected modules (denoising, nonlocal-AR, and reconstruction). The design of all three modules leverages the latest advances including dense/skip connections as well as fast nonlocal implementation. In addition to explainability, MoG-DUN is accurate (producing fewer aliasing artifacts), computationally efficient (with reduced model parameters), and versatile (capable of handling multiple degradations). The superiority of the proposed MoG-DUN method to existing state-of-the-art image SR methods including RCAN, SRMDNF, and SRFBN is substantiated by extensive experiments on several popular datasets and various degradation scenarios.

Shan Jia, Xin Li, Chuanbo Hu et al.

We have witnessed rapid advances in both face presentation attack models and presentation attack detection (PAD) in recent years. When compared with widely studied 2D face presentation attacks, 3D face spoofing attacks are more challenging because face recognition systems are more easily confused by the 3D characteristics of materials similar to real faces. In this work, we tackle the problem of detecting these realistic 3D face presentation attacks, and propose a novel anti-spoofing method from the perspective of fine-grained classification. Our method, based on factorized bilinear coding of multiple color channels (namely MC\_FBC), targets at learning subtle fine-grained differences between real and fake images. By extracting discriminative and fusing complementary information from RGB and YCbCr spaces, we have developed a principled solution to 3D face spoofing detection. A large-scale wax figure face database (WFFD) with both images and videos has also been collected as super-realistic attacks to facilitate the study of 3D face presentation attack detection. Extensive experimental results show that our proposed method achieves the state-of-the-art performance on both our own WFFD and other face spoofing databases under various intra-database and inter-database testing scenarios.

Ao Luo, Fan Yang, Xin Li et al.

Crowd counting is an important yet challenging task due to the large scale and density variation. Recent investigations have shown that distilling rich relations among multi-scale features and exploiting useful information from the auxiliary task, i.e., localization, are vital for this task. Nevertheless, how to comprehensively leverage these relations within a unified network architecture is still a challenging problem. In this paper, we present a novel network structure called Hybrid Graph Neural Network (HyGnn) which targets to relieve the problem by interweaving the multi-scale features for crowd density as well as its auxiliary task (localization) together and performing joint reasoning over a graph. Specifically, HyGnn integrates a hybrid graph to jointly represent the task-specific feature maps of different scales as nodes, and two types of relations as edges:(i) multi-scale relations for capturing the feature dependencies across scales and (ii) mutual beneficial relations building bridges for the cooperation between counting and localization. Thus, through message passing, HyGnn can distill rich relations between the nodes to obtain more powerful representations, leading to robust and accurate results. Our HyGnn performs significantly well on four challenging datasets: ShanghaiTech Part A, ShanghaiTech Part B, UCF_CC_50 and UCF_QNRF, outperforming the state-of-the-art approaches by a large margin.

Xuan Xu, Yanfang Ye, Xin Li

Image demosaicing and super-resolution are two important tasks in color imaging pipeline. So far they have been mostly independently studied in the open literature of deep learning; little is known about the potential benefit of formulating a joint demosaicing and super-resolution (JDSR) problem. In this paper, we propose an end-to-end optimization solution to the JDSR problem and demonstrate its practical significance in computational imaging. Our technical contributions are mainly two-fold. On network design, we have developed a Residual-Dense Squeeze-and-Excitation Networks (RDSEN) supported by a pre-demosaicing network (PDNet) as the pre-processing step. We address the issue of spatio-spectral attention for color-filter-array (CFA) data and discuss how to achieve better information flow by concatenating Residue-Dense Squeeze-and-Excitation Blocks (RDSEBs) for JDSR. Experimental results have shown that significant PSNR/SSIM gain can be achieved by RDSEN over previous network architectures including state-of-the-art RCAN. On perceptual optimization, we propose to leverage the latest ideas including relativistic discriminator and pre-excitation perceptual loss function to further improve the visual quality of textured regions in reconstructed images. Our extensive experiment results have shown that Texture-enhanced Relativistic average Generative Adversarial Network (TRaGAN) can produce both subjectively more pleasant images and objectively lower perceptual distortion scores than standard GAN for JDSR. Finally, we have verified the benefit of JDSR to high-quality image reconstruction from real-world Bayer pattern data collected by NASA Mars Curiosity.

Chen Zhao, Jiaqi Yang, Xin Xiong et al.

Point cloud analysis is a fundamental task in 3D computer vision. Most previous works have conducted experiments on synthetic datasets with well-aligned data; while real-world point clouds are often not pre-aligned. How to achieve rotation invariance remains an open problem in point cloud analysis. To meet this challenge, we propose a novel approach toward achieving rotation-invariant (RI) representations by combining local geometry with global topology. In our local-global-representation (LGR)-Net, we have designed a two-branch network where one stream encodes local geometric RI features and the other encodes global topology-preserving RI features. Motivated by the observation that local geometry and global topology have different yet complementary RI responses in varying regions, two-branch RI features are fused by an innovative multi-layer perceptron (MLP) based attention module. To the best of our knowledge, this work is the first principled approach toward adaptively combining global and local information under the context of RI point cloud analysis. Extensive experiments have demonstrated that our LGR-Net achieves the state-of-the-art performance on various rotation-augmented versions of ModelNet40, ShapeNet, ScanObjectNN, and S3DIS.

Xin Li, Tianwei Lin, Xiao Liu et al.

Existing action localization approaches adopt shallow temporal convolutional networks (\ie, TCN) on 1D feature map extracted from video frames. In this paper, we empirically find that stacking more conventional temporal convolution layers actually deteriorates action classification performance, possibly ascribing to that all channels of 1D feature map, which generally are highly abstract and can be regarded as latent concepts, are excessively recombined in temporal convolution. To address this issue, we introduce a novel concept-wise temporal convolution (CTC) layer as an alternative to conventional temporal convolution layer for training deeper action localization networks. Instead of recombining latent concepts, CTC layer deploys a number of temporal filters to each concept separately with shared filter parameters across concepts. Thus can capture common temporal patterns of different concepts and significantly enrich representation ability. Via stacking CTC layers, we proposed a deep concept-wise temporal convolutional network (C-TCN), which boosts the state-of-the-art action localization performance on THUMOS'14 from 42.8 to 52.1 in terms of mAP(\%), achieving a relative improvement of 21.7\%. Favorable result is also obtained on ActivityNet.

Tianwei Lin, Xiao Liu, Xin Li et al.

Temporal action proposal generation is an challenging and promising task which aims to locate temporal regions in real-world videos where action or event may occur. Current bottom-up proposal generation methods can generate proposals with precise boundary, but cannot efficiently generate adequately reliable confidence scores for retrieving proposals. To address these difficulties, we introduce the Boundary-Matching (BM) mechanism to evaluate confidence scores of densely distributed proposals, which denote a proposal as a matching pair of starting and ending boundaries and combine all densely distributed BM pairs into the BM confidence map. Based on BM mechanism, we propose an effective, efficient and end-to-end proposal generation method, named Boundary-Matching Network (BMN), which generates proposals with precise temporal boundaries as well as reliable confidence scores simultaneously. The two-branches of BMN are jointly trained in an unified framework. We conduct experiments on two challenging datasets: THUMOS-14 and ActivityNet-1.3, where BMN shows significant performance improvement with remarkable efficiency and generalizability. Further, combining with existing action classifier, BMN can achieve state-of-the-art temporal action detection performance.

Chen Zhao, Zhiguo Cao, Chi Li et al.

Feature correspondence selection is pivotal to many feature-matching based tasks in computer vision. Searching for spatially k-nearest neighbors is a common strategy for extracting local information in many previous works. However, there is no guarantee that the spatially k-nearest neighbors of correspondences are consistent because the spatial distribution of false correspondences is often irregular. To address this issue, we present a compatibility-specific mining method to search for consistent neighbors. Moreover, in order to extract and aggregate more reliable features from neighbors, we propose a hierarchical network named NM-Net with a series of convolution layers taking the generated graph as input, which is insensitive to the order of correspondences. Our experimental results have shown the proposed method achieves the state-of-the-art performance on four datasets with various inlier ratios and varying numbers of feature consistencies.

Fangfang Wu, Weisheng Dong, Guangming Shi et al.

State-of-the-art approaches toward image restoration can be classified into model-based and learning-based. The former - best represented by sparse coding techniques - strive to exploit intrinsic prior knowledge about the unknown high-resolution images; while the latter - popularized by recently developed deep learning techniques - leverage external image prior from some training dataset. It is natural to explore their middle ground and pursue a hybrid image prior capable of achieving the best in both worlds. In this paper, we propose a systematic approach of achieving this goal called Structured Analysis Sparse Coding (SASC). Specifically, a structured sparse prior is learned from extrinsic training data via a deep convolutional neural network (in a similar way to previous learning-based approaches); meantime another structured sparse prior is internally estimated from the input observation image (similar to previous model-based approaches). Two structured sparse priors will then be combined to produce a hybrid prior incorporating the knowledge from both domains. To manage the computational complexity, we have developed a novel framework of implementing hybrid structured sparse coding processes by deep convolutional neural networks. Experimental results show that the proposed hybrid image restoration method performs comparably with and often better than the current state-of-the-art techniques.

Xin Li, Mooi Choo Chuah

Designing a scheme that can achieve a good performance in predicting single person activities and group activities is a challenging task. In this paper, we propose a novel robust and efficient human activity recognition scheme called ReHAR, which can be used to handle single person activities and group activities prediction. First, we generate an optical flow image for each video frame. Then, both video frames and their corresponding optical flow images are fed into a Single Frame Representation Model to generate representations. Finally, an LSTM is used to pre- dict the final activities based on the generated representations. The whole model is trained end-to-end to allow meaningful representations to be generated for the final activity recognition. We evaluate ReHAR using two well-known datasets: the NCAA Basketball Dataset and the UCFSports Action Dataset. The experimental results show that the pro- posed ReHAR achieves a higher activity recognition accuracy with an order of magnitude shorter computation time compared to the state-of-the-art methods.

Aritra Dutta, Xin Li

Classical principal component analysis (PCA) is not robust to the presence of sparse outliers in the data. The use of the $\ell_1$ norm in the Robust PCA (RPCA) method successfully eliminates the weakness of PCA in separating the sparse outliers. In this paper, by sticking a simple weight to the Frobenius norm, we propose a weighted low rank (WLR) method to avoid the often computationally expensive algorithms relying on the $\ell_1$ norm. As a proof of concept, a background estimation model has been presented and compared with two $\ell_1$ norm minimization algorithms. We illustrate that as long as a simple weight matrix is inferred from the data, one can use the weighted Frobenius norm and achieve the same or better performance.

Aritra Dutta, Xin Li, Peter Richtárik

Principal component pursuit (PCP) is a state-of-the-art approach for background estimation problems. Due to their higher computational cost, PCP algorithms, such as robust principal component analysis (RPCA) and its variants, are not feasible in processing high definition videos. To avoid the curse of dimensionality in those algorithms, several methods have been proposed to solve the background estimation problem in an incremental manner. We propose a batch-incremental background estimation model using a special weighted low-rank approximation of matrices. Through experiments with real and synthetic video sequences, we demonstrate that our method is superior to the state-of-the-art background estimation algorithms such as GRASTA, ReProCS, incPCP, and GFL.