论文检索

Wanjiang Weng, Hongsong Wang, Junbo Wang, Lei He, Guo-Sen Xie

Contrastive learning has achieved great success in skeleton-based representation learning recently. However, the prevailing methods are predominantly negative-based, necessitating additional momentum encoder and memory bank to get negative samples, which increases the difficulty of model training. Furthermore, these methods primarily concentrate on learning a global representation for recognition and retrieval tasks, while overlooking the rich and detailed local representations that are crucial for dense prediction tasks. To alleviate these issues, we introduce a Unified Skeleton-based Dense Representation Learning framework based on feature decorrelation, called USDRL, which employs feature decorrelation across temporal, spatial, and instance domains in a multi-grained manner to reduce redundancy among dimensions of the representations to maximize information extraction from features. Additionally, we design a Dense Spatio-Temporal Encoder (DSTE) to capture fine-grained action representations effectively, thereby enhancing the performance of dense prediction tasks. Comprehensive experiments, conducted on the benchmarks NTU-60, NTU-120, PKU-MMD I, and PKU-MMD II, across diverse downstream tasks including action recognition, action retrieval, and action detection, conclusively demonstrate that our approach significantly outperforms the current state-of-the-art (SOTA) approaches.

Yuanbo Wen, Tao Gao, Jing Zhang, Ziqi Li, Ting Chen

Existing approaches aiming to remove adverse weather degradations compromise the image quality and incur the long processing time. To this end, we introduce a multi-axis prompt and multi-dimension fusion network (MPMF-Net). Specifically, we develop a multi-axis prompts learning block (MPLB), which learns the prompts along three separate axis planes, requiring fewer parameters and achieving superior performance. Moreover, we present a multi-dimension feature interaction block (MFIB), which optimizes intra-scale feature fusion by segregating features along height, width and channel dimensions. This strategy enables more accurate mutual attention and adaptive weight determination. Additionally, we propose the coarse-scale degradation-free implicit neural representations (CDINR) to normalize the degradation levels of different weather conditions. Extensive experiments demonstrate the significant improvements of our model over the recent well-performing approaches in both reconstruction fidelity and inference time.

Yu Wen, Chen Zhang, Chenhao Xie, Xin Fu

Image super-resolution (SR) is essential for bridging the gap between modern hardware and real-time computer graphics (CG) applications. It reduces CG workload by allowing low-resolution rendering, with original quality restored later via mathematical operations or machine learning. However, recent learning-based SR methods often rely on complex models, demanding high computational resources and undermining the benefits of reduced rendering workload. Our qualitative and quantitative analysis of the SR process and rendering reveals that readily accessible rendering information can significantly enhance neural network design by serving as additional features. To capitalize on this, we propose CGSR, an optimization framework designed for lightweight real-time super-resolution. CGSR utilizes rendering information to boost both network extensibility and efficiency. It utilizes progressively available rendering information from the pipeline, which arrives earlier than the rendered frame, enabling pre-processing and masking of latency. These features are then integrated into a selected SR network backbone to form a CG-enhanced network. This network is further optimized and refined into a CG-optimized version using neural architecture search (NAS). To improve runtime performance, CGSR also employs rendering-aware hybrid pruning, which dynamically prunes the network based on temporal rendering data. Evaluation results show that CGSR significantly reduces parameter size, multi-add operations, and inference time while maintaining high SR quality across various backbone SR networks.

Yang Wei, Jingyu Tan, Guowen Xu, Zhuoran Ma, Zhuo Ma, Bin Xiao

Substitute training-based data-free black-box attacks pose a significant threat to enterprise-deployed models. These attacks use a generator to synthesize data and query APIs, then train a substitute model to approximate the target model's decision boundary based on the returned results. However, existing attack methods often struggle to produce sufficiently diverse data, particularly for complex target models and extensive target data domains, severely limiting their practical application. To address this gap, we design domain-augmented learning to improve the quality of the synthetic data domain (SDD) generated by the generator from two perspectives. Specifically, (1) To broaden the SDD's coverage, we introduce textual semantic embeddings into the generator for the first time. (2) For enhancing the SDD's discretization, we propose a competitive optimization strategy that forces the generator to self-compete, along with heterogeneity excitation to overcome the constraints of information entropy on diversity. Comprehensive experiments demonstrate that our method is more effective. In non-targeted attacks on the CIFAR-10 and Tiny-ImageNet datasets, our method outperforms the state-of-the-art by 14% and 7% in attack success rate, respectively.

Xiaobao Wei, Peng Chen, Ming Lu, Hui Chen, Feng Tian

Rendering photorealistic head avatars from arbitrary viewpoints is crucial for various applications like virtual reality. Although previous methods based on Neural Radiance Fields (NeRF) can achieve impressive results, they lack fidelity and efficiency. Recent methods using 3D Gaussian Splatting (3DGS) have improved rendering quality and real-time performance but still require significant storage overhead. In this paper, we introduce a method called GraphAvatar that utilizes Graph Neural Networks (GNN) to generate 3D Gaussians for the head avatar. Specifically, GraphAvatar trains a geometric GNN and an appearance GNN to generate the attributes of the 3D Gaussians from the tracked mesh. Therefore, our method can store the GNN models instead of the 3D Gaussians, significantly reducing the storage overhead to just 10MB. To reduce the impact of face-tracking errors, we also present a novel graph-guided optimization module to refine face-tracking parameters during training. Finally, we introduce a 3D-aware enhancer for post-processing to enhance the rendering quality. We conduct comprehensive experiments to demonstrate the advantages of GraphAvatar, surpassing existing methods in visual fidelity and storage consumption. The ablation study sheds light on the trade-offs between rendering quality and model size.

Jiangning Wei, Lixiong Qin, Bo Yu, Tianjian Zou, Chuhan Yan, Dandan Xiao, Yang Yu, Lan Yang, Ke Li, Jun Liu

Action recognition is a crucial task in artificial intelligence, with significant implications across various domains. We initially perform a comprehensive analysis of seven prominent action recognition methods across five widely-used datasets. This analysis reveals a critical, yet previously overlooked, observation: as the velocity of actions increases, the performance of these methods variably declines, undermining their robustness. This decline in performance poses significant challenges for their application in real-world scenarios. Building on these findings, we introduce the Velocity-Aware Action Recognition (VA-AR) framework to obtain robust action representations across different velocities. Our principal insight is that rapid actions (e.g., the giant circle backward in uneven bars or a smash in badminton) occur within short time intervals, necessitating smaller temporal attention windows to accurately capture intricate changes. Conversely, slower actions (e.g., drinking water or wiping face) require larger windows to effectively encompass the broader context. VA-AR employs a Mixture of Window Attention (MoWA) strategy, dynamically adjusting its attention window size based on the action's velocity. This adjustment enables VA-AR to obtain a velocity-aware representation, thereby enhancing the accuracy of action recognition. Extensive experiments confirm that VA-AR achieves state-of-the-art performance on the same five datasets, demonstrating VA-AR's effectiveness across a broad spectrum of action recognition scenarios.

Baole Wei, Yuxuan Zhou, Liangcai Gao, Zhi Tang

The goal of scene text image super-resolution (STISR) is to enhance the clarity of text within line images, thereby improving readability and enabling more accurate text recognition. However, existing STISR methods often rely heavily on Text Prior (TP) derived from trained recognizers, which can be unreliable and may lead to incorrect glyph restoration. Text images contain two crucial types of information: semantic content from word meanings and structural details from glyphs. When semantic information is unreliable, accurate perception of glyph structures becomes essential. This paper introduces GlyphSR, a novel STISR framework that addresses three key challenges: precise extraction, effective learning, and optimal utilization of glyph structural information. GlyphSR incorporates the Glyph Extraction Module (GEM), a training-free approach leveraging the Segment Anything Model (SAM) to accurately extract character-level glyphs. The Glyph Perception Module (GPM) models and learns glyph structures through segmentation and classification tasks, while the Glyph Fusion Module (GFM) integrates glyph information to enhance overall STISR model performance. Extensive experiments on the TextZoom dataset demonstrate that GlyphSR achieves a new state-of-the-art performance.

Zihao Wang, Yiming Huang, Gengyu Lyu, Yucheng Zhao, Ziyu Zhou, Bochen Xie, Zhen Yang, Yongjian Deng

Salient object detection (SOD) methods for 2D images have great significance in the field of human-computer interaction (HCI). However, as a common data format in HCI, the SOD research in the form of 3D point cloud data remains limited. Previous works commonly treat this task as point cloud segmentation, which perceives all points in the scene for prediction. However, these methods neglect that SOD is designed to simulate human visual perception where human can only see the surfaces rather than occluded point clouds. Thereby, these methods may fail when meet such situations. This paper aims to solve this problem by approximately simulating the perception paradigm of humans towards 3D scenes. Thus, we propose a framework based on the 3D visual point cloud backbone and its multi-view projection named MSV-PCT. Specifically, instead of relying solely on general point cloud learning frameworks, we additionally introduce multi-sparse-view learning branches to supplement the SOD perception. Furthermore, we propose a novel point cloud edge detection loss function to effectively address artifacts, enabling the accurate segmentation of the edges of salient objects from the background. Finally, to evaluate the generalization of point cloud SOD methods, we introduce a new approach to generate simulated PC-SOD datasets from RGBD-SOD data. Experiments on the simulated datasets show that MSV-PCT achieves better accuracy and robustness.

Zicheng Wang, Qiuxia Wu

Designing an appropriate loss function can enhance the discriminative power on gait recognition. However, previous research focuses on improving network structure and enriching input modalities but overlooks the loss functions. Although transferring loss functions from face recognition can address sample-level loss, additional design is needed for part-level loss. Therefore, we have designed a new loss function called Waveloss, aimed at adaptively and dynamically changing the preference for parts of different difficulties. First, the previous method treats the loss of different parts equally, which brings the problems of difficult convergence or susceptibility to noise interference, so we propose norm-fusion to adaptively learn samples of different difficulties. Additionally, since we find the exponential value represents preference for learning different samples, we introduce the Dynamic Learning Process, which dynamically adjusts the exponential value during iteration to focus on samples of varying difficulties at different training stages. Finally, as the changes of the exponential value leads to significant fluctuations in the gradient, we introduce the gradient truncation and normalization to avoid getting trapped in local optima and gradient vanishing or exploding by adaptively adjusting the gradient. Experimental results demonstrate that our proposed Waveloss achieves state-of-the-art performance on various gait recognition datasets and can improve the performance of different backbones as well.

Zhuhao Wang, Yihua Sun, Zihan Li, Xuan Yang, Fang Chen, Hongen Liao

Drafting radiology reports is a complex task requiring flexibility, where radiologists tail content to available information and particular clinical demands. However, most current radiology report generation (RRG) models are constrained to a fixed task paradigm, such as predicting the full ''finding'' section from a single image, inherently involving a mismatch between inputs and outputs. The trained models lack the flexibility for diverse inputs and could generate harmful, input-agnostic hallucinations. To bridge the gap between current RRG models and the clinical demands in practice, we first develop a data generation pipeline to create a new MIMIC-RG4 dataset, which considers four common radiology report drafting scenarios and has perfectly corresponded input and output. Secondly, we propose a novel large language model (LLM) based RRG framework, namely LLM-RG4, which utilizes LLM's flexible instruction-following capabilities and extensive general knowledge. We further develop an adaptive token fusion module that offers flexibility to handle diverse scenarios with different input combinations, while minimizing the additional computational burden associated with increased input volumes. Besides, we propose a token-level loss weighting strategy to direct the model's attention towards positive and uncertain descriptions. Experimental results demonstrate that LLM-RG4 achieves state-of-the-art performance in both clinical efficiency and natural language generation on the MIMIC-RG4 and MIMIC-CXR datasets. We quantitatively demonstrate that our model has minimal input-agnostic hallucinations, whereas current open-source models commonly suffer from this problem.

Zhishen Wang, Rui Wang, Lihua Jing

With the successful transition of Transformers from natural language processing (NLP) to computer vision (CV) domains, Vision Transformers (ViTs) have achieved state-of-the-art performance in many CV tasks. However, backdoor attacks, a significant threat in deep learning, also pose a risk to the security of ViT models. Recently, several backdoor attack methods targeting the patch-level self-attention mechanism in ViTs have been proposed, but they are relatively naive in terms of stealthiness and robustness against defensive measures, lacking in-depth investigation. In this paper, we explore the crucial role of attention-level imperceptibility in backdoor attacks for ViTs and propose an Attention-Imperceptible Backdoor Attacks on Vision Transformers (AIBA). In AIBA, a constrained adversarial perturbation is used as the trigger to achieve visual imperceptibility. Additionally, the trigger is designed to seamlessly implant into the focal areas of the image, ensuring that the trigger receives enough attention from the model without causing anomalies at the attention level. During the backdoor learning process, we designed an efficient constrained bi-level optimization training strategy at the mini-batch level to implant an effective backdoor in the victim model using the imperceptible trigger. We evaluated the effectiveness of the proposed AIBA across multiple datasets and ViT benchmarks and explored the robustness of AIBA against current ViT-specific defense methods. The experimental results demonstrate that our backdoor attack method can successfully implant a powerful and stealthy backdoor into ViTs.

Zhiming Wang, Lin Gu, Feng Lu

CutMix is a data augmentation strategy that cuts and pastes image patches to mixup training data. Existing methods pick either random or salient areas which are often inconsistent to labels, thus misguiding the training model. By our knowledge, we integrate human gaze to guide cutmix for the first time. Since human attention is driven by both high-level recognition and low-level clues, we propose a controllable Top-down Attention Guided Module to obtain a general artificial attention which balances top-down and bottom-up attention. The proposed TdATttenMix then picks the patches and adjust the label mixing ratio that focuses on regions relevant to the current label. Experimental results demonstrate that our TdAttenMix outperforms existing state-of-the-art mixup methods across eight different benchmarks. Additionally, we introduce a new metric based on the human gaze and use this metric to investigate the issue of image-label inconsistency.

Zhen Wang, Yaozu Wu, Dongyuan Li, Shiyin Tan, Zhishuai Yin

Enhancing images captured under low-light conditions has been a topic of research for several years. Nonetheless, existing image restoration techniques mainly concentrate on reconstructing images from RGB data, often neglecting the possibility of utilizing additional modalities. With the progress in handheld technology, capturing thermal images with mobile devices has become straightforward. Investigating the integration of thermal data into image restoration presents a valuable research opportunity. Therefore, in this paper, we propose a multimodal low-light image enhancement task based on thermal information and establish a dataset named TLIE (Thermal-aware Low-light Image Enhancement), consisting of 1,113 samples. Each sample in our dataset includes a low-light image, a normal-light image, and the corresponding thermal map. Additionally, based on TLIE dataset, we develop a multimodal approach that simultaneously processes input images and thermal map data to produce the predicted normal-light images. We compare our method with previous unimodal and multimodal state-of-the-art LIE methods, and the experimental results and detailed ablation studies prove the effectiveness of our method.

Zhen Wang, Zihang Lin, Meng Yuan, Yuehu Liu, Chi Zhang

Recent advances in text-to-image diffusion models have shown an outstanding ability in zero-shot style transfer. However, existing methods often struggle to balance preserving the semantic content of the input image and faithfully transferring the target style in line with the edit prompt. Especially when applied to complex traffic scenes with diverse objects, layouts, and stylistic variations, current diffusion models tend to exhibit Style Neglection, i.e., failing to generate the required style in the prompt. To address this issue, we propose Style Nursing, which directs the model to focus on style subject tokens in the text prompt and excites their corresponding visual activations. Moreover, we introduce Spatial and Semantic Guidance to guide the preservation of content after editing, which utilizes spatial features from the DDIM sampling process together with attention maps from the semantic reconstruction. To evaluate the performance of zero-shot style transfer methods in traffic scenes, we present STREET-6K, a new benchmark dataset comprising 6000 images showcasing diverse traffic scenes and style transfer variations, accompanied by comprehensive annotations and evaluation metrics. Our approach beats state-of-the-art image translation methods in comprehensive quantitative metrics and human evaluations on traffic scene image synthesis while seamlessly generalizing to various other types of images without training or fine-tuning. Further experiments on detection and segmentation tasks show that fine-tuning perception models on our synthesized images improves Recall and mean Intersection over Union (mIoU) by over 10% and 3% respectively in rarely-seen traffic scenes.

Zeyu Wang, Chen Li, Huiying Xu, Xinzhong Zhu, Hongbo Li

Driven by the rapid development of deep learning technology, the YOLO series has set a new benchmark for real-time object detectors. Additionally, transformer-based structures have emerged as the most powerful solution in the field, greatly extending the model's receptive field and achieving significant performance improvements. However, this improvement comes at a cost, as the quadratic complexity of the self-attentive mechanism increases the computational burden of the model. To address this problem, we introduce a simple yet effective baseline approach called Mamba YOLO. Our contributions are as follows: 1) We propose that the ODMamba backbone introduce a State Space Model (SSM) with linear complexity to address the quadratic complexity of self-attention. Unlike the other Transformer-base and SSM-base method, ODMamba is simple to train without pretraining. 2) For real-time requirement, we designed the macro structure of ODMamba, determined the optimal stage ratio and scaling size. 3) We design the RG Block that employs a multi-branch structure to model the channel dimensions, which addresses the possible limitations of SSM in sequence modeling, such as insufficient receptive fields and weak image localization. This design captures localized image dependencies more accurately and significantly. Extensive experiments on the publicly available COCO benchmark dataset show that Mamba YOLO achieves state-of-the-art performance compared to previous methods. Specifically, a tiny version of Mamba YOLO achieves a 7.5% improvement in mAP on a single 4090 GPU with an inference time of 1.5 ms.

Yuxuan Wang, Yijun Liu, Fei Yu, Chen Huang, Kexin Li, Zhiguo Wan, Wanxiang Che, Hongyang Chen

Despite the rapid development of Chinese vision-language models (VLMs), most existing Chinese vision-language (VL) datasets are constructed on Western-centric images from existing English VL datasets. The cultural bias in the images makes these datasets unsuitable for evaluating VLMs in Chinese culture. To remedy this issue, we present a new Chinese Vision-Language Understanding Evaluation (CVLUE) benchmark dataset, where the selection of object categories and images is entirely driven by Chinese native speakers, ensuring that the source images are representative of Chinese culture. The benchmark contains four distinct VL tasks ranging from image-text retrieval to visual question answering, visual grounding and visual dialogue. We present a detailed statistical analysis of CVLUE and provide a baseline performance analysis with several open-source multilingual VLMs on CVLUE and its English counterparts to reveal their performance gap between English and Chinese. Our in-depth category-level analysis reveals a lack of Chinese cultural knowledge in existing VLMs. We also find that fine-tuning on Chinese culture-related VL datasets effectively enhances VLMs' understanding of Chinese culture.

Yuxiao Wang, Wenpeng Neng, Zhenao Wei, Yu Lei, Weiying Xue, Nan Zhuang, Yanwu Xu, Xinyu Jiang, Qi Liu

Human-object contact (HOT) is designed to accurately identify the areas where humans and objects come into contact. Current methods frequently fail to account for scenarios where objects are frequently blocking the view, resulting in inaccurate identification of contact areas. To tackle this problem, we suggest using a perspective interaction HOT detector called PIHOT, which utilizes a depth map generation model to offer depth information of humans and objects related to the camera, thereby preventing false interaction detection. Furthermore, we use mask dilatation and object restoration techniques to restore the texture details in covered areas, improve the boundaries between objects, and enhance the perception of humans interacting with objects. Moreover, a spatial awareness perception is intended to concentrate on the characteristic features close to the points of contact. The experimental results show that the PIHOT algorithm achieves state-of-the-art performance on three benchmark datasets for HOT detection tasks. Compared to the most recent DHOT, our method enjoys an average improvement of 13%, 27.5%, 16%, and 18.5% on SC-Acc., C-Acc., mIoU, and wIoU metrics, respectively.

Yun Wang, Jiahao Zheng, Chenghao Zhang, Zhanjie Zhang, Kunhong Li, Yongjian Zhang, Junjie Hu

Self-supervised stereo matching has drawn attention due to its ability to estimate disparity without needing ground-truth data. However, existing self-supervised stereo matching methods heavily rely on the photo-metric consistency assumption, which is vulnerable to natural disturbances, resulting in ambiguous supervision and inferior performance compared to the supervised ones. To relax the limitation of the photo-metric consistency assumption and even bypass this assumption, we propose a novel self-supervised framework named DualNet, which consists of two key steps: robust self-supervised teacher learning and pseudo-label supervised student training. Specifically, the teacher model is first trained in a self-supervised manner with a focus on feature-metric consistency and data augmentation consistency. Then, the output of the teacher model is geometrically constrained to obtain high-quality pseudo labels. Benefiting from these high-quality pseudo labels, the student model can outperform its teacher model by a large margin. With the two well-designed steps, the proposed framework DualNet ranks 1st among all self-supervised methods on multiple benchmarks, surprisingly even outperforming several supervised counterparts.

Yujia Wang, Fang-Lue Zhang, Neil A. Dodgson

360° images have wide applications in fields such as virtual reality and user experience design. Our goal is to adjust these images to guide users' visual attention. To achieve this, we present a novel task: target scanpath-guided 360° image enhancement, which aims to enhance 360° images based on user-specified target scanpaths. We develop a Progressive Scanpath-Guided Enhancement Method (PSEM) to address this problem through three stages. In the first stage, we propose a Time-Alignment and Spatial Similarity Clustering (TASSC) algorithm that accounts for the spherical nature of 360° images and the temporal dependency of scanpaths to generate representative scanpaths. In the second stage, we learn the differences between the source and the target scanpaths and select the objects to be edited based on these differences. Particularly, we propose a Dual-Stream Scanpath Difference Encoder (DSDE) embedded into the Segment Anything Model (SAM) network for object mask generation. Finally, we employ a Stable Diffusion network fine-tuned with LoRA technology to produce the final enhanced image. Additionally, we design special loss functions to supervise the training of the second and third stages. Experimental results have demonstrated the effectiveness of our approach for scanpath-guided 360° image enhancement.

Yuji Wang, Jingchen Ni, Yong Liu, Chun Yuan, Yansong Tang

Zero-shot Referring Image Segmentation (RIS) identifies the instance mask that best aligns with a specified referring expression without training and fine-tuning, significantly reducing the labor-intensive annotation process. Despite achieving commendable results, previous CLIP-based models have a critical drawback: the models exhibit a notable reduction in their capacity to discern relative spatial relationships of objects. This is because they generate all possible masks on an image and evaluate each masked region for similarity to the given expression, often resulting in decreased sensitivity to direct positional clues in text inputs. Moreover, most methods have weak abilities to manage relationships between primary words and their contexts, causing confusion and reduced accuracy in identifying the correct target region. To address these challenges, we propose IteRPrimE (Iterative Grad-CAM Refinement and Primary word Emphasis), which leverages a saliency heatmap through Grad-CAM from a Vision-Language Pre-trained (VLP) model for image-text matching. An iterative Grad-CAM refinement strategy is introduced to progressively enhance the model's focus on the target region and overcome positional insensitivity, creating a self-correcting effect. Additionally, we design the Primary Word Emphasis module to help the model handle complex semantic relations, enhancing its ability to attend to the intended object. Extensive experiments conducted on the RefCOCO/+/g, and PhraseCut benchmarks demonstrate that IteRPrimE outperforms previous SOTA zero-shot methods, particularly excelling in out-of-domain scenarios.