论文检索

Jianhui Zhang, Jun Yao, Liqi Yan, Yanhong Xu, Zheng Wang

Object trajectory prediction is a hot research issue with wide applications in video surveillance and autonomous driving. The previous studies consider the interaction sparsity mainly among the pedestrians instead of multi-type of objects, which brings new types of interactions and consequently superfluous ones. This paper proposes a Multi-type Object Trajectory Prediction (MOTP) method with a Sparse Multi-relational Graph Convolutional Network (SMGCN) and a novel multi-round Global Temporal Aggregation (GTA). MOTP introduces a novel adaptive sparsification and multi-scale division method to model interactions among multitype of objects. It further incorporates a Sparse Multi-relational Temporal Graph to capture the temporal division of multi-type trajectories, along with a multi-round Global Temporal Aggregation (GTA) mechanism to mitigate error accumulation, and enhances the trajectory prediction accuracy. The extensive evaluation on the ETH, UCY and SDD datasets shows that our method outperforms the typical state-of-the-art works by significant margins. Codes will be available in https://github.com/ sounio/SMGCN.

Jiahang Zhang, Lilang Lin, Jiaying Liu

In real-world scenarios, human actions often fall into a long-tailed distribution. It makes the existing skeleton-based action recognition works, which are mostly designed based on balanced datasets, suffer from a sharp performance degradation. Recently, many efforts have been made to image/video long-tailed learning. However, directly applying them to skeleton data can be sub-optimal due to the lack of consideration of the crucial spatial-temporal motion patterns, especially for some modality-specific methodologies such as data augmentation. To this end, considering the crucial role of the body parts in the spatially concentrated human actions, we attend to the mixing augmentations and propose a novel method, Shap-Mix, which improves long-tailed learning by mining representative motion patterns for tail categories. Specifically, we first develop an effective spatial-temporal mixing strategy for the skeleton to boost representation quality. Then, the employed saliency guidance method is presented, consisting of the saliency estimation based on Shapley value and a tail-aware mixing policy. It preserves the salient motion parts of minority classes in mixed data, explicitly establishing the relationships between crucial body structure cues and high-level semantics. Extensive experiments on three large-scale skeleton datasets show our remarkable performance improvement under both long-tailed and balanced settings. Our project is publicly available at: https://jhang2020.github.io/Projects/Shap-Mix/Shap-Mix.html.

Hansong Zhang, Shikun Li, Fanzhao Lin, Weiping Wang, Zhenxing Qian, Shiming Ge

Dataset condensation addresses the problem of data burden by learning a small synthetic training set that preserves essential knowledge from the larger real training set. To date, the state-of-the-art (SOTA) results are often yielded by optimization-oriented methods, but their inefficiency hinders their application to realistic datasets. On the other hand, the Distribution-Matching (DM) methods show remarkable efficiency but sub-optimal results compared to optimization-oriented methods. In this paper, we reveal the limitations of current DM-based methods from the inner-class and inter-class views, i.e., Persistent Training and Distribution Shift. To address these problems, we propose a new DM-based method named Dual-view distribution AligNment for dataset CondEnsation (DANCE), which exploits a few pre-trained models to improve DM from both inner-class and inter-class views. Specifically, from the inner-class view, we construct multiple ``mid encoders'' to perform pseudo long-term distribution alignment, making the condensed set a good proxy of the real one during the whole training process; while from the inter-class view, we use the expert models to perform distribution calibration, ensuring the synthetic data remains in the real class region during condensing. Experiments demonstrate the proposed method achieves a SOTA performance while maintaining comparable efficiency with the original DM across various scenarios. Source codes are available at https://github.com/Hansong-Zhang/DANCE.

Hangtao Zhang, Shengshan Hu, Yichen Wang, Leo Yu Zhang, Ziqi Zhou, Xianlong Wang, Yanjun Zhang, Chao Chen

Object detection tasks, crucial in safety-critical systems like autonomous driving, focus on pinpointing object locations. These detectors are known to be susceptible to backdoor attacks. However, existing backdoor techniques have primarily been adapted from classification tasks, overlooking deeper vulnerabilities specific to object detection. This paper is dedicated to bridging this gap by introducing Detector Collapse (DC), a brand-new backdoor attack paradigm tailored for object detection. DC is designed to instantly incapacitate detectors (i.e., severely impairing detector's performance and culminating in a denial-of-service). To this end, we develop two innovative attack schemes: Sponge for triggering widespread misidentifications and Blinding for rendering objects invisible. Remarkably, we introduce a novel poisoning strategy exploiting natural objects, enabling DC to act as a practical backdoor in real-world environments. Our experiments on different detectors across several benchmarks show a significant improvement (~10%-60% absolute and ~2-7x relative) in attack efficacy over state-of-the-art attacks.

Haiyang Zhang, Mengchao Wang, Shuai He, Anlong Ming

Current text-to-image synthesis (TIS) models have demonstrated the ability to generate high-fidelity images based on textual prompts. However, the efficacy of these models heavily relies on the keywords present in the prompts, and there is a dearth of objective analysis regarding how different keywords impact the ultimate quality of generated results. Therefore, manual evaluation becomes necessary but limited and inefficient to ascertain the role played by keywords. In this paper, we propose automated keywords-ranking for prompts (AK4Prompts), a keyword evaluation model based on mainstream TIS models that explicitly quantifies the multidimensional impact of various keywords on image generation based on prompts. To enable personalized keyword evaluation based on prompt content, we propose decoupling the latent representations of keywords and prompts in TIS models, followed by integrating the semantic features of prompts into keywords. For quantitative and multidimensional evaluation, we align the fused features of keywords using HPSv2, aesthetic score, and CLIP score, each representing distinct factors contributing to keyword impact. Our AK4Prompts can flexibly and automatically select the keywords that best match the original prompt based on individual user preferences. Extensive experimental results show the superiority of AK4Prompts to improve the quality of generated images significantly over strong baselines. Our approach not only enhances usability and user experience but also addresses the current gap in automated analysis and evaluation of keyword effects. Our code is availableat https://github.com/mRobotit/AK4Prompts.

Guangtong Zhang, Bineng Zhong, Qihua Liang, Zhiyi Mo, Shuxiang Song

Most existing visual-language trackers greatly rely on the initial language descriptions on a target object to extract their multi-modal features. However, the initial language descriptions are often inaccurate in a highly time-varying video sequence and thus greatly deteriorate their tracking performance due to the low quality of extracted multi-modal features. To address this challenge, we propose a Diffusion Mask-Driven Visual-language Tracker (DMTrack) based on a diffusion model. Confronting the issue of low-quality multi-modal features due to inaccurate language descriptions, we leverage the diffusion model to capture high-quality semantic information from multi-modal features and transform it into target mask features. During the training phase, we further enhance the diffusion model's perception of pixel-level features by calculating the loss between the target mask features and the ground truth masks. Additionally, we perform joint localization of the target using both target mask features and visual features, instead of relying solely on multi-modal features for localization. Through extensive experiments on four tracking benchmarks (i.e., LaSOT, TNL2K, LaSOText, and OTB-Lang), we validate that our proposed Diffusion Mask-Driven Visual-language Tracker can improve the robustness and effectiveness of the model.

Mengmeng Zhan, Zongqian Wu, Rongyao Hu, Ping Hu, Heng Tao Shen, Xiaofeng Zhu

In domain adaptation, challenges such as data privacy constraints can impede access to source data, catalyzing the development of source-free domain adaptation (SFDA) methods. However, current approaches heavily rely on models trained on source data, posing the risk of overfitting and suboptimal generalization.This paper introduces a dynamic prompt learning paradigm that harnesses the power of large-scale vision-language models to enhance the semantic transfer of source models. Specifically, our approach fosters robust and adaptive collaboration between the source-trained model and the vision-language model, facilitating the reliable extraction of domain-specific information from unlabeled target data, while consolidating domain-invariant knowledge. Without the need for accessing source data, our method amalgamates the strengths inherent in both traditional SFDA approaches and vision-language models, formulating a collaborative framework for addressing SFDA challenges. Extensive experiments conducted on three benchmark datasets showcase the superiority of our framework over previous SOTA methods.

Hongliang Zeng, Ping Zhang, Chengjiong Wu, Jiahua Wang, Tingyu Ye, Fang Li

Precise perception of articulated objects is vital for empowering service robots. Recent studies mainly focus on point cloud, a single-modal approach, often neglecting vital texture and lighting details and assuming ideal conditions like optimal viewpoints, unrepresentative of real-world scenarios. To address these limitations, we introduce MARS, a novel framework for articulated object characterization. It features a multi-modal fusion module utilizing multi-scale RGB features to enhance point cloud features, coupled with reinforcement learning-based active sensing for autonomous optimization of observation viewpoints. In experiments conducted with various articulated object instances from the PartNet-Mobility dataset, our method outperformed current state-of-the-art methods in joint parameter estimation accuracy. Additionally, through active sensing, MARS further reduces errors, demonstrating enhanced efficiency in handling suboptimal viewpoints. Furthermore, our method effectively generalizes to real-world articulated objects, enhancing robot interactions. Code is available at https://github.com/robhlzeng/MARS.

Youngsik Yun, Jihie Kim

Image Captioning generates descriptive sentences from images using Vision-Language Pre-trained models (VLPs) such as BLIP, which has improved greatly. However, current methods lack the generation of detailed descriptive captions for the cultural elements depicted in the images, such as the traditional clothing worn by people from Asian cultural groups. In this paper, we propose a new framework, Culturally-aware Image Captioning (CIC), that generates captions and describes cultural elements extracted from cultural visual elements in images representing cultures. Inspired by methods combining visual modality and Large Language Models (LLMs) through appropriate prompts, our framework (1) generates questions based on cultural categories from images, (2) extracts cultural visual elements from Visual Question Answering (VQA) using generated questions, and (3) generates culturally-aware captions using LLMs with the prompts. Our human evaluation conducted on 45 participants from 4 different cultural groups with a high understanding of the corresponding culture shows that our proposed framework generates more culturally descriptive captions when compared to the image captioning baseline based on VLPs. Resources can be found at https://shane3606.github.io/cic.

Yao Yuan, Wutao Liu, Pan Gao, Qun Dai, Jie Qin

Recently, unsupervised salient object detection (USOD) has gained increasing attention due to its annotation-free nature. However, current methods mainly focus on specific tasks such as RGB and RGB-D, neglecting the potential for task migration. In this paper, we propose a unified USOD framework for generic USOD tasks. Firstly, we propose a Progressive Curriculum Learning-based Saliency Distilling (PCL-SD) mechanism to extract saliency cues from a pre-trained deep network. This mechanism starts with easy samples and progressively moves towards harder ones, to avoid initial interference caused by hard samples. Afterwards, the obtained saliency cues are utilized to train a saliency detector, and we employ a Self-rectify Pseudo-label Refinement (SPR) mechanism to improve the quality of pseudo-labels. Finally, an adapter-tuning method is devised to transfer the acquired saliency knowledge, leveraging shared knowledge to attain superior transferring performance on the target tasks. Extensive experiments on five representative SOD tasks confirm the effectiveness and feasibility of our proposed method. Code and supplement materials are available at https://github.com/I2-Multimedia-Lab/A2S-v3.

Xiaotian Yu, Haoming Luo, Jiacong Hu, Xiuming Zhang, Yuexuan Wang, Wenjie Liang, Yijun Bei, Mingli Song, Zunlei Feng

Pathological slides are commonly gigapixel images with abundant information and are therefore significant for clinical diagnosis. However, the ultra-large size makes both training and evaluation extremely time-consuming. Most existing methods need to crop the slide into patches, which also leads to large memory requirements. In this paper, we propose the Self-reform Multilayer Transformer (SMT) to accelerate the pathological image diagnosis and prognosis. Inspired by the pathologists' diagnostic procedure, SMT is designed to achieve layer-by-layer focus on critical regions. In the forward process, the first layer takes thumbnails as inputs and measures the significance of each patch that deserves focusing. Images from focused regions are cropped with a higher magnification and used as the input of the next layer. By analogy, the third layer inputs are focused images of second layer, which contain abundant cellular features. In addition to the forward focusing, the backward reform strategy is proposed to improve the precision of former layers. This cyclic process achieves iterative interactions for better performance on both classification and focusing. In this way, only a small part of critical patches are required in SMT for diagnosis and prognosis. Sufficient experiments demonstrate that SMT achieves hundreds times faster speed, while achieving comparable accuracy and less storage compared with existing SOTA methods.

Chong Yu, Tao Chen, Zhongxue Gan, Jiayuan Fan

As Artificial Intelligence evolves, the neural models vulnerable to adversarial attacks may produce fatal results in critical applications. This paper mainly discusses the robustness of the compressed neural models facing adversarial attacks. A few studies discuss the interaction between model compression and adversarial attack. However, they focus on the robustness against the traditional attacks designed for the dense models, not the attacks intended explicitly for the compressed models, using sparsity and quantization techniques. Compressed models often have fewer parameters and smaller sizes that are more friendly to resource-limited devices than dense models, so they are widely deployed in various edge and mobile devices. However, introducing the sparsity and quantization into neural models further imposes higher attack risks. A specific adversarial attack method (Spear) is proposed to generate the particular adversarial attack samples for evaluating the robustness of the compressed models. The Spear attack finds minimal perturbations to create the attack samples to maximize the different behaviors between the compressed and dense reference models. We demonstrate the proposed Spear attack technique can generally be applied to various networks and tasks through quantitative and ablation experiments.

Shi Yin, Shijie Huang, Shangfei Wang, Jinshui Hu, Tao Guo, Bing Yin, Baocai Yin, Cong Liu

Recently, heatmap regression methods based on 1D landmark representations have shown prominent performance on locating facial landmarks. However, previous methods ignored to make deep explorations on the good potentials of 1D landmark representations for sequential and structural modeling of multiple landmarks to track facial landmarks. To address this limitation, we propose a Transformer architecture, namely 1DFormer, which learns informative 1D landmark representations by capturing the dynamic and the geometric patterns of landmarks via token communications in both temporal and spatial dimensions for facial landmark tracking. For temporal modeling, we propose a confidence-enhanced multi-head attention mechanism with a recurrently token mixing strategy to adaptively and robustly embed long-term landmark dynamics into their 1D representations; for structure modeling, we design intra-group and inter-group geometric encoding mechanisms to encode the component-level as well as global-level facial structure patterns as a refinement for the 1D representations of landmarks through token communications in the spatial dimension via 1D convolutional layers. Experimental results on the 300VW and the TF databases show that 1DFormer successfully models the long-range sequential patterns as well as the inherent facial structures to learn informative 1D representations of landmark sequences, and achieves state-of-the-art performance on facial landmark tracking. Codes of our model are available in the supplementary materials.

Yiwei Yang, Zheyuan Liu, Jun Jia, Zhongpai Gao, Yunhao Li, Wei Sun, Xiaohong Liu, Guangtao Zhai

Traditional image steganography focuses on concealing one image within another, aiming to avoid steganalysis by unauthorized entities. Coverless image steganography (CIS) enhances imperceptibility by not using any cover image. Recent works have utilized text prompts as keys in CIS through diffusion models. However, this approach faces three challenges: invalidated when private prompt is guessed, crafting public prompts for semantic diversity, and the risk of prompt leakage during frequent transmission. To address these issues, we propose DiffStega, an innovative training-free diffusion-based CIS strategy for universal application. DiffStega uses a password-dependent reference image as an image prompt alongside the text, ensuring that only authorized parties can retrieve the hidden information. Furthermore, we develop Noise Flip technique to further secure the steganography against unauthorized decryption. To comprehensively assess our method across general CIS tasks, we create a dataset comprising various image steganography instances. Experiments indicate substantial improvements in our method over existing ones, particularly in aspects of versatility, password sensitivity, and recovery quality. Codes are available at https://github.com/evtricks/DiffStega.

Teng Yang, Song Xiao, Wenqian Dong, Jiahui Qu, Yueguang Yang

The joint classification of multisource remote sensing data is a prominent research field. However, most of the existing works are tailored for two specific data sources, which fail to effectively address the diverse combinations of data sources in practical applications. The importance of designing a unified network with applicability has been disregarded. In this paper, we propose a unified and self-supervised Symbiotic Diffusion framework (named SymDiffuser), which achieves the joint classification of any pair of different remote sensing data sources in a single model. The SymDiffuser captures the inter-modal relationship through establishing reciprocal conditional distributions across diverse sources step by step. The fusion process of multisource data is consistently represented within the framework from a data distribution perspective. Subsequently, features under the current conditional distribution at each time step is integrated during the downstream phase to accomplish the classification task. Such joint classification methodology transcends source-specific considerations, rendering it applicable to remote sensing data from any diverse sources. The experimental results showcase the framework's potential in achieving state-of-the-art performance in multimodal fusion classification task.

Haolin Yang, Chaoqiang Zhao, Lu Sheng, Yang Tang

Nighttime self-supervised monocular depth estimation has received increasing attention in recent years. However, using night images for self-supervision is unreliable because the photometric consistency assumption is usually violated in the videos taken under complex lighting conditions. Even with domain adaptation or photometric loss repair, performance is still limited by the poor supervision of night images on trainable networks. In this paper, we propose a self-supervised nighttime monocular depth estimation method that does not use any night images during training. Our framework utilizes day images as a stable source for self-supervision and applies physical priors (e.g., wave optics, reflection model and read-shot noise model) to compensate for some key day-night differences. With day-to-night data distribution compensation, our framework can be trained in an efficient one-stage self-supervised manner. Though no nighttime images are considered during training, qualitative and quantitative results demonstrate that our method achieves SoTA depth estimating results on the challenging nuScenes-Night and RobotCar-Night compared with existing methods.

Dejie Yang, Zhu Xu, Wentao Mo, Qingchao Chen, Siyuan Huang, Yang Liu

3D Vision-Language Pre-training (3D-VLP) aims to provide a pre-train model which can bridge 3D scenes with natural language, which is an important technique for embodied intelligence. However, current 3D-VLP datasets are hindered by limited scene-level diversity and insufficient fine-grained annotations (only 1.2K scenes and 280K textual annotations in ScanScribe), primarily due to the labor-intensive of collecting and annotating 3D scenes. To overcome these obstacles, we construct SynVL3D, a comprehensive synthetic scene-text corpus with 10K indoor scenes and 1M descriptions at object, view, and room levels, which has the advantages of diverse scene data, rich textual descriptions, multi-grained 3D-text associations, and low collection cost. Utilizing the rich annotations in SynVL3D, we pre-train a simple and unified Transformer for aligning 3D and language with multi-grained pretraining tasks. Moreover, we propose a synthetic-to-real domain adaptation in downstream task fine-tuning process to address the domain shift. Through extensive experiments, we verify the effectiveness of our model design by achieving state-of-the-art performance on downstream tasks including visual grounding, dense captioning, and question answering. Codes are available at: https://github.com/idejie/3DSyn

Shiyue Yan, Xiaoshi Qiu, Qingmin Liao, Jing-Hao Xue, Shaojun Liu

Bokeh rendering for images shot with small apertures has drawn much attention in practice. Very recently people start to explore diffusion models for bokeh rendering, aiming to leverage the models' surging power of image generation. However, we can clearly observe two big issues with the images rendered by diffusion models: large fluctuation and severe color deviation. To address these issues, we propose in this paper a prior-aware sampling approach, which can adaptively control the noise scale through learned priors, and a prior-aware noise scheduling strategy, which can greatly reduce the number of inference steps without sacrificing performance. Extensive experiments show that our method can effectively alleviate the fluctuation problem of sampling results while ensuring similar color styles to the input image. In addition, our method outperforms state-of-the-art methods, sometimes even with only two steps of sampling. Our code is available at https://github.com/Loeiii/Reschedule-Diffusion-based-Bokeh-Rendering.

Rui Yan, Hongyu Qu, Xiangbo Shu, Wenbin Li, Jinhui Tang, Tieniu Tan

Finetuning the large vision-language models on video data with a set of learnable prompts has shown promising performance on zero-shot activity recognition but still requires extra video data and expensive training costs. Inspired by recent Test-time Prompt Tuning (TPT) on the image domain, this work attempts to extend TPT to video data for zero-shot activity recognition. However, monotonous spatial augmentation and short class names cannot meet the need to capture diverse and complicated semantics of human behavior during prompt tuning. To this end, this work proposes a Dual Temporal-Sync Test-time Prompt Tuning (DTS-TPT) framework for zero-shot activity recognition. DTS-TPT tunes the learnable prompts appended to text inputs on video feature sequences of different temporal scales in multiple steps during test time. In each tuning step, we minimize the semantic consistency among the predictions from video feature sequences randomly augmented via AugMix with both original class names and the corresponding description generated through LLM. Compared with the state-of-the-art methods, the proposed method improves the zero-shot top-1 accuracy by approximately 2% ~ 5% on popular benchmarks. The code is available at https://github.com/quhongyu/DTS-TPT.

Huibin Yan, Shuoyao Wang

The U-shape (encoder-decoder) architecture, combined with effective blocks, has shown significant success in image restoration. In U-shape models, there is insufficient focus on the feature fusion problem between encoder and decoder features at the same level. Current methods often employ simplistic operations like summation or concatenation, which makes it difficult to strike a balance between performance and complexity. To address this issue, we propose a compression-in-the-middle mechanism, termed Integration-Compression-Integration (ICI), which effectively conducts dense fusion and avoids information loss. From the block design perspective, we design a multi-dimension aggregation (MDA) mechanism, capable of effectively aggregating features from both the channel and spatial dimension. Combining the IntegrationCompression-Integration feature fusion and the multi-dimension aggregation, our dense fusion and multi-dimension aggregation network (DFMDANet) achieves superior performance over state-ofthe-art algorithms on 16 benchmarking datasets for numerous image restoration tasks.