arXiv subjects

Jin Tang

Publications and source records attributed to Jin Tang.

At least 127 records · Page 7Linked to original sources

arXiv2024

Pedestrian Attribute Recognition via CLIP based Prompt Vision-Language Fusion

Existing pedestrian attribute recognition (PAR) algorithms adopt pre-trained CNN (e.g., ResNet) as their backbone network for visual feature learning, which might obtain sub-optimal results due to the insufficient employment of the relations between pedestrian images and attribute labels. In this paper, we formulate PAR as a vision-language fusion problem and fully exploit the relations between pedestrian images and attribute labels. Specifically, the attribute phrases are first expanded into sentences, and then the pre-trained vision-language model CLIP is adopted as our backbone for feature embedding of visual images and attribute descriptions. The contrastive learning objective connects the vision and language modalities well in the CLIP-based feature space, and the Transformer layers used in CLIP can capture the long-range relations between pixels. Then, a multi-modal Transformer is adopted to fuse the dual features effectively and feed-forward network is used to predict attributes. To optimize our network efficiently, we propose the region-aware prompt tuning technique to adjust very few parameters (i.e., only the prompt vectors and classification heads) and fix both the pre-trained VL model and multi-modal Transformer. Our proposed PAR algorithm only adjusts 0.75% learnable parameters compared with the fine-tuning strategy. It also achieves new state-of-the-art performance on both standard and zero-shot settings for PAR, including RAPv1, RAPv2, WIDER, PA100K, and PETA-ZS, RAP-ZS datasets. The source code and pre-trained models will be released on https://github.com/Event-AHU/OpenPAR.

cs.CV↗

arXiv2024

VFM-Det: Towards High-Performance Vehicle Detection via Large Foundation Models

Existing vehicle detectors are usually obtained by training a typical detector (e.g., YOLO, RCNN, DETR series) on vehicle images based on a pre-trained backbone (e.g., ResNet, ViT). Some researchers also exploit and enhance the detection performance using pre-trained large foundation models. However, we think these detectors may only get sub-optimal results because the large models they use are not specifically designed for vehicles. In addition, their results heavily rely on visual features, and seldom of they consider the alignment between the vehicle's semantic information and visual representations. In this work, we propose a new vehicle detection paradigm based on a pre-trained foundation vehicle model (VehicleMAE) and a large language model (T5), termed VFM-Det. It follows the region proposal-based detection framework and the features of each proposal can be enhanced using VehicleMAE. More importantly, we propose a new VAtt2Vec module that predicts the vehicle semantic attributes of these proposals and transforms them into feature vectors to enhance the vision features via contrastive learning. Extensive experiments on three vehicle detection benchmark datasets thoroughly proved the effectiveness of our vehicle detector. Specifically, our model improves the baseline approach by $+5.1\%$, $+6.2\%$ on the $AP_{0.5}$, $AP_{0.75}$ metrics, respectively, on the Cityscapes dataset.The source code of this work will be released at https://github.com/Event-AHU/VFM-Det.

cs.CV↗

arXiv2024

Full-frequency dynamic convolution: a physical frequency-dependent convolution for sound event detection

Recently, 2D convolution has been found unqualified in sound event detection (SED). It enforces translation equivariance on sound events along frequency axis, which is not a shift-invariant dimension. To address this issue, dynamic convolution is used to model the frequency dependency of sound events. In this paper, we proposed the first full-dynamic method named full-frequency dynamic convolution (FFDConv). FFDConv generates frequency kernels for every frequency band, which is designed directly in the structure for frequency-dependent modeling. It physically furnished 2D convolution with the capability of frequency-dependent modeling. FFDConv outperforms not only the baseline by 6.6% in DESED real validation dataset in terms of PSDS1, but outperforms the other full-dynamic methods. In addition, by visualizing features of sound events, we observed that FFDConv could effectively extract coherent features in specific frequency bands, consistent with the vocal continuity of sound events. This proves that FFDConv has great frequency-dependent perception ability.

eess.AS↗

arXiv2024

SELD-Mamba: Selective State-Space Model for Sound Event Localization and Detection with Source Distance Estimation

In the Sound Event Localization and Detection (SELD) task, Transformer-based models have demonstrated impressive capabilities. However, the quadratic complexity of the Transformer's self-attention mechanism results in computational inefficiencies. In this paper, we propose a network architecture for SELD called SELD-Mamba, which utilizes Mamba, a selective state-space model. We adopt the Event-Independent Network V2 (EINV2) as the foundational framework and replace its Conformer blocks with bidirectional Mamba blocks to capture a broader range of contextual information while maintaining computational efficiency. Additionally, we implement a two-stage training method, with the first stage focusing on Sound Event Detection (SED) and Direction of Arrival (DoA) estimation losses, and the second stage reintroducing the Source Distance Estimation (SDE) loss. Our experimental results on the 2024 DCASE Challenge Task3 dataset demonstrate the effectiveness of the selective state-space model in SELD and highlight the benefits of the two-stage training approach in enhancing SELD performance.

cs.SD↗

arXiv2024

Visible-Thermal Multiple Object Tracking: Large-scale Video Dataset and Progressive Fusion Approach

The complementary benefits from visible and thermal infrared data are widely utilized in various computer vision task, such as visual tracking, semantic segmentation and object detection, but rarely explored in Multiple Object Tracking (MOT). In this work, we contribute a large-scale Visible-Thermal video benchmark for MOT, called VT-MOT. VT-MOT has the following main advantages. 1) The data is large scale and high diversity. VT-MOT includes 582 video sequence pairs, 401k frame pairs from surveillance, drone, and handheld platforms. 2) The cross-modal alignment is highly accurate. We invite several professionals to perform both spatial and temporal alignment frame by frame. 3) The annotation is dense and high-quality. VT-MOT has 3.99 million annotation boxes annotated and double-checked by professionals, including heavy occlusion and object re-acquisition (object disappear and reappear) challenges. To provide a strong baseline, we design a simple yet effective tracking framework, which effectively fuses temporal information and complementary information of two modalities in a progressive manner, for robust visible-thermal MOT. A comprehensive experiment are conducted on VT-MOT and the results prove the superiority and effectiveness of the proposed method compared with state-of-the-art methods. From the evaluation results and analysis, we specify several potential future directions for visible-thermal MOT. The project is released in https://github.com/wqw123wqw/PFTrack.

cs.CV↗

arXiv2024

Semantics Guided Disentangled GAN for Chest X-ray Image Rib Segmentation

The label annotations for chest X-ray image rib segmentation are time consuming and laborious, and the labeling quality heavily relies on medical knowledge of annotators. To reduce the dependency on annotated data, existing works often utilize generative adversarial network (GAN) to generate training data. However, GAN-based methods overlook the nuanced information specific to individual organs, which degrades the generation quality of chest X-ray image. Hence, we propose a novel Semantics guided Disentangled GAN (SD-GAN), which can generate the high-quality training data by fully utilizing the semantic information of different organs, for chest X-ray image rib segmentation. In particular, we use three ResNet50 branches to disentangle features of different organs, then use a decoder to combine features and generate corresponding images. To ensure that the generated images correspond to the input organ labels in semantics tags, we employ a semantics guidance module to perform semantic guidance on the generated images. To evaluate the efficacy of SD-GAN in generating high-quality samples, we introduce modified TransUNet(MTUNet), a specialized segmentation network designed for multi-scale contextual information extracting and multi-branch decoding, effectively tackling the challenge of organ overlap. We also propose a new chest X-ray image dataset (CXRS). It includes 1250 samples from various medical institutions. Lungs, clavicles, and 24 ribs are simultaneously annotated on each chest X-ray image. The visualization and quantitative results demonstrate the efficacy of SD-GAN in generating high-quality chest X-ray image-mask pairs. Using generated data, our trained MTUNet overcomes the limitations of the data scale and outperforms other segmentation networks.

eess.IV↗

arXiv2024

Retain, Blend, and Exchange: A Quality-aware Spatial-Stereo Fusion Approach for Event Stream Recognition

Existing event stream-based pattern recognition models usually represent the event stream as the point cloud, voxel, image, etc., and design various deep neural networks to learn their features. Although considerable results can be achieved in simple cases, however, the model performance may be limited by monotonous modality expressions, sub-optimal fusion, and readout mechanisms. In this paper, we propose a novel dual-stream framework for event stream-based pattern recognition via differentiated fusion, termed EFV++. It models two common event representations simultaneously, i.e., event images and event voxels. The spatial and three-dimensional stereo information can be learned separately by utilizing Transformer and Graph Neural Network (GNN). We believe the features of each representation still contain both efficient and redundant features and a sub-optimal solution may be obtained if we directly fuse them without differentiation. Thus, we divide each feature into three levels and retain high-quality features, blend medium-quality features, and exchange low-quality features. The enhanced dual features will be fed into the fusion Transformer together with bottleneck features. In addition, we introduce a novel hybrid interaction readout mechanism to enhance the diversity of features as final representations. Extensive experiments demonstrate that our proposed framework achieves state-of-the-art performance on multiple widely used event stream-based classification datasets. Specifically, we achieve new state-of-the-art performance on the Bullying10k dataset, i.e., $90.51\%$, which exceeds the second place by $+2.21\%$. The source code of this paper has been released on \url{https://github.com/Event-AHU/EFV_event_classification/tree/EFVpp}.

cs.CV↗

arXiv2024

Graph Edge Representation via Tensor Product Graph Convolutional Representation

Graph Convolutional Networks (GCNs) have been widely studied. The core of GCNs is the definition of convolution operators on graphs. However, existing Graph Convolution (GC) operators are mainly defined on adjacency matrix and node features and generally focus on obtaining effective node embeddings which cannot be utilized to address the graphs with (high-dimensional) edge features. To address this problem, by leveraging tensor contraction representation and tensor product graph diffusion theories, this paper analogously defines an effective convolution operator on graphs with edge features which is named as Tensor Product Graph Convolution (TPGC). The proposed TPGC aims to obtain effective edge embeddings. It provides a complementary model to traditional graph convolutions (GCs) to address the more general graph data analysis with both node and edge features. Experimental results on several graph learning tasks demonstrate the effectiveness of the proposed TPGC.

cs.LG↗

arXiv2024

Knowledge-driven Subspace Fusion and Gradient Coordination for Multi-modal Learning

Multi-modal learning plays a crucial role in cancer diagnosis and prognosis. Current deep learning based multi-modal approaches are often limited by their abilities to model the complex correlations between genomics and histology data, addressing the intrinsic complexity of tumour ecosystem where both tumour and microenvironment contribute to malignancy. We propose a biologically interpretative and robust multi-modal learning framework to efficiently integrate histology images and genomics by decomposing the feature subspace of histology images and genomics, reflecting distinct tumour and microenvironment features. To enhance cross-modal interactions, we design a knowledge-driven subspace fusion scheme, consisting of a cross-modal deformable attention module and a gene-guided consistency strategy. Additionally, in pursuit of dynamically optimizing the subspace knowledge, we further propose a novel gradient coordination learning strategy. Extensive experiments demonstrate the effectiveness of the proposed method, outperforming state-of-the-art techniques in three downstream tasks of glioma diagnosis, tumour grading, and survival analysis. Our code is available at https://github.com/helenypzhang/Subspace-Multimodal-Learning.

eess.IV↗

arXiv2024

A Unified Graph Selective Prompt Learning for Graph Neural Networks

In recent years, graph prompt learning/tuning has garnered increasing attention in adapting pre-trained models for graph representation learning. As a kind of universal graph prompt learning method, Graph Prompt Feature (GPF) has achieved remarkable success in adapting pre-trained models for Graph Neural Networks (GNNs). By fixing the parameters of a pre-trained GNN model, the aim of GPF is to modify the input graph data by adding some (learnable) prompt vectors into graph node features to better align with the downstream tasks on the smaller dataset. However, existing GPFs generally suffer from two main limitations. First, GPFs generally focus on node prompt learning which ignore the prompting for graph edges. Second, existing GPFs generally conduct the prompt learning on all nodes equally which fails to capture the importances of different nodes and may perform sensitively w.r.t noisy nodes in aligning with the downstream tasks. To address these issues, in this paper, we propose a new unified Graph Selective Prompt Feature learning (GSPF) for GNN fine-tuning. The proposed GSPF integrates the prompt learning on both graph node and edge together, which thus provides a unified prompt model for the graph data. Moreover, it conducts prompt learning selectively on nodes and edges by concentrating on the important nodes and edges for prompting which thus make our model be more reliable and compact. Experimental results on many benchmark datasets demonstrate the effectiveness and advantages of the proposed GSPF method.

cs.LG↗

arXiv2024

AFter: Attention-based Fusion Router for RGBT Tracking

Multi-modal feature fusion as a core investigative component of RGBT tracking emerges numerous fusion studies in recent years. However, existing RGBT tracking methods widely adopt fixed fusion structures to integrate multi-modal feature, which are hard to handle various challenges in dynamic scenarios. To address this problem, this work presents a novel \emph{A}ttention-based \emph{F}usion rou\emph{ter} called AFter, which optimizes the fusion structure to adapt to the dynamic challenging scenarios, for robust RGBT tracking. In particular, we design a fusion structure space based on the hierarchical attention network, each attention-based fusion unit corresponding to a fusion operation and a combination of these attention units corresponding to a fusion structure. Through optimizing the combination of attention-based fusion units, we can dynamically select the fusion structure to adapt to various challenging scenarios. Unlike complex search of different structures in neural architecture search algorithms, we develop a dynamic routing algorithm, which equips each attention-based fusion unit with a router, to predict the combination weights for efficient optimization of the fusion structure. Extensive experiments on five mainstream RGBT tracking datasets demonstrate the superior performance of the proposed AFter against state-of-the-art RGBT trackers. We release the code in https://github.com/Alexadlu/AFter.

cs.CV↗

arXiv2024

Pre-training on High Definition X-ray Images: An Experimental Study

Existing X-ray based pre-trained vision models are usually conducted on a relatively small-scale dataset (less than 500k samples) with limited resolution (e.g., 224 $\times$ 224). However, the key to the success of self-supervised pre-training large models lies in massive training data, and maintaining high resolution in the field of X-ray images is the guarantee of effective solutions to difficult miscellaneous diseases. In this paper, we address these issues by proposing the first high-definition (1280 $\times$ 1280) X-ray based pre-trained foundation vision model on our newly collected large-scale dataset which contains more than 1 million X-ray images. Our model follows the masked auto-encoder framework which takes the tokens after mask processing (with a high rate) is used as input, and the masked image patches are reconstructed by the Transformer encoder-decoder network. More importantly, we introduce a novel context-aware masking strategy that utilizes the chest contour as a boundary for adaptive masking operations. We validate the effectiveness of our model on two downstream tasks, including X-ray report generation and disease recognition. Extensive experiments demonstrate that our pre-trained medical foundation vision model achieves comparable or even new state-of-the-art performance on downstream benchmark datasets. The source code and pre-trained models of this paper will be released on https://github.com/Event-AHU/Medical_Image_Analysis.

eess.IV↗

arXiv2024

State Space Model for New-Generation Network Alternative to Transformers: A Survey

In the post-deep learning era, the Transformer architecture has demonstrated its powerful performance across pre-trained big models and various downstream tasks. However, the enormous computational demands of this architecture have deterred many researchers. To further reduce the complexity of attention models, numerous efforts have been made to design more efficient methods. Among them, the State Space Model (SSM), as a possible replacement for the self-attention based Transformer model, has drawn more and more attention in recent years. In this paper, we give the first comprehensive review of these works and also provide experimental comparisons and analysis to better demonstrate the features and advantages of SSM. Specifically, we first give a detailed description of principles to help the readers quickly capture the key ideas of SSM. After that, we dive into the reviews of existing SSMs and their various applications, including natural language processing, computer vision, graph, multi-modal and multi-media, point cloud/event stream, time series data, and other domains. In addition, we give statistical comparisons and analysis of these models and hope it helps the readers to understand the effectiveness of different structures on various tasks. Then, we propose possible research points in this direction to better promote the development of the theoretical model and application of SSM. More related works will be continuously updated on the following GitHub: https://github.com/Event-AHU/Mamba_State_Space_Model_Paper_List.

cs.LG↗

arXiv2024

Cross-Covariate Gait Recognition: A Benchmark

Gait datasets are essential for gait research. However, this paper observes that present benchmarks, whether conventional constrained or emerging real-world datasets, fall short regarding covariate diversity. To bridge this gap, we undertake an arduous 20-month effort to collect a cross-covariate gait recognition (CCGR) dataset. The CCGR dataset has 970 subjects and about 1.6 million sequences; almost every subject has 33 views and 53 different covariates. Compared to existing datasets, CCGR has both population and individual-level diversity. In addition, the views and covariates are well labeled, enabling the analysis of the effects of different factors. CCGR provides multiple types of gait data, including RGB, parsing, silhouette, and pose, offering researchers a comprehensive resource for exploration. In order to delve deeper into addressing cross-covariate gait recognition, we propose parsing-based gait recognition (ParsingGait) by utilizing the newly proposed parsing data. We have conducted extensive experiments. Our main results show: 1) Cross-covariate emerges as a pivotal challenge for practical applications of gait recognition. 2) ParsingGait demonstrates remarkable potential for further advancement. 3) Alarmingly, existing SOTA methods achieve less than 43% accuracy on the CCGR, highlighting the urgency of exploring cross-covariate gait recognition. Link: https://github.com/ShinanZou/CCGR.

cs.CV↗

arXiv2024

Sewing skyrmion and antiskyrmion by quadrupole of Bloch points

We report three-dimensional topological spin configurations including a novel form of skyrmion-antiskyrmion coupling in D2d chiral magnets. The skyrmion-antiskyrmion coupled string, consisting of skyrmions located in the near-surface layers and antiskyrmions in the interior of the nanostructured sample that are sewn together by emergent Bloch points, is a hybrid three-dimensional soliton solution resulting from the application of micromagnetic equations. We further provide experimental evidence of these 3D topological skyrmionic strings in a FeNiPdP chiral magnet with S4 symmetry. Our results demonstrate reversible topological magnetic transformations between skyrmion-antiskyrmion and skyrmion-bubble strings, which are mediated by the creation and annihilation of Bloch points.

cond-mat.mtrl-sci↗

arXiv2024

Unifying Graph Contrastive Learning via Graph Message Augmentation

Graph contrastive learning is usually performed by first conducting Graph Data Augmentation (GDA) and then employing a contrastive learning pipeline to train GNNs. As we know that GDA is an important issue for graph contrastive learning. Various GDAs have been developed recently which mainly involve dropping or perturbing edges, nodes, node attributes and edge attributes. However, to our knowledge, it still lacks a universal and effective augmentor that is suitable for different types of graph data. To address this issue, in this paper, we first introduce the graph message representation of graph data. Based on it, we then propose a novel Graph Message Augmentation (GMA), a universal scheme for reformulating many existing GDAs. The proposed unified GMA not only gives a new perspective to understand many existing GDAs but also provides a universal and more effective graph data augmentation for graph self-supervised learning tasks. Moreover, GMA introduces an easy way to implement the mixup augmentor which is natural for images but usually challengeable for graphs. Based on the proposed GMA, we then propose a unified graph contrastive learning, termed Graph Message Contrastive Learning (GMCL), that employs attribution-guided universal GMA for graph contrastive learning. Experiments on many graph learning tasks demonstrate the effectiveness and benefits of the proposed GMA and GMCL approaches.

cs.LG↗

arXiv2024

CRSOT: Cross-Resolution Object Tracking using Unaligned Frame and Event Cameras

Existing datasets for RGB-DVS tracking are collected with DVS346 camera and their resolution ($346 \times 260$) is low for practical applications. Actually, only visible cameras are deployed in many practical systems, and the newly designed neuromorphic cameras may have different resolutions. The latest neuromorphic sensors can output high-definition event streams, but it is very difficult to achieve strict alignment between events and frames on both spatial and temporal views. Therefore, how to achieve accurate tracking with unaligned neuromorphic and visible sensors is a valuable but unresearched problem. In this work, we formally propose the task of object tracking using unaligned neuromorphic and visible cameras. We build the first unaligned frame-event dataset CRSOT collected with a specially built data acquisition system, which contains 1,030 high-definition RGB-Event video pairs, 304,974 video frames. In addition, we propose a novel unaligned object tracking framework that can realize robust tracking even using the loosely aligned RGB-Event data. Specifically, we extract the template and search regions of RGB and Event data and feed them into a unified ViT backbone for feature embedding. Then, we propose uncertainty perception modules to encode the RGB and Event features, respectively, then, we propose a modality uncertainty fusion module to aggregate the two modalities. These three branches are jointly optimized in the training phase. Extensive experiments demonstrate that our tracker can collaborate the dual modalities for high-performance tracking even without strictly temporal and spatial alignment. The source code, dataset, and pre-trained models will be released at https://github.com/Event-AHU/Cross_Resolution_SOT.

cs.CV↗

arXiv2023

A Multi-Stage Adaptive Feature Fusion Neural Network for Multimodal Gait Recognition

Gait recognition is a biometric technology that has received extensive attention. Most existing gait recognition algorithms are unimodal, and a few multimodal gait recognition algorithms perform multimodal fusion only once. None of these algorithms may fully exploit the complementary advantages of the multiple modalities. In this paper, by considering the temporal and spatial characteristics of gait data, we propose a multi-stage feature fusion strategy (MSFFS), which performs multimodal fusions at different stages in the feature extraction process. Also, we propose an adaptive feature fusion module (AFFM) that considers the semantic association between silhouettes and skeletons. The fusion process fuses different silhouette areas with their more related skeleton joints. Since visual appearance changes and time passage co-occur in a gait period, we propose a multiscale spatial-temporal feature extractor (MSSTFE) to learn the spatial-temporal linkage features thoroughly. Specifically, MSSTFE extracts and aggregates spatial-temporal linkages information at different spatial scales. Combining the strategy and modules mentioned above, we propose a multi-stage adaptive feature fusion (MSAFF) neural network, which shows state-of-the-art performance in many experiments on three datasets. Besides, MSAFF is equipped with feature dimensional pooling (FD Pooling), which can significantly reduce the dimension of the gait representations without hindering the accuracy. https://github.com/ShinanZou/MSAFF

cs.CV↗