1 citations · 2 across the 18 of their papers we have counts for
18 papers
Spatio-Temporal Conditional Denoising Transformer for Modality-Missing RGBT Tracking
Andong Lu, Ziyi Zha, Jiandong Jin +4
Missing modalities in RGBT tracking often lead to incomplete and unstable multimodal feature representations that greatly degrade the performance. Existing methods typically attemp…
Graph-based Semantic Calibration Network for Unaligned UAV RGBT Image Semantic Segmentation and A Large-scale Benchmark
Fangqiang Fan, Zhicheng Zhao, Xiaoliang Ma +2
Fine-grained RGBT image semantic segmentation is crucial for all-weather unmanned aerial vehicle (UAV) scene understanding. However, UAV RGBT image semantic segmentation faces two…
Compositional-Degradation UAV Image Restoration: Conditional Decoupled MoE Network and A Benchmark
Jinquan Yan, Zhicheng Zhao, Zhengzheng Tu +3
UAV images are critical for applications such as large-area mapping, infrastructure inspection, and emergency response. However, in real-world flight environments, a single image i…
Cross-modal Fuzzy Alignment Network for Text-Aerial Person Retrieval and A Large-scale Benchmark
Yifei Deng, Chenglong Li, Yuyang Zhang +2
Text-aerial person retrieval aims to identify targets in UAV-captured images from eyewitness descriptions, supporting intelligent transportation and public security applications. C…
Vehicle-centric Perception via Multimodal Structured Pre-training
Wentao Wu, Xiao Wang, Chenglong Li +2
Vehicle-centric perception plays a crucial role in many intelligent systems, including large-scale surveillance systems, intelligent transportation, and autonomous driving. Existin…
Pedestrian Attribute Recognition via Hierarchical Cross-Modality HyperGraph Learning
Xiao Wang, Shujuan Wu, Xiaoxia Cheng +3
Current Pedestrian Attribute Recognition (PAR) algorithms typically focus on mapping visual features to semantic labels or attempt to enhance learning by fusing visual and attribut…
Adversarial Semantic and Label Perturbation Attack for Pedestrian Attribute Recognition
Weizhe Kong, Xiao Wang, Ruichong Gao +5
Pedestrian Attribute Recognition (PAR) is an indispensable task in human-centered research and has made great progress in recent years with the development of deep neural networks.…
CM3AE: A Unified RGB Frame and Event-Voxel/-Frame Pre-training Framework
Wentao Wu, Xiao Wang, Chenglong Li +4
Event cameras have attracted increasing attention in recent years due to their advantages in high dynamic range, high temporal resolution, low power consumption, and low latency. S…
Breaking Shallow Limits: Task-Driven Pixel Fusion for Gap-free RGBT Tracking
Andong Lu, Yuanzhi Guo, Wanyu Wang +3
Current RGBT tracking methods often overlook the impact of fusion location on mitigating modality gap, which is key factor to effective tracking. Our analysis reveals that shallowe…
Towards General Multimodal Visual Tracking
Andong Lu, Mai Wen, Jinhu Wang +4
Existing multimodal tracking studies focus on bi-modal scenarios such as RGB-Thermal, RGB-Event, and RGB-Language. Although promising tracking performance is achieved through lever…
Dynamic Disentangled Fusion Network for RGBT Tracking
Chenglong Li, Tao Wang, Zhaodong Ding +2
RGBT tracking usually suffers from various challenging factors of low resolution, similar appearance, extreme illumination, thermal crossover and occlusion, to name a few. Existing…
VFM-Det: Towards High-Performance Vehicle Detection via Large Foundation Models
Wentao Wu, Fanghua Hong, Xiao Wang +2
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)…
RGBT Tracking via All-layer Multimodal Interactions with Progressive Fusion Mamba
Andong Lu, Wanyu Wang, Chenglong Li +2
Existing RGBT tracking methods often design various interaction models to perform cross-modal fusion of each layer, but can not execute the feature interactions among all layers, w…
AFter: Attention-based Fusion Router for RGBT Tracking
Andong Lu, Wanyu Wang, Chenglong Li +2
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…
Structural Information Guided Multimodal Pre-training for Vehicle-centric Perception
Xiao Wang, Wentao Wu, Chenglong Li +4
Understanding vehicles in images is important for various applications such as intelligent transportation and self-driving system. Existing vehicle-centric works typically pre-trai…
Nighttime Person Re-Identification via Collaborative Enhancement Network with Multi-domain Learning
Andong Lu, Chenglong Li, Tianrui Zha +3
Prevalent nighttime person re-identification (ReID) methods typically combine image relighting and ReID networks in a sequential manner. However, their performance (recognition acc…
Modality-missing RGBT Tracking: Invertible Prompt Learning and High-quality Benchmarks
Andong Lu, Jiacong Zhao, Chenglong Li +2
Current RGBT tracking research relies on the complete multi-modal input, but modal information might miss due to some factors such as thermal sensor self-calibration and data trans…
Pedestrian Attribute Recognition via CLIP based Prompt Vision-Language Fusion
Xiao Wang, Jiandong Jin, Chenglong Li +3
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-optima…