1.2k citations · 1.4k across the 17 of their papers we have counts for
17 papers
How Far are Modern Trackers from UAV-Anti-UAV? A Million-Scale Benchmark and New Baseline
Chunhui Zhang, Li Liu, Zhipeng Zhang +5
Unmanned Aerial Vehicles (UAVs) offer wide-ranging applications but also pose significant safety and privacy violation risks in areas like airport and infrastructure inspection, sp…
COST: Contrastive One-Stage Transformer for Vision-Language Small Object Tracking
Chunhui Zhang, Li Liu, Jialin Gao +5
Transformer has recently demonstrated great potential in improving vision-language (VL) tracking algorithms. However, most of the existing VL trackers rely on carefully designed me…
MambaTrack: Exploiting Dual-Enhancement for Night UAV Tracking
Chunhui Zhang, Li Liu, Hao Wen +2
Night unmanned aerial vehicle (UAV) tracking is impeded by the challenges of poor illumination, with previous daylight-optimized methods demonstrating suboptimal performance in low…
Underwater Camouflaged Object Tracking Meets Vision-Language SAM2
Chunhui Zhang, Li Liu, Guanjie Huang +5
Over the past decade, significant progress has been made in visual object tracking, largely due to the availability of large-scale datasets. However, these datasets have primarily…
Awesome Multi-modal Object Tracking
Chunhui Zhang, Li Liu, Hao Wen +2
Multi-modal object tracking (MMOT) is an emerging field that combines data from various modalities, \eg vision (RGB), depth, thermal infrared, event, language and audio, to estimat…
WebUOT-1M: Advancing Deep Underwater Object Tracking with A Million-Scale Benchmark
Chunhui Zhang, Li Liu, Guanjie Huang +3
Underwater object tracking (UOT) is a foundational task for identifying and tracing submerged entities in underwater video sequences. However, current UOT datasets suffer from limi…
On Mixing Times of Metropolized Algorithm With Optimization Step (MAO) : A New Framework
EL Mahdi Khribch, George Deligiannidis, Daniel Paulin
In this paper, we consider sampling from a class of distributions with thin tails supported on and make two primary contributions. First, we propose a new Metropoliz…
Receptive Multi-granularity Representation for Person Re-Identification
Guanshuo Wang, Yufeng Yuan, Jiwei Li +2
A key for person re-identification is achieving consistent local details for discriminative representation across variable environments. Current stripe-based feature learning appro…
Layer Pruning for Accelerating Very Deep Neural Networks
Weiwei Zhang, Changsheng chen, Xuechun Wu +4
In this paper, we propose an adaptive pruning method. This method can cut off the channel and layer adaptively. The proportion of the layer and the channel to be cut is learned ada…
Relation-Aware Pyramid Network (RapNet) for temporal action proposal
Jialin Gao, Zhixiang Shi, Jiani Li +3
In this technical report, we describe our solution to temporal action proposal (task 1) in ActivityNet Challenge 2019. First, we fine-tune a ResNet-50-C3D CNN on ActivityNet v1.3 b…
Pixel-Anchor: A Fast Oriented Scene Text Detector with Combined Networks
Yuan Li, Yuanjie Yu, Zefeng Li +4
Recently, semantic segmentation and general object detection frameworks have been widely adopted by scene text detecting tasks. However, both of them alone have obvious shortcoming…
Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-identification
Yang Fu, Yunchao Wei, Guanshuo Wang +3
Domain adaptation in person re-identification (re-ID) has always been a challenging task. In this work, we explore how to harness the natural similar characteristics existing in th…
An improved hybrid CTC-Attention model for speech recognition
Zhe Yuan, Zhuoran Lyu, Jiwei Li +1
Recently, end-to-end speech recognition with a hybrid model consisting of the connectionist temporal classification(CTC) and the attention encoder-decoder achieved state-of-the-art…
A novel pyramidal-FSMN architecture with lattice-free MMI for speech recognition
Xuerui Yang, Jiwei Li, Xi Zhou
Deep Feedforward Sequential Memory Network (DFSMN) has shown superior performance on speech recognition tasks. Based on this work, we propose a novel network architecture which int…
Cascaded CNN-resBiLSTM-CTC: An End-to-End Acoustic Model For Speech Recognition
Xinpei Zhou, Jiwei Li, Xi Zhou
Automatic speech recognition (ASR) tasks are resolved by end-to-end deep learning models, which benefits us by less preparation of raw data, and easier transformation between langu…
Learning Discriminative Features with Multiple Granularities for Person Re-Identification
Guanshuo Wang, Yufeng Yuan, Xiong Chen +2
The combination of global and partial features has been an essential solution to improve discriminative performances in person re-identification (Re-ID) tasks. Previous part-based…
Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network
Yao Feng, Fan Wu, Xiaohu Shao +2
We propose a straightforward method that simultaneously reconstructs the 3D facial structure and provides dense alignment. To achieve this, we design a 2D representation called UV…