Loading...
Research
Research
Research Projects
VAD
Video Anomaly Detection
Objective:Enable intelligent surveillance through scene-aware anomaly learning over distributed video environments.
Latest development：Dual-Space Video Violence Detection with Hyperbolic Vision-Language Guidance
We propose PiercingEye — a novel dual-space learning framework that integrates Euclidean and hyperbolic geometry to enhance the discriminative power of feature representations.
VIA
Video Intelligent Analysis
Objective:Advancing intelligent video analysis including detection, behavior understanding and re-identification.
Latest development：Dynamic-Static Collaboration for Unsupervised Domain Adaptive Video-Based Visible-Infrared Person Re-Identification
We proposed the first unsupervised domain adaptive visible-infrared video person re-identification task (UDA-VVI-ReID), and this method achieves significant results.
EI
Embodied Intelligence
Objective:Empowering intelligent agents to learn and interact with the physical world through embodiment.
Latest development：The team successfully developed a large-model robotic arm system called 'Wise Insight, Sharp-Eyed Quick-Hand'.
The system uses images and voice commands as input, enabling the robotic arm to accurately understand human language and perform complex tasks.
Pulications
Selected Publications
2025 2025
PiercingEye: Dual-Space Video Violence Detection with Hyperbolic Vision-Language
Guidance
[Paper]
TPAMI, 2025 (CCF A,IF=20.8 )
TPAMI, 2025 (CCF A,IF=20.8 )
A2Seek: Towards Reasoning-Centric Benchmark for Aerial Anomaly Understanding
[Paper]
NeurIPS , 2025 (CCF A,SCI一区Top)
NeurIPS , 2025 (CCF A,SCI一区Top)
Dual-space Normalizing Flow for Unsupervised Video Anomaly Detection
[Paper]
TIP , 2025 (CCF A,SCI一区Top)
TIP , 2025 (CCF A,SCI一区Top)
Video-Level Language-Driven Video-Based Visible-Infrared Person Re-Identification
[Paper]
TIFS , 2025 (CCF A,中科院一区Top)
TIFS , 2025 (CCF A,中科院一区Top)
Dual-Space Video Person Re-Identification
[Paper]
International Journal of Computer Vision, 2025 (CCF A,计算机视觉领域顶级期刊，IF:11.6)
International Journal of Computer Vision, 2025 (CCF A,计算机视觉领域顶级期刊，IF:11.6)
2024 2024
Beyond Euclidean: Dual-Space Representation Learning for Weakly Supervised Video Violence
Detection
[ Paper ]
Jiaxu Leng, Zhanjie Wu, Mingpi Tan, Yiran Liu, Ji Gan, Haosheng Chen, and Xinbo Gao*
Advances in Neural Information Processing Systems (NeurIPS), 2024. (CCF A, 机器学习领域顶级会议)
Jiaxu Leng, Zhanjie Wu, Mingpi Tan, Yiran Liu, Ji Gan, Haosheng Chen, and Xinbo Gao*
Advances in Neural Information Processing Systems (NeurIPS), 2024. (CCF A, 机器学习领域顶级会议)
Difficulty-Guided Variant Degradation Learning for Blind Image Super-Resolution
[ Paper ]
Jiaxu Leng, Jia Wang, Mengjingcheng Mo, Ji Gan, Wen Lu, and Xinbo Gao*
IEEE Transactions on Neural Networks and Learning Systems, 2024. (SCI一区TOP, IF:10.4)
Jiaxu Leng, Jia Wang, Mengjingcheng Mo, Ji Gan, Wen Lu, and Xinbo Gao*
IEEE Transactions on Neural Networks and Learning Systems, 2024. (SCI一区TOP, IF:10.4)
Recent Advances for Aerial Object Detection: A Survey
[ Paper ]
Jiaxu Leng, Yongming Ye, Mengjingcheng Mo, Chenqiang Gao, Ji Gan, Bin Xiao, and Xinbo Gao*
ACM Computing Surveys, 2024. (SCI一区TOP, 理论计算机科学NO.1综述期刊 ，IF:23.8)
Jiaxu Leng, Yongming Ye, Mengjingcheng Mo, Chenqiang Gao, Ji Gan, Bin Xiao, and Xinbo Gao*
ACM Computing Surveys, 2024. (SCI一区TOP, 理论计算机科学NO.1综述期刊 ，IF:23.8)
Modality-Free Violence Detection via Cross-Modal Causal Attention and Feature
Distillation
[ Paper ]
Jiaxu Leng, Zhanjie Wu, Mengjingcheng Mo, Mingpi Tan, Shuang Li, Xinbo Gao*
IEEE International Conference on Multimedia and Expo (ICME), 2024 (CCF B, 多媒体领域顶级国际会议)
Jiaxu Leng, Zhanjie Wu, Mengjingcheng Mo, Mingpi Tan, Shuang Li, Xinbo Gao*
IEEE International Conference on Multimedia and Expo (ICME), 2024 (CCF B, 多媒体领域顶级国际会议)
RC-DETR: Improving DETRs in Crowded Pedestrian Detection via Rank-Based Contrastive
Learning
[ Paper ]
Jiaxu Leng, Yongming Ye, Mengjingcheng Mo, Chenqiang Gao, Ji Gan, Bin Xiao, and Xinbo Gao*
Neural Networks, 2024. (CCF B, 人工智能领域重要期刊)
Jiaxu Leng, Yongming Ye, Mengjingcheng Mo, Chenqiang Gao, Ji Gan, Bin Xiao, and Xinbo Gao*
Neural Networks, 2024. (CCF B, 人工智能领域重要期刊)
2023 2023
CRNet: Context-guided Reasoning Network for Detecting Hard Objects
[ Paper ]
Jiaxu Leng, Yiran Liu, Xinbo Gao* and Zhihui Wang
IEEE Transactions on Multimedia, 2023. (SCI一区TOP，多媒体领域顶刊)
Jiaxu Leng, Yiran Liu, Xinbo Gao* and Zhihui Wang
IEEE Transactions on Multimedia, 2023. (SCI一区TOP，多媒体领域顶刊)
Selecting Learnable Training Samples is All DETRs Need in Crowded Pedestrian
Detection
[
Paper ]
Feng Gao, Jiaxu Leng*, Ji Gan and Xinbo Gao*
ACM Multimedia (ACM MM) 2023. (CCF A，多媒体领域顶会)
Feng Gao, Jiaxu Leng*, Ji Gan and Xinbo Gao*
ACM Multimedia (ACM MM) 2023. (CCF A，多媒体领域顶会)
Characters as Graphs: Interpretable Handwritten Chinese Character Recognition via Pyramid
Graph Transformer
[ Paper ]
Ji Gan, Yuyan Chen, Bo Hu, Jiaxu Leng*, Weiqiang Wang and Xinbo Gao*
Pattern Recognition, 2023. (SCI一区TOP，人工智能领域顶刊)
Ji Gan, Yuyan Chen, Bo Hu, Jiaxu Leng*, Weiqiang Wang and Xinbo Gao*
Pattern Recognition, 2023. (SCI一区TOP，人工智能领域顶刊)
Selecting Learnable Training Samples is All DETRs Need in Crowded Pedestrian
Detection
[ Paper ]
Feng Gao, Jiaxu Leng, Ji Gan, Xinbo Gao*
ACM Multimedia (ACM MM), 2023. (CCF A，多媒体领域顶会)
Feng Gao, Jiaxu Leng, Ji Gan, Xinbo Gao*
ACM Multimedia (ACM MM), 2023. (CCF A，多媒体领域顶会)
Contextual Learning in Fourier Complex Field for VHR Remote Sensing Images
[ Paper ]
Yan Zhang, Xiyuan Gao, Qingyan Duan, Jiaxu Leng, Xiao Pu, Xinbo Gao*
IEEE Transactions on Neural Networks and Learning Systems (IEEE TNNLS), 2024. (CCF A, 人工智能领域顶级期刊)
Yan Zhang, Xiyuan Gao, Qingyan Duan, Jiaxu Leng, Xiao Pu, Xinbo Gao*
IEEE Transactions on Neural Networks and Learning Systems (IEEE TNNLS), 2024. (CCF A, 人工智能领域顶级期刊)
Before 2022 before
Anomaly Warning: Learning and Memorizing Future Semantic Patterns for Unsupervised
Ex-ante Potential Anomaly Prediction
[ Paper ]
Jiaxu Leng, Mingpi Tan, Xinbo Gao*, Wen Lu and Zongyi Xu
ACM Multimedia (ACM MM), 2022. (CCF A，多媒体领域顶会)
Jiaxu Leng, Mingpi Tan, Xinbo Gao*, Wen Lu and Zongyi Xu
ACM Multimedia (ACM MM), 2022. (CCF A，多媒体领域顶会)
ICNet: Joint Alignment and Reconstruction via Iterative Collaboration for Video
Super-Resolution
[ Paper ]
Jiaxu Leng, Jia Wang, Xinbo Gao*, Bo Hu, Ji Gan and Chengqiang Gao
ACM Multimedia (ACM MM), 2022. (CCF A，多媒体领域顶会)
Jiaxu Leng, Jia Wang, Xinbo Gao*, Bo Hu, Ji Gan and Chengqiang Gao
ACM Multimedia (ACM MM), 2022. (CCF A，多媒体领域顶会)
Pareto Refocusing for Drone-view Object Detection
[ Paper ]
Jiaxu Leng, Mengjingcheng Mo, Yinghua Zhou, Chenqiang Gao, Weisheng Li and Xinbo Gao*
IEEE Transactions on Circuits and Systems for Video Technology, 2022. (SCI一区TOP，视频技术领域顶刊)
Jiaxu Leng, Mengjingcheng Mo, Yinghua Zhou, Chenqiang Gao, Weisheng Li and Xinbo Gao*
IEEE Transactions on Circuits and Systems for Video Technology, 2022. (SCI一区TOP，视频技术领域顶刊)
Correlation Filter Tracker with Sample-Reliability Awareness and Self-Guided Update
[ Paper ]
Lifang Zhou, Jiaqi Li, Bangjun Lei, Weisheng Li and Jiaxu Leng*
IEEE Transactions on Circuits and Systems for Video Technology, 2022. (SCI一区TOP，视频技术领域顶刊)
Lifang Zhou, Jiaqi Li, Bangjun Lei, Weisheng Li and Jiaxu Leng*
IEEE Transactions on Circuits and Systems for Video Technology, 2022. (SCI一区TOP，视频技术领域顶刊)
HiGAN+: Handwriting Imitation GAN with Disentangled Representations
[ Paper ]
Ji Gan, Weiqiang Wang*, Jiaxu Leng, Xinbo Gao*
ACM Transactions on Graphics, 2022. (SCI一区TOP，计算机图形学领域顶刊)
Ji Gan, Weiqiang Wang*, Jiaxu Leng, Xinbo Gao*
ACM Transactions on Graphics, 2022. (SCI一区TOP，计算机图形学领域顶刊)
CrossNet: Detecting Objects as Crosses
[ Paper ]
Jiaxu Leng*, Yin Liu, Zhihui Wang, Haibo Hu and Xinbo Gao
IEEE Transactions on Multimedia, 2021. (SCI一区TOP，多媒体领域顶刊)
Jiaxu Leng*, Yin Liu, Zhihui Wang, Haibo Hu and Xinbo Gao
IEEE Transactions on Multimedia, 2021. (SCI一区TOP，多媒体领域顶刊)
Selective Domain-invariant Feature Alignment Network for Face Anti-spoofing
[ Paper ]
Lifang Zhou, Jun Luo, Xinbo Gao, Weisheng Li, Bangjun Lei, and Jiaxu Leng*
IEEE Transactions on Information Forensics & Security, 2021. (SCI一区TOP，信息安全领域顶刊)
Lifang Zhou, Jun Luo, Xinbo Gao, Weisheng Li, Bangjun Lei, and Jiaxu Leng*
IEEE Transactions on Information Forensics & Security, 2021. (SCI一区TOP，信息安全领域顶刊)
MTCNet: Multi-Task Collaboration Network for Rotation-Invariance Face Detection
[ Paper ]
Lifang Zhoua, Hui Zhao, Jiaxu Leng*
Pattern Recognition, 2021. (SCI一区TOP，人工智能领域顶刊)
Lifang Zhoua, Hui Zhao, Jiaxu Leng*
Pattern Recognition, 2021. (SCI一区TOP，人工智能领域顶刊)