Tianyang Xu 徐天阳
 |
Tianyang Xu |
I am currently an Associate Professor with the School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China. I received my Ph.D. degree from Jiangnan University in 2019 under the supervision of Prof. Xiao-Jun Wu and Prof. Josef Kittler, and Bachelor degree from Nanjing University in 2011. I was a research fellow at the Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, United Kingdom, from 2019 to 2021. My research interests include computer vision and pattern recognition, e.g., visual tracking, video classification, multimodal analysis, and manifold learning.
Publications
FusionBooster: A Unified Image Fusion Boosting Paradigm. IJCV, 2024. [paper] [Code]
Adaptive Log-Euclidean Metrics for SPD Matrix Learning. IEEE TIP, 2024. [paper]
APMG: 3D Molecule Generation Driven by Atomic Chemical Properties. IEEE/ACM TCBB, 2024. [paper]
M-Adapter: Multi-Level Image-to-Video Adaptation for Video Action Recognition. CVIU, 2024. [paper]
MMDRFuse: Distilled Mini-Model with Dynamic Refresh for Multi-Modality Image Fusion. ACM MM, 2024. (oral) [paper] [Code]
Learning Feature Restoration Transformer for Robust Dehazing Visual Object Tracking. IJCV, 2024. [paper]
View-shuffled clustering via the modified Hungarian algorithm. Neural Networks, 2024. [paper]
HabLSTM: A Non-stationary Feature Focusing LSTM for Spatiotemporal Prediction of Harmful Algal Bloom. IEEE TGRS, 2024. [paper]
Multi-Level Fusion for Robust RGBT Tracking via Enhanced Thermal Representation. ACM TOMM, 2024. [paper]
Efficient Few-Shot Action Recognition via Multi-Level Post-Reasoning. ECCV, 2024. [paper] [Code]
C2C: Component-to-Composition Learning for Zero-Shot Compositional Action Recognitionn. ECCV, 2024. (oral) [paper] [Code]
YOLO-WIT: 红外遥感弱小船舶目标检测算法. 北京航空航天大学学报, 2024. [paper]
CRTrack: Learning Correlation-Refine network for visual object tracking. Pattern Recognition, 2024. [paper]
Selective Depth Attention Networks for Adaptive Multi-scale Feature Representation. IEEE TAI, 2024. [paper]
Self-supervised learning for RGB-D object tracking. Pattern Recognition, 2024. [paper]
Perceiving Actions via Temporal Video Frame Pairs. ACM TIST, 2024. [paper]
Feature enhancement and coarse-to-fine detection for RGB-D tracking. PRL, 2024. [paper]
Learning Adaptive Spatio-Temporal Inference Transformer for Coarse-to-Fine Animal Visual Tracking: Algorithm and Benchmark. IJCV, 2024. [paper] [Code]
Unified Referring Expression Generation for Bounding Boxes and Segmentations. IEEE SPL, 2024. [paper]
Memory Prompt for Spatio-Temporal Transformer Visual Object Tracking. IEEE TAI, 2024. [paper]
UniMod1K: Towards a More Universal Large-Scale Dataset and Benchmark for Multi-Modal Learning. IJCV, 2024. [paper]
Generative-based Fusion Mechanism for Multi-Modal Tracking. AAAI, 2024. [paper]
SCD-Net: Spatiotemporal Clues Disentanglement Network for Self-supervised Skeleton-based Action Recognition. AAAI, 2024. [paper]
Pluggable Attack for Visual Object Tracking. IEEE TIFS, 2023. [paper]
Scene adaptive mechanism for action recognition. CVIU, 2023. [paper]
A Spatio-Temporal Robust Tracker with Spatial-Channel Transformer and Jitter Suppression. IJCV, 2023. [paper]
GuideFuse: A novel guided auto-encoder fusion network for infrared and visible images. IEEE TIM, 2023. [paper]
Exploring Fusion Strategies for Accurate RGBT Visual Object Tracking. Information Fusion, 2023. [paper]
TGFuse: An Infrared and Visible Image Fusion Approach Based on Transformer and Generative Adversarial Network. IEEE TIP, 2023. [paper]
LRRNet: A novel Representation Learning Guided Fusion Network for Infrared and Visible Images. IEEE TPAMI, 2023. [paper] [Code]
Fast Self-guided Multi-view Subspace Clustering. IEEE TIP, 2023. [paper]
RGBD1K: A Large-scale Dataset and Benchmark for RGB-D Object Tracking. AAAI, 2023. (oral) [paper] [Code] [Slide]
Riemannian Local Mechanism for SPD Neural Networks. AAAI, 2023. [paper] [Slide]
Towards Robust Visual Object Tracking with Independent Target-Agnostic Detection and Effective Siamese Cross-Task Interaction. IEEE TIP, 2023. [paper]
MUFusion: A general unsupervised image fusion network based on memory unit. Information Fusion, 2023. [paper] [Code]
Enhanced robust spatial feature selection and correlation filter learning for UAV tracking. Neural Networks, 2023. [Code]
多尺度分解和八度卷积相结合的红外与可见光图像融合. 中国图象图形学报, 2023. [paper]
Motion Complement and Temporal Multifocusing for Skeleton-based Action Recognition. IEEE TCSVT, 2023. [paper] [Code]
Discriminative Dictionary Pair Learning With Scale-Constrained Structured Representation for Image Classification. IEEE TNNLS, 2022. [paper]
U-SPDNet: An SPD manifold learning-based neural network for visual classification. Neural Networks, 2022. [paper] [Code]
I Know How You Move: Explicit Motion Estimation for Human Action Recognition. IEEE TMM, 2022. [paper]
Memory-Token Transformer for Unsupervised Video Anomaly Detection. ICPR, 2022. [paper]
Deep Metric Learning on the SPD Manifold for Image Set Classification. IEEE TCSVT, 2022. [paper] [Code]
Learning a discriminative SPD manifold neural network for image set classification. Neural Networks, 2022. [paper] [Code]
用于骨架行为识别的多维特征嵌合注意力机制. 中国图象图形学报, 2022. [paper]
Distillation, Ensemble and Selection for building a Better and Faster Siamese based Tracker. IEEE TCSVT, 2022. [paper]
WATCH: Two-stage Discrete Cross-media Hashing. IEEE TKDE, 2022. [paper]
Two-Stage Supervised Discrete Hashing for Cross-Modal Retrieval. IEEE TSMC, 2022. [paper]
DreamNet: A Deep Riemannian Manifold Network for SPD Matrix Learning. ACCV, 2022. [paper] [Code]
KITPose: Keypoint-Interactive Transformer for Animal Pose Estimation. PRCV, 2022. (oral, best student paper award) [paper]
Adaptive channel selection for robust visual object tracking with discriminative correlation filters. IJCV, 2021. [paper] [Code]
Locality-constrained collaborative representation with multi-resolution dictionary for face recognition. PRCV, 2021. [paper]
Unifusion: A lightweight unified image fusion network. IEEE TIM, 2021. [paper] [Code]
Hybrid riemannian graph-embedding metric learning for image set classification. IEEE TBD, 2021. [paper]
FEXNet: Foreground Extraction Network for Human Action Recognition. IEEE TCSVT, 2021. [paper]
MSC-Fuse: An Unsupervised Multi-scale Convolutional Fusion Framework for Infrared and Visible Image. ICIG, 2021. [paper]
From RGB to depth: domain transfer network for face anti-spoofing. IEEE TIFS, 2021. [paper]
Dah: Discrete asymmetric hashing for efficient cross-media retrieval. IEEE TKDE, 2022. [paper] [Code]
Adaptive feature fusion for visual object tracking. Pattern Recognition, 2021. [paper]
Robust visual object tracking via adaptive attribute-aware discriminative correlation filters. IEEE TMM, 2021. [paper]
An accelerated correlation filter tracker. Pattern Recognition, 2020. [paper]
Complementary discriminative correlation filters based on collaborative representation for visual object tracking. IEEE TCSVT, 2020. [paper]
Learning low-rank and sparse discriminative correlation filters for coarse-to-fine visual object tracking. IEEE TCSVT, 2020. [paper] [Code]
Learning Adaptive Discriminative Correlation Filters via Temporal Consistency preserving Spatial Feature Selection for Robust Visual Object Tracking. IEEE TIP, 2019. [paper] [Code]
Joint group feature selection and discriminative filter learning for robust visual object tracking. ICCV, 2019. [paper] [Code] [Slide]
Non-negative subspace representation learning scheme for correlation filter based tracking. ICPR, 2018. [paper]
Awards
2nd-Place Award, Perception Test Challenge - Temporal Sound Localisation (ECCV2024)
1st-Place Award, MMVRAC 2024 - Animal Pose Estimation (ICME2024)
2nd-Place Award, MMVRAC 2024 - Person Reidentification (ICME2024)
2nd-Place Award, MMVRAC 2024 - Skeleton-based Action Recognition (ICME2024)
2nd-Place Award, Perception Test Challenge - Point Tracking (ICCV2023)
Most Novel Submissions, Perception Test Challenge (ICCV2023)
2nd-Place Award, AI City Challenge 2023 - Naturalistic Driving Action Recognition (CVPR2023)
PRCV 2022 Best Student Paper Award
2nd-Place Award, VOT-LT2022 Challenge (ECCV2022)
2nd-Place Award, VOT-D2022 Challenge (ECCV2022)
ICCPR 2022 Best Presentation Award
3rd-Place Award, Make-up Dense Video Captioning Challenge (ACM MM2022)
2021年度中国图象图形学学会优秀博士学位论文奖
1st-Place Award, Multi-Modal Video Reasoning and Analyzing Competition 2021- Skeleton-based Action Recognition (ICCV2021)
1st-Place Award, Multi-Modal Video Reasoning and Analyzing Competition 2021- Fisheye Video-based Action Recognition (ICCV2021)
IEEE CCIS 2021 Best Paper Award
2nd-Place Award, VOT-RGBD2021 Challenge (ICCV2021)
3rd-Place Award, Anti-UAV2021 Challenge (CVPR2021)
1st-Place Award, VOT-RGBT2020 Challenge (ECCV2020)
1st-Place Award, Anti-UAV2020 Challenge (CVPR2020)