Xiao-Jun Wu

An Improved Graph Pooling Network for Skeleton-Based Action Recognition

Cong Wu, Tianyang Xu, Josef Kittler, 2024, 2404.16359.

Revisiting RGBT Tracking Benchmarks from the Perspective of Modality Validity: A New Benchmark, Problem, and Method

Zhenhua Feng, Xuefeng Zhu, Zhangyong Tang, 2024, 2405.00168.

Self-supervised learning for RGB-D object tracking

Zhenhua Feng, Xuefeng Zhu, Sara Atito, 2024, Pattern Recognition.

TENet: Targetness Entanglement Incorporating with Multi-Scale Pooling and Mutually-Guided Fusion for RGB-E Object Tracking

Zhangyong Tang, Tianyang Xu, Josef Kittler, 2024, ArXiv.

UniMod1K: Towards a More Universal Large-Scale Dataset and Benchmark for Multi-modal Learning

Xuefeng Zhu, Zhangyong Tang, Tianyang Xu, 2024, International Journal of Computer Vision.

Perceiving Actions via Temporal Video Frame Pairs

Zhongwei Shen, Tianyang Xu, Josef Kittler, 2024, ACM Transactions on Intelligent Systems and Technology.

C2C: Component-to-Composition Learning for Zero-Shot Compositional Action Recognition

Zhenhua Feng, Sara Atito, Tianyang Xu, 2024, 2407.06113.