Weijing Wu — accepted AI-conference papers

2026

An Efficient Token Compression Framework for Visual Object Tracking

Weijing Wu, Qihua Liang, Bineng Zhong, Haiying Xia, Zhiyi Mo, Shuxiang Song

CVPR 2026

Refining visual representations by eliminating their internal feature-level redundancy is crucial for simultaneously optimizing the performance and computational cost of models in visual tracking. To enhance their performance, many contemporary Transformer-based trackers leverage a larger number of

Cited by 0 Source ↗code ↗Scholar ↗

2026

MUTrack: A Memory-Aware Unified Representation Framework for Visual Tracking

Weijing Wu, Qihua Liang, Bineng Zhong, Xiaohu Tang, Yufei Tan, Ning Li +1

AAAI 2026technical

Building a unified target representation that simultaneously achieves short-term adaptability and long-term stability is crucial for robust visual tracking. However, existing trackers typically face an inherent trade-off. Methods primarily relying on short-term appearance and motion cues achieve ra

Cited by 0 Source ↗PDF ↗Scholar ↗