📝 Publications

PVMamba: Parallelizing Vision Mamba via Dynamic State Aggregation
Fei Xie, Zhongdao Wang, Weijia Zhang, Chao Ma

• Adapting Mamba into 2D visual data.
• CODE.
• PDF

VRM: Knowledge Distillation via Virtual Relation Matching
Weijia Zhang, Fei Xie, Weidong Cai, Chao Ma

• Improved knowledge distillation method.
• Coming soon.
• PDF

Mamba-Adaptor: State Space Model Adaptor for Visual Recognition
Fei Xie, Jiahao Nie, Yujin Tang, Wenkang Zhang, Hongshen Zhao

• Specialized Adaptor module design for Vision Mamba.
• CODE
• PDF

P2P: Part-to-Part Motion Cues Guide a Strong Tracking Framework for LiDAR Point Clouds
Jiahao Nie, Fei Xie, Sifan Zhou, Xueyi Zhou, Dong-Kyu Chae, Zhiwei He

• A simple motion-based single object tracker in point clouds.
• CODE
• PDF

QuadMamba: Learning Quadtree-based Selective Scan for Visual State Space Model
Fei Xie, Weijia Zhang, Zhongdao Wang, Chao Ma.

• QuadMamba is a visual Mamba-based backbone network for classification, detection, and segmentation.
• CODE
• PDF

Correlation-Embedded Transformer Tracking: A Single-Branch Framework
Fei Xie, Wankou Yang, Chunyu Wang, Lei Chu, Yue Cao, Chao Ma, Wenjun Zeng.

• SuperSBT improves our Single-Branch Tracking framework with a more specialized design.
• CODE
• PDF

DiffusionTrack: Point Set Diffusion Model for Visual Object Tracking
Fei Xie, Zhongdao Wang, Chao Ma.

• DiffusionTrack is the first diffusion-based generative framework for visual object tracking.
• CODE
• PDF

Towards Category Unification of 3D Single Object Tracking on Point Clouds
Jiahao Nie, Zhiwei He, Xudong Lv, Xueyi Zhou, Dong-Kyu Chae, Fei Xie

• First attempt to track multiple categories in point clouds.
• CODE
• PDF

VideoTrack: Learning to Track Objects via Video Transformer
Fei Xie, Lei Chu, Jiahao Li, Yan Lu and Chao Ma.

• VideoTrack is the first video backbone network for visual tracking.
• CODE
• PDF

Correlation-Aware Deep Tracking
Fei Xie, Chunyu Wang, Guangting Wang, Yue Cao, Wankou Yang, Wenjun Zeng.

• SBT is the first single-branch/one-stream transformer tracker that simplifies the Siamese tracking framework by using joint feature extraction and correlation.
• CODE
• PDF

Learning Tracking Representations via Dual-Branch Fully Transformer Networks
Fei Xie, Chunyu Wang, Guangting Wang, Yue Cao, Wankou Yang, Wenjun Zeng.

• DualTFR is the first fully transformer-based tracking model that inspires researchers to adopt transformer-based feature extraction for tracking.
• CODE
• PDF

Learning Spatio-Appearance Memory Network for High-Performance Visual Tracking
Fei Xie, Wankou Yang, Kaihua Zhang, Bo Liu, Guangting Wang, Wangmeng Zuo

• SAMN can simultaneously track objects and conduct segmentation.
• CODE
• PDF