149 citations · 158 across the 5 of their papers we have counts for
5 papers
MambaTrack: A Simple Baseline for Multiple Object Tracking with State Space Model
Changcheng Xiao, Qiong Cao, Zhigang Luo +1
Tracking by detection has been the prevailing paradigm in the field of Multi-object Tracking (MOT). These methods typically rely on the Kalman Filter to estimate the future locatio…
MotionTrack: Learning Motion Predictor for Multiple Object Tracking
Changcheng Xiao, Qiong Cao, Yujie Zhong +4
Significant progress has been achieved in multi-object tracking (MOT) through the evolution of detection and re-identification (ReID) techniques. Despite these advancements, accura…
Improving Unsupervised Domain Adaptation by Reducing Bi-level Feature Redundancy
Mengzhu Wang, Xiang Zhang, Long Lan +3
Reducing feature redundancy has shown beneficial effects for improving the accuracy of deep learning models, thus it is also indispensable for the models of unsupervised domain ada…
Enhancing the Association in Multi-Object Tracking via Neighbor Graph
Tianyi Liang, Long Lan, Zhigang Luo
Most modern multi-object tracking (MOT) systems follow the tracking-by-detection paradigm. It first localizes the objects of interest, then extracting their individual appearance f…
MahNMF: Manhattan Non-negative Matrix Factorization
Naiyang Guan, Dacheng Tao, Zhigang Luo +1
Non-negative matrix factorization (NMF) approximates a non-negative matrix by a product of two non-negative low-rank factor matrices and . NMF and its extensions minimiz…