3 Hits in 1.9 sec

Lifted Disjoint Paths with Application in Multiple Object Tracking [article]

Andrea Hornakova, Roberto Henschel, Bodo Rosenhahn, Paul Swoboda
2020 arXiv   pre-print
Additionally, we propose efficient cutting plane algorithms for separating the proposed linear inequalities.  ...  The lifted disjoint path problem is a natural model for multiple object tracking and allows an elegant mathematical formulation for long range temporal interactions.  ...  -T., and Yu, G. mussp: Efficient min-cost flow algorithm for multi-object track- ing. In Advances in Neural Information Processing Sys- tems, pp. 423-432, 2019a.  ... 
arXiv:2006.14550v1 fatcat:6dhykcsqjrbttia4ga52t6u5cu

Joint Object Detection and Multi-Object Tracking with Graph Neural Networks [article]

Yongxin Wang and Kris Kitani and Xinshuo Weng
2021 arXiv   pre-print
Object detection and data association are critical components in multi-object tracking (MOT) systems.  ...  The key idea is that GNNs can model relations between variable-sized objects in both the spatial and temporal domains, which is essential for learning discriminative features for detection and data association  ...  Yu, “muSSP: Efficient [46] A. Milan, S. Roth, and K. Schindler, “Continuous Energy Minimiza- Min-cost Flow Algorithm for Multi-object Tracking,” NeurIPS, 2019.  ... 
arXiv:2006.13164v3 fatcat:aqxjugcrsbfarlvu53tpfjcbve

CAST: Character labeling in Animation using Self-supervision by Tracking [article]

Oron Nir, Gal Rapoport, Ariel Shamir
2022 arXiv   pre-print
Next, we use self-supervision to refine the representation for any specific animation style by gathering many examples of animated characters in this style, using a multi-object tracking.  ...  In this paper we present a method to refine a semantic representation suitable for specific animated content.  ...  IEEE, 2008. [44] Congchao Wang, Yizhi Wang, Yinxue Wang, Chiung-Ting Wu, and Guoqiang Yu. mussp: Efficient min-cost flow algorithm for multi-object tracking.  ... 
arXiv:2201.07619v1 fatcat:mkj5iwowevdwnbc44ywahqr3jm