@article{Luo_Stenger_Zhao_Kim_2015, title={Automatic Topic Discovery for Multi-Object Tracking}, volume={29}, url={https://ojs.aaai.org/index.php/AAAI/article/view/9789}, DOI={10.1609/aaai.v29i1.9789}, abstractNote={ <p> This paper proposes a new approach to multi-object tracking by semantic topic discovery. We dynamically cluster frame-by-frame detections and treat objects as topics, allowing the application of the Dirichlet Process Mixture Model (DPMM). The tracking problem is cast as a topic-discovery task where the video sequence is treated analogously to a document. This formulation addresses tracking issues such as object exclusivity constraints as well as cannot-link constraints which are integrated without the need for heuristic thresholds. The video is temporally segmented into epochs to model the dynamics of word (superpixel) co-occurrences and to model the temporal damping effect. In experiments on public data sets we demonstrate the effectiveness of the proposed algorithm. </p> }, number={1}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Luo, Wenhan and Stenger, Björn and Zhao, Xiaowei and Kim, Tae-Kyun}, year={2015}, month={Mar.} }