Learning from Dances: Pose-Invariant Re-Identification for Multi-Person TrackingDownload PDFOpen Website

2020 (modified: 23 Oct 2022)ICASSP 2020Readers: Everyone
Abstract: Most existing multi-person tracking approaches rely on appearance based re-identification (re-ID) to resolve fragmented tracklets. However, simply using appearance information could be insufficient for videos containing severe pose changes, such as sports or dance videos. With the goal of learning pose-invariant representations, we propose an end-to-end deep learning framework Sparse-Temporal ReID Network. Our proposed network not only realizes human pose disentanglement in an image recovery manner, but also makes efficient linkages between the identical subjects via a unique Sparse temporal identity sampling technique across time steps. Experimental results demonstrate the effectiveness of our proposed method on both multi-view re-ID benchmarks and our newly collected dance video dataset DanceReID http://www.w3.org/1998/Math/MathML" xmlns:xlink="1" target="_blank" rel="nofollow">http://www.w3.org/1999/xlink">1 .
0 Replies

Loading