Abstract | ||
---|---|---|
Most multitask trackers define the trace of each candidate as one task, and assume all tasks are equally related. Multitask learning is only evaluated on the current frame. In fact, these assumptions are limited, and ignore the multitask relationship in consecutive frames. In this letter, we propose a discriminative layered multitask tracker via spatial-temporal Laplacian graphs, which defines the... |
Year | DOI | Venue |
---|---|---|
2017 | 10.1109/LSP.2017.2756998 | IEEE Signal Processing Letters |
Keywords | Field | DocType |
Target tracking,Laplace equations,Robustness,Dictionaries,Sparse matrices,Linear programming | BitTorrent tracker,Mathematical optimization,Multi-task learning,Pattern recognition,Exploit,Robustness (computer science),Artificial intelligence,Linear programming,Discriminative model,Sparse matrix,Mathematics,Laplace operator | Journal |
Volume | Issue | ISSN |
24 | 12 | 1070-9908 |
Citations | PageRank | References |
0 | 0.34 | 21 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Baojie Fan | 1 | 41 | 10.48 |
Xiaomao Li | 2 | 7 | 3.61 |
Yang Cong | 3 | 684 | 38.22 |