Abstract
Person re-identification (ReID) focuses on identifying people across different scenes in video surveillance, which is usually formulated as a binary classification task or a ranking
task in current person ReID approaches. In this paper, we take both tasks into account and propose a multi-task deep network (MTDnet) that makes use of their own advantages
and jointly optimize the two tasks simultaneously for person ReID. To the best of our knowledge, we are the first to integrate both tasks in one network to solve the person ReID.
We show that our proposed architecture significantly boosts the performance. Furthermore, deep architecture in general requires a sufficient dataset for training, which is usually not met in person ReID. To cope with this situation, we further extend the MTDnet and propose a cross-domain architecture that is capable of using an auxiliary set to assist training on small target sets. In the experiments, our approach outperforms most of existing person ReID algorithms on representative datasets including CUHK03, CUHK01, VIPeR, iLIDS and PRID2011, which clearly demonstrates the effectiveness of the proposed approach.
task in current person ReID approaches. In this paper, we take both tasks into account and propose a multi-task deep network (MTDnet) that makes use of their own advantages
and jointly optimize the two tasks simultaneously for person ReID. To the best of our knowledge, we are the first to integrate both tasks in one network to solve the person ReID.
We show that our proposed architecture significantly boosts the performance. Furthermore, deep architecture in general requires a sufficient dataset for training, which is usually not met in person ReID. To cope with this situation, we further extend the MTDnet and propose a cross-domain architecture that is capable of using an auxiliary set to assist training on small target sets. In the experiments, our approach outperforms most of existing person ReID algorithms on representative datasets including CUHK03, CUHK01, VIPeR, iLIDS and PRID2011, which clearly demonstrates the effectiveness of the proposed approach.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of The Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17) |
| Editors | Satinder Singh, Shaul Markovitch |
| Place of Publication | Palo Alto, CA |
| Publisher | AAAI Press |
| Pages | 3988-3994 |
| Number of pages | 7 |
| Publication status | Published - 17 Feb 2017 |
| Event | Thirty-first AAAI Conference on Artificial Intelligence - Hilton San Francisco, San Francisco, United States Duration: 4 Feb 2017 → 9 Feb 2017 http://www.aaai.org/Conferences/AAAI/aaai17.php (Link to Conference website) |
Conference
| Conference | Thirty-first AAAI Conference on Artificial Intelligence |
|---|---|
| Abbreviated title | AAAI-17 |
| Country/Territory | United States |
| City | San Francisco |
| Period | 4/02/17 → 9/02/17 |
| Internet address |
|
Keywords
- Person re-identification
- Multi-task
- Deep learning