Person Reidentification by Deep Structured Prediction—A Fully Parameterized Approach
| Autor: | Xin Chen, Xinpeng L. Liao, Chengcui Zhang, Ming Dong |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Structure (mathematical logic)
business.industry Computer science Contrast (statistics) Sampling (statistics) Parameterized complexity 020207 software engineering 02 engineering and technology Machine learning computer.software_genre Computer Science Applications Hardware and Architecture Signal Processing 0202 electrical engineering electronic engineering information engineering Media Technology A priori and a posteriori Artificial intelligence Minification Structured prediction business Image retrieval computer Software |
| Zdroj: | IEEE MultiMedia. 26:42-55 |
| ISSN: | 1941-0166 1070-986X |
| DOI: | 10.1109/mmul.2019.2897678 |
| Popis: | Existing efforts on person reidentification (re-ID) either ignore the structural interactions among person images or require a highly crafted re-ID structure as a priori information. In contrast, our approach formulates person re-ID as a deep structured prediction problem that outperforms the state-of-the-art methods by utilizing neural-style-transfer-based structure sampling and fully parameterized energy networks. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|