Jon Almazan, Bojana Gajic, Naila Murray, & Diane Larlus. (2018). Re-ID done right: towards good practices for person re-identification.
Abstract: Training a deep architecture using a ranking loss has become standard for the person re-identification task. Increasingly, these deep architectures include additional components that leverage part detections, attribute predictions, pose estimators and other auxiliary information, in order to more effectively localize and align discriminative image regions. In this paper we adopt a different approach and carefully design each component of a simple deep architecture and, critically, the strategy for training it effectively for person re-identification. We extensively evaluate each design choice, leading to a list of good practices for person re-identification. By following these practices, our approach outperforms the state of the art, including more complex methods with auxiliary components, by large margins on four benchmark datasets. We also provide a qualitative analysis of our trained representation which indicates that, while compact, it is able to capture information from localized and discriminative regions, in a manner akin to an implicit attention mechanism.
|
Jordi Gonzalez, Dani Rowe, Juan Andrade, & Juan J. Villanueva. (2006). Efficient Management of Multiple Agent Tracking Through Observation Handling.
|
Jordi Gonzalez, Javier Varona, Juan J. Villanueva, & Xavier Roca. (2001). On-line Human Activity Recognition for Video Surveillance..
|
Jordi Gonzalez, Javier Varona, Xavier Roca, & Juan J. Villanueva. (2001). Human Activity Learning and Recognition from Appearance..
|
Jordi Gonzalez, Javier Varona, Xavier Roca, & Juan J. Villanueva. (2003). Automatic Keyframing of Human Actions for Computer Animation.
|
Jordi Gonzalez, Javier Varona, Xavier Roca, & Juan J. Villanueva. (2003). A Human Action Comparison Framework for Motion Understanding.
|
Jordi Gonzalez, Javier Varona, Xavier Roca, & Juan J. Villanueva. (2003). Automatic Keyframing of Human Actions for Computer Animation.
|
Jordi Gonzalez, Javier Varona, Xavier Roca, & Juan J. Villanueva. (2003). A Human Action Comparison Framework for Motion Understanding.
|
Jordi Gonzalez, Javier Varona, Xavier Roca, & Juan J. Villanueva. (2003). Human Sequence Evaluation: towards Knowledge-based Scene Interpretations.
|
Jordi Gonzalez, Javier Varona, Xavier Roca, & Juan J. Villanueva. (2004). Analysis of Human Walking Based on aSpaces.
|
Jordi Gonzalez, Javier Varona, Xavier Roca, & Juan J. Villanueva. (2004). Situation Graph Trees for Human Behavior Modeling.
|
Jordi Vitria. (1996). Disseny de sistemes (intel.ligents) de visio..
|
Jordi Vitria, & J. Llacer. (1995). Recovering brightness and depth from focus using the Expectation-Maximization Algorithm..
|
Jordi Vitria, & J. Llacer. (1993). Recovering Depth from Focus Using Iterative image Estimation Techniques..
|
Jordi Vitria, X. Binefa, & Juan J. Villanueva. (1992). Morphological Algorithms for Visual Analysis of Integrated Circuits..
|