Video Person Re-ID: Fantastic Techniques and Where to Find Them (Student Abstract)

Authors

  • Priyank Pathak New York University
  • Amir Erfan Eshratifar University of Southern California, Los Angeles
  • Michael Gormish Clarifai

DOI:

https://doi.org/10.1609/aaai.v34i10.7219

Abstract

The ability to identify the same person from multiple camera views without the explicit use of facial recognition is receiving commercial and academic interest. The current status-quo solutions are based on attention neural models. In this paper, we propose Attention and CL loss, which is a hybrid of center and Online Soft Mining (OSM) loss added to the attention loss on top of a temporal attention-based neural network. The proposed loss function applied with bag-of-tricks for training surpasses the state of the art on the common person Re-ID datasets, MARS and PRID 2011. Our source code is publicly available on github1.

Downloads

Published

2020-04-03

How to Cite

Pathak, P., Eshratifar, A. E., & Gormish, M. (2020). Video Person Re-ID: Fantastic Techniques and Where to Find Them (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 34(10), 13893-13894. https://doi.org/10.1609/aaai.v34i10.7219

Issue

Section

Student Abstract Track