Video Person Re-ID: Fantastic Techniques and Where to Find Them

21 Nov 2019  ·  Priyank Pathak, Amir Erfan Eshratifar, Michael Gormish ·

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 github.

PDF Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Person Re-Identification MARS B-BOT + OSM + CL Centers* (Re-rank) mAP 88.5 # 1
Person Re-Identification MARS B-BOT + Attention and CL loss Rank-1 88.6 # 10
Person Re-Identification MARS B-BOT + Attention and CL loss* mAP 82.9 # 10
Person Re-Identification PRID2011 B-BOT + Attention and CL loss* Rank-1 96.6 # 1

Methods


No methods listed for this paper. Add relevant methods here