Video-based Person Re-identification via 3D Convolutional Networks and Non-local Attention

07/12/2018
by   Xingyu Liao, et al.
0

Video-based person re-identification (ReID) is a challenging problem, where some video tracks of people across non-overlapping cameras are available for matching. Feature aggregation from a video track is a key step for video-based person ReID. Many existing methods tackle this problem by average/maximum temporal pooling or RNNs with attention. However, these methods cannot deal with temporal dependency and spatial misalignment problems at the same time. We are inspired by video action recognition that involves the identification of different actions from video tracks. Firstly, we use 3D convolutions on video volume, instead of using 2D convolutions across frames, to extract spatial and temporal features simultaneously. Secondly, we use a non-local block to tackle the misalignment problem and capture spatial-temporal long-range dependencies. As a result, the network can learn useful spatial-temporal information as a weighted sum of the features in all space and temporal positions in the input feature map. Experimental results on three datasets show that our framework outperforms state-of-the-art approaches by a large margin on multiple metrics.

READ FULL TEXT
research
08/05/2019

Spatially and Temporally Efficient Non-local Attention Network for Video-based Person Re-Identification

Video-based person re-identification (Re-ID) aims at matching video sequ...
research
03/27/2018

Diversity Regularized Spatiotemporal Attention for Video-based Person Re-identification

Video-based person re-identification matches video clips of people acros...
research
03/12/2019

Learning Feature Aggregation in Temporal Domain for Re-Identification

Person re-identification is a standard and established problem in the co...
research
05/22/2021

Video-based Person Re-identification without Bells and Whistles

Video-based person re-identification (Re-ID) aims at matching the video ...
research
12/06/2020

Skeleon-Based Typing Style Learning For Person Identification

We present a novel architecture for person identification based on typin...
research
08/31/2019

Second-order Non-local Attention Networks for Person Re-identification

Recent efforts have shown promising results for person re-identification...
research
11/16/2021

Keypoint Message Passing for Video-based Person Re-Identification

Video-based person re-identification (re-ID) is an important technique i...

Please sign up or login with your details

Forgot password? Click here to reset