Multi-Granularity Reference-Aided Attentive Feature Aggregation for Video-Based Person Re-Identification
Authors:
- 1 June 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 10404-10413
Abstract
Video-based person re-identification (reID) aims at matching the same person across video clips. It is a challenging task due to the existence of redundancy among frames, newly revealed appearance, occlusion, and motion blurs. In this paper, we propose an attentive feature aggregation module, namely Multi-Granularity Reference-aided Attentive Feature Aggregation (MG-RAFA), to delicately aggregate spatio-temporal features into a discriminative video-level feature representation. In order to determine the contribution/importance of a spatial-temporal feature node, we propose to learn the attention from a global view with convolutional operations. Specifically, we stack its relations, \ieno, pairwise correlations with respect to a representative set of reference feature nodes (S-RFNs) that represents global video information, together with the feature itself to infer the attention. Moreover, to exploit the semantics of different levels, we propose to learn multi-granularity attentions based on the relations captured at different granularities. Extensive ablation studies demonstrate the effectiveness of our attentive feature aggregation module MG-RAFA. Our framework achieves the state-of-the-art performance on three benchmark datasets.Keywords
All Related Versions
This publication has 28 references indexed in Scilit:
- Quality Aware Network for Set to Set Recognition2017
- See the Forest for the Trees: Joint Spatial and Temporal Recurrent Neural Networks for Video-Based Person Re-identification2017
- Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset2017
- Video-Based Person Re-Identification With Accumulative Motion ContextIEEE Transactions on Circuits and Systems for Video Technology, 2017
- End-to-End Comparative Attention Networks for Person Re-IdentificationIEEE Transactions on Image Processing, 2017
- Deep Residual Learning for Image Recognition2016
- Rethinking the Inception Architecture for Computer Vision2016
- Recurrent Convolutional Network for Video-Based Person Re-identification2016
- 3D Convolutional Neural Networks for Human Action RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- The recognition of human movement using temporal templatesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2001