Video-based Person Re-identification with Accumulative Motion Context
Preprint
Abstract
Video based person re-identification plays a central role in realistic security and video surveillance. In this paper we propose a novel Accumulative Motion Context (AMOC) network for addressing this important problem, which effectively exploits the long-range motion context for robustly identifying the same person under challenging conditions. Given a video sequence of the same or different persons, the proposed AMOC network jointly learns appearance representation and motion context from a collection of adjacent frames using a two-stream convolutional architecture. Then AMOC accumulates clues from motion context by recurrent aggregation, allowing effective information flow among adjacent frames and capturing dynamic gist of the persons. The architecture of AMOC is end-to-end trainable and thus motion context can be adapted to complement appearance clues under unfavorable conditions (\textit{e.g.}, occlusions). Extensive experiments are conduced on two public benchmark datasets, \textit{i.e.}, the iLIDS-VID and PRID-2011 datasets, to investigate the performance of AMOC. The experimental results demonstrate that the proposed AMOC network outperforms state-of-the-arts for video-based re-identification significantly and confirm the advantage of exploiting long-range motion context for video based person re-identification, validating our motivation evidently.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- End-to-End Comparative Attention Networks for Person Re-IdentificationIEEE Transactions on Image Processing, 2017
- Convolutional Two-Stream Network Fusion for Video Action Recognition2016
- Recurrent Convolutional Network for Video-Based Person Re-identification2016
- Person Re-identification by Exploiting Spatio-Temporal Cues and Multi-view Metric LearningIEEE Signal Processing Letters, 2016
- Person Re-Identification by Discriminative Selection in Video RankingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Deep feature learning with relative distance comparison for person re-identificationPattern Recognition, 2015
- Kernelized Relaxed Margin Components Analysis for Person Re-identificationIEEE Signal Processing Letters, 2014
- Color Invariants for Person ReidentificationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Reidentification by Relative Distance ComparisonIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- A Database and Evaluation Methodology for Optical FlowInternational Journal of Computer Vision, 2010