Zero-Shot Person Re-identification via Cross-View Consistency
- 3 December 2015
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 18 (2), 260-272
- https://doi.org/10.1109/tmm.2015.2505083
Abstract
Person re-identification, aiming to identify images of the same person from various cameras configured in different places, has attracted much attention in the multimedia retrieval community. In this problem, choosing a proper distance metric is a crucial aspect, and many classic methods utilize a uniform learnt metric. However, their performance is limited due to ignoring the zero-shot and fine-grained characteristics presented in real person re-identification applications. In this paper, we investigate two consistencies across two cameras, which are cross-view support consistency and cross-view projection consistency. The philosophy behind it is that, in spite of visual changes in two images of the same person under two camera views, the support sets in their respective views are highly consistent, and after being projected to the same view, their context sets are also highly consistent. Based on the above phenomena, we propose a data-driven distance metric (DDDM) method, re-exploiting the training data to adjust the metric for each query-gallery pair. Experiments conducted on three public data sets have validated the effectiveness of the proposed method, with a significant improvement over three baseline metric learning methods. In particular, on the public VIPeR dataset, the proposed method achieves an accuracy rate of 42.09% at rank-1, which outperforms the state-of-the-art methods by 4.29%.Keywords
Funding Information
- The National Natural Science Foundation of China (61170023, 61172173, 61231015, 61303114, 61501413, 61562048)
- the National High Technology Research and Development Program of China (2015AA016306)
- The Internet of Things Development Funding Project of Ministry of industry in 2013 (25)
- The Technology Research Program of Ministry of Public Security (2014JSYJA016)
- the Nature Science Foundation of Hubei Province (2014CFB712)
- The Nature Science Foundation of Jiangxi Province (20151BAB217013)
- the major Science and Technology Innovation Plan of Hubei Province (2013AAA020)
This publication has 38 references indexed in Scilit:
- Face Super-Resolution via Multilayer Locality-Constrained Iterative Neighbor Embedding and Intermediate Dictionary LearningIEEE Transactions on Image Processing, 2014
- Person Re-Identification Over Camera Networks Using Multi-Task Distance Metric LearningIEEE Transactions on Image Processing, 2014
- Noise Robust Face Hallucination via Locality-Constrained RepresentationIEEE Transactions on Multimedia, 2014
- Camera Compensation Using a Feature Projection Matrix for Person ReidentificationIEEE Transactions on Circuits and Systems for Video Technology, 2014
- Region-Based Interactive Ranking Optimization for Person Re-identificationLecture Notes in Computer Science, 2014
- People reidentification in surveillance and forensicsACM Computing Surveys, 2013
- Interactive retrieval of targets for wide area surveillancePublished by Association for Computing Machinery (ACM) ,2010
- Principal component analysisWIREs Computational Statistics, 2010
- Heat transfer characteristics of nanofluids: a reviewInternational Journal of Thermal Sciences, 2007
- Multiresolution gray-scale and rotation invariant texture classification with local binary patternsIeee Transactions On Pattern Analysis and Machine Intelligence, 2002