Back to Search
Start Over
ASTA-Net: Adaptive Spatio-Temporal Attention Network for Person Re-Identification in Videos
- Source :
- ACM Multimedia
- Publication Year :
- 2020
- Publisher :
- ACM, 2020.
-
Abstract
- The attention mechanism has been widely applied to enhance pedestrian representation for person re-identification in videos. However, most existing methods learn the spatial and temporal attention separately, and thus ignore the correlation between them. In this work, we propose a novel Adaptive Spatio-Temporal Attention Network (ASTA-Net) to adaptively aggregate the spatial and temporal attention features into discriminative pedestrian representation for person re-identification in videos. Specifically, multiple Adaptive Spatio-Temporal Fusion modules within ASTA-Net are designed for exploring precise spatio-temporal attention on multi-level feature maps. They first obtain the preliminary spatial and temporal attention features via the spatial semantic relations for each frame and temporal dependencies among inconsecutive frames, then adaptively aggregate the preliminary attention features on the basis of their correlation. Moreover, an Adjacent-Frame Motion module is designed to explicitly extract motion patterns according to the feature-level variation among adjacent frames. Extensive experiments on the three widely-used datasets, i.e., MARS, iLIDS-VID and PRID2011, have demonstrated the effectiveness of the proposed approach.
- Subjects :
- Basis (linear algebra)
Computer science
business.industry
Aggregate (data warehouse)
Frame (networking)
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Pattern recognition
02 engineering and technology
Variation (game tree)
010501 environmental sciences
01 natural sciences
Motion (physics)
Discriminative model
Feature (computer vision)
0202 electrical engineering, electronic engineering, information engineering
020201 artificial intelligence & image processing
Artificial intelligence
Representation (mathematics)
business
0105 earth and related environmental sciences
Subjects
Details
- Database :
- OpenAIRE
- Journal :
- Proceedings of the 28th ACM International Conference on Multimedia
- Accession number :
- edsair.doi...........e8b184fb4284b4f71ea234284b0850c7
- Full Text :
- https://doi.org/10.1145/3394171.3413843