SCAN: Self-and-Collaborative Attention Network for Video Person Re-identification
arXiv:1807.05688 · doi:10.1109/TIP.2019.2911488
Abstract
Video person re-identification attracts much attention in recent years. It aims to match image sequences of pedestrians from different camera views. Previous approaches usually improve this task from three aspects, including a) selecting more discriminative frames, b) generating more informative temporal representations, and c) developing more effective distance metrics. To address the above issues, we present a novel and practical deep architecture for video person re-identification termed Self-and-Collaborative Attention Network (SCAN). It has several appealing properties. First, SCAN adopts non-parametric attention mechanism to refine the intra-sequence and inter-sequence feature representation of videos, and outputs self-and-collaborative feature representation for each video, making the discriminative frames aligned between the probe and gallery sequences.Second, beyond existing models, a generalized pairwise similarity measurement is proposed to calculate the similarity feature representations of video pairs, enabling computing the matching scores by the binary classifier. Third, a dense clip segmentation strategy is also introduced to generate rich probe-gallery pairs to optimize the model. Extensive experiments demonstrate the effectiveness of SCAN, which outperforms the best-performing baselines on iLIDS-VID, PRID2011 and MARS dataset, respectively.
arXiv comment10 pages, 5 figures
References in corpus (21)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Two-Stream Convolutional Networks for Action Recognition in Videos
- Deep Residual Learning for Image Recognition
- In Defense of the Triplet Loss for Person Re-Identification
- Learning Discriminative Features with Multiple Granularities for Person Re-Identification
- NormFace: L2 Hypersphere Embedding for Face Verification
- Interaction Networks for Learning about Objects, Relations and Physics
- End-to-End Comparative Attention Networks for Person Re-identification
- Bit-Scalable Deep Hashing with Regularized Similarity Learning for Image Retrieval and Person Re-identification
- Person Re-Identification by Camera Correlation Aware Feature Augmentation
- Temporal Segment Networks: Towards Good Practices for Deep Action Recognition
- Cross-Domain Visual Matching via Generalized Similarity Measure and Feature Learning
- Non-local Neural Networks
- Learning View-Specific Deep Networks for Person Re-Identification
- Visual Interaction Networks
- Quality Aware Network for Set to Set Recognition
- Deep Recurrent Convolutional Networks for Video-based Person Re-identification: An End-to-End Approach
- Identity-Aware Textual-Visual Matching with Latent Co-attention
- Temporal Relational Reasoning in Videos
- Region-based Quality Estimation Network for Large-scale Person Re-identification
- Person Re-identification in Videos by Analyzing Spatio-Temporal Tubes
Cited by in corpus (12)
- Attention Mechanisms in Computer Vision: A Survey
- Adaptive Graph Representation Learning for Video Person Re-identification
- Person Re-identification via Attention Pyramid
- Video Joint Modelling Based on Hierarchical Transformer for Co-summarization
- Survey on Reliable Deep Learning-Based Person Re-Identification Models: Are We There Yet?
- Concentrated Multi-Grained Multi-Attention Network for Video Based Person Re-Identification
- Unsupervised Multi-view Clustering by Squeezing Hybrid Knowledge from Cross View and Each View
- Text-Independent Speaker Verification with Dual Attention Network
- A Spectral Nonlocal Block for Neural Networks
- Person Re-Identification using Deep Learning Networks: A Systematic Review
- Channel Recurrent Attention Networks for Video Pedestrian Retrieval
- Set Augmented Triplet Loss for Video Person Re-Identification