Learning Multi-Attention Context Graph for Group-Based Re-Identification
arXiv:2104.14236 · doi:10.1109/TPAMI.2020.3032542
Abstract
Learning to re-identify or retrieve a group of people across non-overlapped camera systems has important applications in video surveillance. However, most existing methods focus on (single) person re-identification (re-id), ignoring the fact that people often walk in groups in real scenarios. In this work, we take a step further and consider employing context information for identifying groups of people, i.e., group re-id. We propose a novel unified framework based on graph neural networks to simultaneously address the group-based re-id tasks, i.e., group re-id and group-aware person re-id. Specifically, we construct a context graph with group members as its nodes to exploit dependencies among different people. A multi-level attention mechanism is developed to formulate both intra-group and inter-group context, with an additional self-attention module for robust graph-level representations by attentively aggregating node-level features. The proposed model can be directly generalized to tackle group-aware person re-id using node-level representations. Meanwhile, to facilitate the deployment of deep learning models on these tasks, we build a new group re-id dataset that contains more than 3.8K images with 1.5K annotated groups, an order of magnitude larger than existing group re-id datasets. Extensive experiments on the novel dataset as well as three existing datasets clearly demonstrate the effectiveness of the proposed framework for both group-based re-id tasks. The code is available at https://github.com/daodaofr/group_reid.
References in corpus (19)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Neural Machine Translation by Jointly Learning to Align and Translate
- FaceNet: A Unified Embedding for Face Recognition and Clustering
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- A Discriminatively Learned CNN Embedding for Person Re-identification
- Multiple Object Recognition with Visual Attention
- Video Salient Object Detection via Fully Convolutional Networks
- A Strong Baseline and Batch Normalization Neck for Deep Person Re-identification
- GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval
- Person Re-Identification by Camera Correlation Aware Feature Augmentation
- FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification
- Attention-based Graph Neural Network for Semi-supervised Learning
- Graph Matching Networks for Learning the Similarity of Graph Structured Objects
- Pose Invariant Embedding for Deep Person Re-identification
- Learning Combinatorial Embedding Networks for Deep Graph Matching
- STA: Spatial-Temporal Attention for Large-Scale Video-based Person Re-Identification
- Learning Correspondence Structures for Person Re-identification
- Group Re-Identification with Multi-grained Matching and Integration
- Rethinking of Pedestrian Attribute Recognition: Realistic Datasets with Efficient Method