Revisiting Temporal Modeling for Video-based Person ReID
arXiv:1805.02104
Abstract
Video-based person reID is an important task, which has received much attention in recent years due to the increasing demand in surveillance and camera networks. A typical video-based person reID system consists of three parts: an image-level feature extractor (e.g. CNN), a temporal modeling method to aggregate temporal features and a loss function. Although many methods on temporal modeling have been proposed, it is hard to directly compare these methods, because the choice of feature extractor and loss function also have a large impact on the final performance. We comprehensively study and compare four different temporal modeling methods (temporal pooling, temporal attention, RNN and 3D convnets) for video-based person reID. We also propose a new attention generation network which adopts temporal convolution to extract temporal information among frames. The evaluation is done on the MARS dataset, and our methods outperform state-of-the-art methods by a large margin. Our source codes are released at https://github.com/jiyanggao/Video-Person-ReID.
arXiv commentcodes available at https://github.com/jiyanggao/Video-Person-ReID
References in corpus (3)
Cited by in corpus (25)
- Automated interpretation of congenital heart disease from multi-view echocardiograms
- Traffic-Aware Multi-Camera Tracking of Vehicles Based on ReID and Camera Link Model
- Multi-Granularity Reference-Aided Attentive Feature Aggregation for Video-based Person Re-identification
- Attention Control with Metric Learning Alignment for Image Set-based Recognition
- Spatial-Temporal Correlation and Topology Learning for Person Re-Identification in Videos
- Attribute-aware Identity-hard Triplet Loss for Video-based Person Re-identification
- Video Person Re-ID: Fantastic Techniques and Where to Find Them
- Video-based Person Re-identification via 3D Convolutional Networks and Non-local Attention
- Learning Longterm Representations for Person Re-Identification Using Radio Signals
- Discriminability Distillation in Group Representation Learning
- Fine-Grained Re-Identification
- Interpreting Depression From Question-wise Long-term Video Recording of SDS Evaluation
- Intra-clip Aggregation for Video Person Re-identification
- Temporal Attribute-Appearance Learning Network for Video-based Person Re-Identification
- A Flow-Guided Mutual Attention Network for Video-Based Person Re-Identification
- Reference-Aided Part-Aligned Feature Disentangling for Video Person Re-Identification
- A Symbolic Temporal Pooling method for Video-based Person Re-Identification
- Object-QA: Towards High Reliable Object Quality Assessment
- MessyTable: Instance Association in Multiple Camera Views
- A Spectral Nonlocal Block for Neural Networks
- Rethinking Temporal Fusion for Video-based Person Re-identification on Semantic and Time Aspect
- Beyond Universal Person Re-ID Attack
- Channel Recurrent Attention Networks for Video Pedestrian Retrieval
- Set Augmented Triplet Loss for Video Person Re-Identification
- Person Re-identification based on Robust Features in Open-world