Flow-Guided Feature Aggregation for Video Object Detection
Xizhou Zhu, Yujie Wang, Jifeng Dai et al. · IEEE International Conference on Computer Vision (ICCV) · 2017
Extending state-of-the-art object detectors from image to video is challenging. The accuracy of detection suffers from degenerated object appearances in videos, e.g., motion blur, video defocus, rare poses, etc. Existing work attempts to exploit temporal information on box level, but such methods are not trained end-to-end. We present flow-guided feature aggregation, an accurate and end-to-end learning framework for video object detection. It leverages temporal coherence on feature level instead. It improves the per-frame features by aggregation of nearby features along the motion paths, and thus improves the video recognition accuracy. Our method significantly improves upon strong singleframe baselines in ImageNet VID [33], especially for more challenging fast moving objects. Our framework is principled, and on par with the best engineered systems winning the ImageNet VID challenges 2016, without additional bells-and-whistles. The code would be released.
Cited by 702 works. doi:10.1109/iccv.2017.52 Open-access PDF
Authors
References
- Deep Residual Learning for Image Recognition
- ImageNet classification with deep convolutional neural networks
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
- Going deeper with convolutions
- ImageNet Large Scale Visual Recognition Challenge
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Dropout: a simple way to prevent neural networks from overfitting
- Fast R-CNN
- SSD: Single Shot MultiBox Detector