Learning Temporal Embeddings for Complex Video Analysis
Vignesh Ramanathan, Kevin Tang, Greg Mori et al. · IEEE International Conference on Computer Vision (ICCV) · 2015
In this paper, we propose to learn temporal embeddings of video frames for complex video analysis. Large quantities of unlabeled video data can be easily obtained from the Internet. These videos possess the implicit weak label that they are sequences of temporally and semantically coherent images. We leverage this information to learn temporal embeddings for video frames by associating frames with the temporal context that they appear in. To do this, we propose a scheme for incorporating temporal context based on past and future frames in videos, and compare this to other contextual representations. In addition, we show how data augmentation using multi-resolution samples and hard negatives helps to significantly improve the quality of the learned embeddings. We evaluate various design decisions for learning temporal embeddings, and show that our embeddings can improve performance for multiple video tasks such as retrieval, classification, and temporal order recovery in unconstrained Internet video.
Cited by 69 works. doi:10.1109/iccv.2015.508 Open-access PDF
Authors
References
- ImageNet classification with deep convolutional neural networks
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- ImageNet: A large-scale hierarchical image database
- Caffe
- Efficient Estimation of Word Representations in Vector Space
- Visualizing Data using t-SNE
- Finding Structure in Time
- Large-Scale Video Classification with Convolutional Neural Networks
- A NEW MEASURE OF RANK CORRELATION
- 3D Convolutional Neural Networks for Human Action Recognition