Learning Temporal Embeddings for Complex Video Analysis
arXiv:1505.00315
Abstract
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.
References in corpus (8)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
- Caffe: Convolutional Architecture for Fast Feature Embedding
- Recurrent Neural Network Regularization
- Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models
- Exploiting Image-trained CNN Architectures for Unconstrained Video Classification
- Unsupervised Feature Learning from Temporal Data
- A Discriminative CNN Video Representation for Event Detection