TimeGate: Conditional Gating of Segments in Long-range Activities
arXiv:2004.01808
Abstract
When recognizing a long-range activity, exploring the entire video is exhaustive and computationally expensive, as it can span up to a few minutes. Thus, it is of great importance to sample only the salient parts of the video. We propose TimeGate, along with a novel conditional gating module, for sampling the most representative segments from the long-range activity. TimeGate has two novelties that address the shortcomings of previous sampling methods, as SCSampler. First, it enables a differentiable sampling of segments. Thus, TimeGate can be fitted with modern CNNs and trained end-to-end as a single and unified model.Second, the sampling is conditioned on both the segments and their context. Consequently, TimeGate is better suited for long-range activities, where the importance of a segment heavily depends on the video context.TimeGate reduces the computation of existing CNNs on three benchmarks for long-range activities: Charades, Breakfast and MultiThumos. In particular, TimeGate reduces the computation of I3D by 50% while maintaining the classification accuracy.
References in corpus (10)
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
- Neural Architecture Search with Reinforcement Learning
- Categorical Reparameterization with Gumbel-Softmax
- The Kinetics Human Action Video Dataset
- Temporal Segment Networks: Towards Good Practices for Deep Action Recognition
- Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding
- Batch-Shaping for Learning Conditional Channel Gated Networks
- VideoGraph: Recognizing Minutes-Long Human Activities in Videos
- Efficient Video Classification Using Fewer Frames