# TimeGate: Conditional Gating of Segments in Long-range Activities

arXiv: https://arxiv.org/abs/2004.01808 · HTML: https://mlsanity.com/paper/2004.01808/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Apr 2020.

## Built on by (most cited first, 7 of 7)

- [Learning To Recognize Procedural Activities with Distant Supervision](https://mlsanity.com/paper/2201.10990/) (2022)
- [Temporal Action Segmentation: An Analysis of Modern Techniques](https://mlsanity.com/paper/2210.10352/) (2022)
- [FrameExit: Conditional Early Exiting for Efficient Video Recognition](https://mlsanity.com/paper/2104.13400/) (2021)
- [AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition](https://mlsanity.com/paper/2105.05165/) (2021)
- [Dynamic Network Quantization for Efficient Video Inference](https://mlsanity.com/paper/2108.10394/) (2021)
- [Are current long-term video understanding datasets long-term?](https://mlsanity.com/paper/2308.11244/) (2023)
- [Video BagNet: short temporal receptive fields increase robustness in long-term action recognition](https://mlsanity.com/paper/2308.11249/) (2023)

## Abstract (arXiv)

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.