Beyond Temporal Pooling Recurrence And Temporal Convolutions For Gesture Recognition In Video
ASecurity**arXiv ID:** 1506.01911 **Authors:** Lionel Pigou, Aäron van den Oord, Sander Dieleman, Mieke Van Herreweghe, Joni Dambre **Published:** 2015-06-05T13:43:01Z **Abstract:** Recent studies have demonstrated the power of recurrent neural networks for machine translation, image captioning and speech recognition. For the task of capturing temporal structure in video, however, there still remain numerous open research questions. Current research suggests using a simple temporal feature pooling str...
- 3 stars
- 0 votes
- 0 copies
- 6 views
- Added September 11, 2026
Security analysis
100/100npx -y skills add hiyenwong/ai_collection --skill beyond-temporal-pooling-recurrence-and-temporal-convolutions-for-gesture-recognition-in-video --agent claude-codeAre you the author of Beyond Temporal Pooling Recurrence And Temporal Convolutions For Gesture Recognition In Video?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/hiyenwong-beyond-temporal-pooling-recurrence-and-temporal-co)# Beyond Temporal Pooling: Recurrence and Temporal Convolutions for Gesture Recognition in Video
**arXiv ID:** 1506.01911
**Authors:** Lionel Pigou, Aäron van den Oord, Sander Dieleman, Mieke Van Herreweghe, Joni Dambre
**Published:** 2015-06-05T13:43:01Z
**Abstract:**
Recent studies have demonstrated the power of recurrent neural networks for machine translation, image captioning and speech recognition. For the task of capturing temporal structure in video, however, there still remain numerous open research questions. Current research suggests using a simple temporal feature pooling strategy to take into account the temporal aspect of video. We demonstrate that this method is not sufficient for gesture recognition, where temporal information is more discriminative compared to general video classification tasks. We explore deep architectures for gesture recognition in video and propose a new end-to-end trainable neural network architecture incorporating temporal convolutions and bidirectional recurrence. Our main contributions are twofold; first, we show that recurrence is crucial for this task; second, we show that adding temporal convolutions leads to significant improvements. We evaluate the different approaches on the Montalbano gesture recognition dataset, where we achieve state-of-the-art results.
## Skill Description
This skill is generated from the arXiv paper: Beyond Temporal Pooling: Recurrence and Temporal Convolutions for Gesture Recognition in Video (1506.01911).
## How to Use
[To be filled in by the user or by future automation]
## References
- [arXiv:1506.01911](http://arxiv.org/abs/1506.01911v3)
Attribution
Related skills
View all in tools →Comments
Loading comments…
Newsletter
Get the weekly list of safe new skills, and the ones we pulled.