TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	EXTRA DATA	REMOVE
Action Detection	Charades	TGM (RGB+Flow)	mAP	22.3	# 13
Action Detection	Multi-THUMOS	TGM	mAP	46.4	# 4

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/temporal-gaussian-mixture-layer-for-videos/action-detection-on-multi-thumos)](https://paperswithcode.com/sota/action-detection-on-multi-thumos?p=temporal-gaussian-mixture-layer-for-videos)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/temporal-gaussian-mixture-layer-for-videos/action-detection-on-charades)](https://paperswithcode.com/sota/action-detection-on-charades?p=temporal-gaussian-mixture-layer-for-videos)`

Temporal Gaussian Mixture Layer for Videos

ICLR 2019 · AJ Piergiovanni, Michael S. Ryoo ·

We introduce a new convolutional layer named the Temporal Gaussian Mixture (TGM) layer and present how it can be used to efficiently capture longer-term temporal information in continuous activity videos. The TGM layer is a temporal convolutional layer governed by a much smaller set of parameters (e.g., location/variance of Gaussians) that are fully differentiable. We present our fully convolutional video models with multiple TGM layers for activity detection. The extensive experiments on multiple datasets, including Charades and MultiTHUMOS, confirm the effectiveness of TGM layers, significantly outperforming the state-of-the-arts.