# Temporal Gaussian Mixture Layer for Videos

## TL;DR

The paper proposes the Temporal Gaussian Mixture (TGM) layer, a novel convolutional layer that efficiently captures long-term temporal dependencies in videos, leading to improved activity detection performance.

## Contribution

Introduction of the TGM layer, a differentiable temporal convolutional layer with fewer parameters, enhancing long-term temporal modeling in video analysis.

## Key findings

- TGM layers outperform existing methods on Charades and MultiTHUMOS datasets.
- Models with TGM layers achieve significant accuracy improvements.
- TGM layers effectively capture long-term temporal information.

## Abstract

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.