Temporal Gaussian Mixture Layer for Videos

ICLR 2019 AJ PiergiovanniMichael 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... (read more)

PDF Abstract

Evaluation Results from the Paper


 SOTA for Action Detection on THUMOS' 14 (using extra training data)

     Get a GitHub badge
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
COMPARE
Action Detection Charades TGM mAP 22.3 # 1
Action Detection Multi-THUMOS TGM mAP 46.4 # 1
Action Detection THUMOS' 14 TGM mAP 57.0 # 1