Constraining Temporal Relationship for Action Localization

02/18/2020
by   Peisen Zhao, et al.
0

Recently, temporal action localization (TAL), i.e., finding specific action segments in untrimmed videos, has attracted increasing attentions of the computer vision community. State-of-the-art solutions for TAL involves predicting three values at each time point, corresponding to the probabilities that the action starts, continues and ends, and post-processing these curves for the final localization. This paper delves deep into this mechanism, and argues that existing approaches mostly ignored the potential relationship of these curves, and results in low quality of action proposals. To alleviate this problem, we add extra constraints to these curves, e.g., the probability of ”action continues” should be relatively high between probability peaks of ”action starts” and ”action ends”, so that the entire framework is aware of these latent constraints during an end-to-end optimization process. Experiments are performed on two popular TAL datasets, THUMOS14 and ActivityNet1.3. Our approach clearly outperforms the baseline both quantitatively (in terms of the AR@AN and mAP) and qualitatively (the curves in the testing stage become much smoother). In particular, when we build our constraints beyond TSA-Net and PGCN, we achieve the state-of-the-art performance especially at strict high IoU settings. The code will be available.

READ FULL TEXT

page 3

page 8

research
05/25/2019

Exploring Feature Representation and Training strategies in Temporal Action Localization

Temporal action localization has recently attracted significant interest...
research
12/01/2021

Graph Convolutional Module for Temporal Action Localization in Videos

Temporal action localization has long been researched in computer vision...
research
08/22/2019

3C-Net: Category Count and Center Loss for Weakly-Supervised Action Localization

Temporal action localization is a challenging computer vision problem wi...
research
04/20/2018

Rethinking the Faster R-CNN Architecture for Temporal Action Localization

We propose TAL-Net, an improved approach to temporal action localization...
research
05/01/2023

Boosting Weakly-Supervised Temporal Action Localization with Text Information

Due to the lack of temporal annotation, current Weakly-supervised Tempor...
research
11/04/2019

Temporal Action Localization using Long Short-Term Dependency

Temporal action localization in untrimmed videos is an important but dif...
research
11/13/2020

SALAD: Self-Assessment Learning for Action Detection

Literature on self-assessment in machine learning mainly focuses on the ...

Please sign up or login with your details

Forgot password? Click here to reset