FIFA: Fast Inference Approximation for Action Segmentation

08/09/2021
by   Yaser Souri, et al.
7

We introduce FIFA, a fast approximate inference method for action segmentation and alignment. Unlike previous approaches, FIFA does not rely on expensive dynamic programming for inference. Instead, it uses an approximate differentiable energy function that can be minimized using gradient-descent. FIFA is a general approach that can replace exact inference improving its speed by more than 5 times while maintaining its performance. FIFA is an anytime inference algorithm that provides a better speed vs. accuracy trade-off compared to exact inference. We apply FIFA on top of state-of-the-art approaches for weakly supervised action segmentation and alignment as well as fully supervised action segmentation. FIFA achieves state-of-the-art results on most metrics on two action segmentation datasets.

READ FULL TEXT

page 20

page 21

page 22

page 23

page 24

page 25

research
04/05/2019

Weakly Supervised Action Segmentation Using Mutual Consistency

Action segmentation is the task of predicting the actions in each frame ...
research
01/09/2019

D^3TW: Discriminative Differentiable Dynamic Time Warping for Weakly Supervised Action Alignment and Segmentation

We address weakly-supervised action alignment and segmentation in videos...
research
05/19/2020

On Evaluating Weakly Supervised Action Segmentation Methods

Action segmentation is the task of temporally segmenting every frame of ...
research
04/01/2019

Benchmarking Approximate Inference Methods for Neural Structured Prediction

Exact structured inference with neural network scoring functions is comp...
research
03/09/2018

Learning Approximate Inference Networks for Structured Prediction

Structured prediction energy networks (SPENs; Belanger & McCallum 2016) ...
research
01/14/2022

Transformers in Action: Weakly Supervised Action Segmentation

The video action segmentation task is regularly explored under weaker fo...
research
03/15/2018

Temporal Human Action Segmentation via Dynamic Clustering

We present an effective dynamic clustering algorithm for the task of tem...

Please sign up or login with your details

Forgot password? Click here to reset