Browse SoTA > Computer Vision > Action Localization > Action Segmentation

Action Segmentation

18 papers with code · Computer Vision
Subtask of Action Localization

Action Segmentation is a challenging problem in high-level video understanding. In its simplest form, Action Segmentation aims to segment a temporally untrimmed video by time and label each segmented part with one of pre-defined action labels. The results of Action Segmentation can be further used as input to various applications, such as video-to-text and action localization.

Source: TricorNet: A Hybrid Temporal Convolutional and Recurrent Network for Video Action Segmentation

Benchmarks

Greatest papers with code

Temporal Convolutional Networks for Action Segmentation and Detection

CVPR 2017 coderSkyChen/Action_Recognition_Zoo

The ability to identify and temporally segment fine-grained human actions throughout a video is crucial for robotics, surveillance, education, and beyond.

ACTION SEGMENTATION SKELETON BASED ACTION RECOGNITION

Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation

CVPR 2020 cmhungsteve/SSTDA

Despite the recent progress of fully-supervised action segmentation techniques, the performance is still not fully satisfactory.

ACTION SEGMENTATION DOMAIN ADAPTATION

MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation

CVPR 2019 yabufarha/ms-tcn

Temporally locating and classifying action segments in long untrimmed videos is of particular interest to many applications like surveillance and robotics.

ACTION SEGMENTATION

Weakly Supervised Energy-Based Learning for Action Segmentation

ICCV 2019 JunLi-Galios/CDFL

This paper is about labeling video frames with action classes under weak supervision in training, where we have access to a temporal ordering of actions, but their start and end frames in training videos are unknown.

ACTION SEGMENTATION VIDEO SEGMENTATION VIDEO SEMANTIC SEGMENTATION

Boundary-Aware Cascade Networks for Temporal Action Segmentation

ECCV 2020 MCG-NJU/BCN

To address these problems, we present a new boundary-aware cascade network by introducing two novel components.

ACTION SEGMENTATION

Weakly-Supervised Action Segmentation with Iterative Soft Boundary Assignment

CVPR 2018 Zephyr-D/TCFPN-ISBA

In this work, we address the task of weakly-supervised human action segmentation in long, untrimmed videos.

ACTION SEGMENTATION