Action Segmentation
72 papers with code • 9 benchmarks • 16 datasets
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
These leaderboards are used to track progress in Action Segmentation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Action Segmentation models and implementationsDatasets
Breakfast
GTEA
JIGSAWS
COIN
Assembly101
Watch-n-Patch
TUM Kitchen
Subtasks
Most implemented papers
Temporal Unet: Sample Level Human Action Recognition using WiFi
geekfeiw/WiSLAR
•
•
In this task, every WiFi distortion sample in the whole series should be categorized into one action, which is a critical technique in precise action localization, continuous action segmentation, and real-time action recognition.
Frontal Low-rank Random Tensors for Fine-grained Action Segmentation
In this paper, we propose an approach to representing high-order information for temporal action segmentation via a simple yet effective bilinear form.
Weakly Supervised Energy-Based Learning for Action Segmentation
JunLi-Galios/CDFL
•
•
ICCV 2019
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 with Joint Self-Supervised Temporal Domain Adaptation
cmhungsteve/SSTDA
•
•
CVPR 2020
Despite the recent progress of fully-supervised action segmentation techniques, the performance is still not fully satisfactory.
SCT: Set Constrained Temporal Transformer for Set Supervised Action Segmentation
MohsenFayyaz89/SCT
•
•
CVPR 2020
In addition, the network estimates the action labels for each frame.
Learning to Segment Actions from Observation and Narration
dpfried/action-segmentation
•
•
ACL 2020
We apply a generative segmental model of task structure, guided by narration, to action segmentation in video.
MS-TCN++: Multi-Stage Temporal Convolutional Network for Action Segmentation
sj-li/MS-TCN2
•
•
Despite the capabilities of these approaches in capturing temporal dependencies, their predictions suffer from over-segmentation errors.
Online Spatiotemporal Action Detection and Prediction via Causal Representations
In this thesis, we focus on video action understanding problems from an online and real-time processing point of view.
ActBERT: Learning Global-Local Video-Text Representations
PaddlePaddle/PaddleVideo
•
•
CVPR 2020
In this paper, we introduce ActBERT for self-supervised learning of joint video-text representations from unlabeled data.
Alleviating Class-wise Gradient Imbalance for Pulmonary Airway Segmentation
haozheng-sjtu/3d-airway-segmentation
•
•
Due to the small size and scattered spatial distribution of peripheral bronchi, this is hampered by severe class imbalance between foreground and background regions, which makes it challenging for CNN-based methods to parse distal small airways.
