computer-vision-2

Action Understanding

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in action-understanding-2

Trend

Dataset

Best Model

Actions

Win-Fail Action Understanding

Libraries

i

Use these libraries to find action-understanding-2 models and implementations

Datasets

MTL-AQA

Fitness-AQA

Win-Fail Action Understanding

W-Oops

Subtasks

No subtasks available.

Most implemented papers

YouMakeup VQA Challenge: Towards Fine-grained Action Understanding in Domain-Specific Videos

Shizhe Chen, Qin Jin, Weiying Wang, Ludan Ruan, Linli Yao•Sat Apr 11 2020

The goal of the YouMakeup VQA Challenge 2020 is to provide a common benchmark for fine-grained action understanding in domain-specific videos e.g. makeup instructional videos, and two novel question-answering tasks are proposed to evaluate models' fine-grade action understanding abilities.

3

Content

0

Paper Graph

Action recognition with trajectory-pooled deep-convolutional descriptors

Y. Qiao, Xiaoou Tang, Limin Wang•Mon May 18 2015

This paper presents a new video representation, called trajectory-pooled deep-convolutional descriptor (TDD), which shares the merits of both hand-crafted features and deep-learned features, and achieves superior performance to the state of the art on these datasets.

1189 0

Paper Graph

Detailed 2D-3D Joint Representation for Human-Object Interaction

Jiefeng Li, Yong-Lu Li, Xinpeng Liu, Shiyi Wang, Cewu Lu, Han Lu, Junqi Liu•Thu Apr 16 2020

A detailed 2D-3D joint representation learning method for human-Object Interaction detection and a new benchmark named Ambiguous-HOI consisting of hard ambiguous images are proposed to better evaluate the 2D ambiguity processing capacity of models.

151 0

Paper Graph

LEMMA: A Multi-view Dataset for Learning Multi-agent Multi-task Activities

Song-Chun Zhu, Baoxiong Jia, Yixin Zhu, Siyuan Huang, Yixin Chen•Thu Jul 30 2020

The LEMMA dataset is introduced to provide a single home to address missing dimensions of daily human activities, including the goal-directed actions, concurrent multi-tasks, and collaborations among multi-agents with meticulously designed settings.

65 0

Paper Graph

Online Spatiotemporal Action Detection and Prediction via Causal Representations

Gurkirt Singh•Sun Aug 30 2020

It is sought to establish that online/causal representations can achieve similar performance to that of offline three dimensional convolutional neural networks (CNNs) on various tasks, including action recognition, temporal action segmentation and early prediction.

0 0

Paper Graph

Temporal Relational Modeling with Self-Supervision for Action Segmentation

D. Dou, Di Hu, Dong Wang, Xingjian Li•Sun Dec 13 2020

This paper introduces an effective GCN module, Dilated Temporal Graph Reasoning Module (DTGRM), designed to model temporal relations and dependencies between video frames at various time spans and outperforms state-of-the-art action segmentation models on three challenging datasets.

61 0

Paper Graph

Win-Fail Action Recognition

Paritosh Parmar, B. Morris•Sun Feb 14 2021

This work introduces a first of its kind paired win-fail action understanding dataset with samples from the following domains: “General Stunts,” “Internet Wins-Fails,’ “Trick Shots” & “Party Games” and systematically analyzes the characteristics of the task/dataset to determine its suitability to serve as a video understanding problem benchmark.

7 0

Paper Graph

Home Action Genome: Cooperative Compositional Action Understanding

Juan Carlos Niebles, Haofeng Chen, Nishant Rai, Jingwei Ji, Rishi Desai, K. Kozuka, Shun Ishizaka, Ehsan Adeli•Mon May 10 2021

HOMAGE is introduced: a multi-view action dataset with multiple modalities and view-points supplemented with hierarchical activity and atomic action labels together with dense scene composition labels and Cooperative Compositional Action Understanding (CCAU), a cooperative learning framework for hierarchical action recognition that is aware of compositional action elements.

87 0

Paper Graph

PIANO: A Parametric Hand Bone Model from Magnetic Resonance Imaging

Minye Wu, Jingyi Yu, Lan Xu, Yuwei Li, Yuyao Zhang•Sun Jun 20 2021

PIANO is presented, the first parametric bone model of human hands from MRI data, which is biologically correct, simple to animate, and differentiable, achieving more anatomically precise modeling of the inner hand kinematic structure in a data-driven manner than the traditional hand models based on the outer surface only.

26 0

Paper Graph

Adding a benchmark result helps the community track progress.