Action Understanding
24 papers with code • 1 benchmarks • 4 datasets
Benchmarks
These leaderboards are used to track progress in Action Understanding
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
MTL-AQA
Fitness-AQA
Win-Fail Action Understanding
Most implemented papers
Action Recognition with Trajectory-Pooled Deep-Convolutional Descriptors
Visual features are of vital importance for human action understanding in videos.
YouMakeup VQA Challenge: Towards Fine-grained Action Understanding in Domain-Specific Videos
AIM3-RUC/YouMakeup_Baseline
•
•
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.
Detailed 2D-3D Joint Representation for Human-Object Interaction
DirtyHarryLYL/DJ-RN
•
•
CVPR 2020
In light of these, we propose a detailed 2D-3D joint representation learning method.
LEMMA: A Multi-view Dataset for Learning Multi-agent Multi-task Activities
Buzz-Beater/LEMMA
•
•
ECCV 2020
Understanding and interpreting human actions is a long-standing challenge and a critical indicator of perception in artificial intelligence.
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.
Video Action Understanding
Many believe that the successes of deep learning on image understanding problems can be replicated in the realm of video understanding.
Temporal Relational Modeling with Self-Supervision for Action Segmentation
redwang/DTGRM
•
•
The main reason is that large number of nodes (i. e., video frames) makes GCNs hard to capture and model temporal relations in videos.
Win-Fail Action Recognition
We introduce a first of its kind paired win-fail action understanding dataset with samples from the following domains: "General Stunts," "Internet Wins-Fails," "Trick Shots," and "Party Games."
Home Action Genome: Cooperative Compositional Action Understanding
nishantrai18/homage
•
•
CVPR 2021
However, there remains a lack of studies that extend action composition and leverage multiple viewpoints and multiple modalities of data for representation learning.
PIANO: A Parametric Hand Bone Model from Magnetic Resonance Imaging
Hand modeling is critical for immersive VR/AR, action understanding, or human healthcare.
