SOTAVerified

Action Recognition

Action Recognition is a computer vision task that involves recognizing human actions in videos or images. The goal is to classify and categorize the actions being performed in the video or image into a predefined set of action classes.

In the video domain, it is an open question whether training an action classification network on a sufficiently large dataset, will give a similar boost in performance when applied to a different temporal task or dataset. The challenges of building video datasets has meant that most popular benchmarks for action recognition are small, having on the order of 10k videos.

Please note some benchmarks may be located in the Action Classification or Video Classification tasks, e.g. Kinetics-400.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 701–750 of 2759 papers

TitleStatusHype
How Much Does Audio Matter to Recognize Egocentric Object Interactions?—0
Bypass Enhancement RGB Stream Model for Pedestrian Action Recognition of Autonomous Vehicles—0
Bullying10K: A Large-Scale Neuromorphic Dataset towards Privacy-Preserving Bullying Recognition—0
Building Neural Networks on Matrix Manifolds: A Gyrovector Space Approach—0
ALGO: Object-Grounded Visual Commonsense Reasoning for Open-World Egocentric Action Recognition—0
3D Convolutional with Attention for Action Recognition—0
Evolving Skeletons: Motion Dynamics in Action Recognition—0
ALBAR: Adversarial Learning approach to mitigate Biases in Action Recognition—0
Bubblenet: A Disperse Recurrent Structure To Recognize Activities—0
A Latent Clothing Attribute Approach for Human Pose Estimation—0
Accuracy and Performance Comparison of Video Action Recognition Approaches—0
Bringing Image Scene Structure to Video via Frame-Clip Consistency of Object Tokens—0
A Large-scale Varying-view RGB-D Action Dataset for Arbitrary-view Human Action Recognition—0
Bridging the gap between Human Action Recognition and Online Action Detection—0
Action Recognition for American Sign Language—0
3D Convolutional Neural Networks for Ultrasound-Based Silent Speech Interfaces—0
Bregman Divergences for Infinite Dimensional Covariance Matrices—0
Brain-inspired Computational Modeling of Action Recognition with Recurrent Spiking Neural Networks Equipped with Reinforcement Delay Learning—0
BQN: Busy-Quiet Net Enabled by Motion Band-Pass Module for Action Recognition—0
Boundary-Aware Proposal Generation Method for Temporal Action Localization—0
A Large-Scale Robustness Analysis of Video Action Recognition Models—0
Action recognition by learning pose representations—0
Bootstrapped Representation Learning for Skeleton-Based Action Recognition—0
Boosting Video Representation Learning with Multi-Faceted Integration—0
A Large-Scale Re-identification Analysis in Sporting Scenarios: the Betrayal of Reaching a Critical Point—0
A Key Volume Mining Deep Framework for Action Recognition—0
Boosting Adversarial Transferability for Skeleton-based Action Recognition via Exploring the Model Posterior Space—0
Action Recognition by Hierarchical Sequence Summarization—0
A Cause and Effect Analysis of Motion Trajectories for Modeling Actions—0
0/1 Deep Neural Networks via Block Coordinate Descent—0
Event Transformer+. A multi-purpose solution for efficient event data processing—0
Evolving Space-Time Neural Architectures for Videos—0
AI on the Road: A Comprehensive Analysis of Traffic Accidents and Accident Detection System in Smart Cities—0
Body Joint guided 3D Deep Convolutional Descriptors for Action Recognition—0
Action Recognition based on Subdivision-Fusion Model—0
Action Recognition by Hierarchical Mid-level Action Elements—0
Event Masked Autoencoder: Point-wise Action Recognition with Event-Based Cameras—0
Blockwise Temporal-Spatial Pathway Network—0
A Hybrid RNN-HMM Approach for Weakly Supervised Temporal Action Segmentation—0
BlanketSet -- A clinical real-world in-bed action recognition and qualitative semi-synchronised MoCap dataset—0
A Hybrid Loss for Multiclass and Structured Prediction—0
BlanketGen2-Fit3D: Synthetic Blanket Augmentation Towards Improving Real-World In-Bed Blanket Occluded Human Pose Estimation—0
Bio-Inspired Human Action Recognition using Hybrid Max-Product Neuro-Fuzzy Classifier and Quantum-Behaved PSO—0
A Hybrid Framework for Action Recognition in Low-Quality Video Sequences—0
Binary Coding for Partial Action Analysis With Limited Observation Ratios—0
Bilinear Heterogeneous Information Machine for RGB-D Action Recognition—0
A Hierarchical Pose-Based Approach to Complex Action Understanding Using Dictionaries of Actionlets and Motion Poselets—0
A Better Baseline for AVA—0
Big Data and Deep Learning in Smart Cities: A Comprehensive Dataset for AI-Driven Traffic Accident Detection and Computer Vision Systems—0
A Hierarchical Graph-based Approach for Recognition and Description Generation of Bimanual Actions in Videos—0
Show:102550
← PrevPage 15 of 56Next →
All datasetsSomething-Something V2UCF101HMDB-51Something-Something V1AVA v2.2EPIC-KITCHENS-100NTU RGB+DNTU RGB+D 120Diving-48ActivityNetAVA v2.1H2O (2 Hands and Objects)

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MViTv2-B (IN-21K + Kinetics400 pretrain)Top-5 Accuracy93.4—Unverified
2RSANet-R50 (8+16 frames, ImageNet pretrained, 2 clips)Top-5 Accuracy91.1—Unverified
3MVD (Kinetics400 pretrain, ViT-H, 16 frame)Top-1 Accuracy77.3—Unverified
4InternVideoTop-1 Accuracy77.2—Unverified
5DejaVidTop-1 Accuracy77.2—Unverified
6InternVideo2-1BTop-1 Accuracy77.1—Unverified
7VideoMAE V2-gTop-1 Accuracy77—Unverified
8MVD (Kinetics400 pretrain, ViT-L, 16 frame)Top-1 Accuracy76.7—Unverified
9Hiera-L (no extra data)Top-1 Accuracy76.5—Unverified
10TubeViT-LTop-1 Accuracy76.1—Unverified
#ModelMetricClaimedVerifiedStatus
1FTP-UniFormerV2-L/143-fold Accuracy99.7—Unverified
2OmniVec23-fold Accuracy99.6—Unverified
3OmniVec3-fold Accuracy99.6—Unverified
4VideoMAE V2-g3-fold Accuracy99.6—Unverified
5BIKE3-fold Accuracy98.8—Unverified
6SMART3-fold Accuracy98.64—Unverified
7ZeroI2V ViT-L/143-fold Accuracy98.6—Unverified
8OmniSource (SlowOnly-8x8-R101-RGB + I3D-Flow)3-fold Accuracy98.6—Unverified
9PERF-Net (multi-distilled S3D)3-fold Accuracy98.6—Unverified
10Text4Vis3-fold Accuracy98.2—Unverified