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 2001–2050 of 2759 papers

TitleStatusHype
Unlimited Knowledge Distillation for Action Recognition in the Dark—0
Unmanned Aerial Vehicle Control Through Domain-based Automatic Speech Recognition—0
Unrepresentative video data: A review and evaluation—0
Unseen Action Recognition with Unpaired Adversarial Multimodal Learning—0
Unsupervised Action Proposal Ranking through Proposal Recombination—0
Unsupervised Discriminative Embedding for Sub-Action Learning in Complex Activities—0
Unsupervised Domain Adaptation for Action Recognition via Self-Ensembling and Conditional Embedding Alignment—0
Unsupervised Domain Adaptation for Zero-Shot Learning—0
Unsupervised Few-Shot Action Recognition via Action-Appearance Aligned Meta-Adaptation—0
Unsupervised Learning for Human Sensing Using Radio Signals—0
Unsupervised Learning of Object Structure and Dynamics from Videos—0
Unsupervised Motion Representation Enhanced Network for Action Recognition—0
Unsupervised representation learning with long-term dynamics for skeleton based action recognition—0
Unsupervised Spatial-Temporal Feature Enrichment and Fidelity Preservation Network for Skeleton based Action Recognition—0
Unsupervised Spectral Dual Assignment Clustering of Human Actions in Context—0
Unsupervised Video Representation Learning by Bidirectional Feature Prediction—0
Unsupervised View-Invariant Human Posture Representation—0
User Satisfaction Modeling with Domain Adaptation in Task-oriented Dialogue Systems—0
Using joint angles based on the international biomechanical standards for human action recognition and related tasks—0
Using The Concept Hierarchy for Household Action Recognition—0
VA-AR: Learning Velocity-Aware Action Representations with Mixture of Window Attention—0
Variational Conditional Dependence Hidden Markov Models for Skeleton-Based Action Recognition—0
Vertex Feature Encoding and Hierarchical Temporal Modeling in a Spatial-Temporal Graph Convolutional Network for Action Recognition—0
Vi2CLR: Video and Image for Visual Contrastive Learning of Representation—0
Video 3D Sampling for Self-supervised Representation Learning—0
Video action recognition for lane-change classification and prediction of surrounding vehicles—0
Video Action Recognition Using spatio-temporal optical flow video frames—0
Video Action Recognition Via Neural Architecture Searching—0
Video Action Recognition with Attentive Semantic Units—0
Video Action Transformer Network—0
Benchmarking Badminton Action Recognition with a New Fine-Grained Dataset—0
Video-Based Action Recognition Using Rate-Invariant Analysis of Covariance Trajectories—0
Video-based Contrastive Learning on Decision Trees: from Action Recognition to Autism Diagnosis—0
Video-based Human Action Recognition using Deep Learning: A Review—0
Video-based Person Re-identification via 3D Convolutional Networks and Non-local Attention—0
Perceptron Synthesis Network: Rethinking the Action Scale Variances in Videos—0
Video Domain Incremental Learning for Human Action Recognition in Home Environments—0
VideoGLUE: Video General Understanding Evaluation of Foundation Models—0
Video Is Graph: Structured Graph Module for Video Action Recognition—0
Video Jigsaw: Unsupervised Learning of Spatiotemporal Context for Video Action Recognition—0
VideoLightFormer: Lightweight Action Recognition using Transformers—0
Video Modeling with Correlation Networks—0
Texture-Based Input Feature Selection for Action Recognition—0
Videoprompter: an ensemble of foundational models for zero-shot video understanding—0
Video Representation Learning by Recognizing Temporal Transformations—0
Video Representation Learning Using Discriminative Pooling—0
Video-ReTime: Learning Temporally Varying Speediness for Time Remapping—0
Video RWKV:Video Action Recognition Based RWKV—0
Videos as Space-Time Region Graphs—0
Video Segmentation Learning Using Cascade Residual Convolutional Neural Network—0
Show:102550
← PrevPage 41 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