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 1551–1600 of 2759 papers

TitleStatusHype
On the spatial attention in Spatio-Temporal Graph Convolutional Networks for skeleton-based human action recognitionCode1
Mutual Modality Learning for Video Action ClassificationCode1
Learning Representations from Audio-Visual Spatial Alignment—0
Memory Group Sampling Based Online Action Recognition Using Kinetic Skeleton Features—0
A Survey on Contrastive Self-supervised Learning—0
Bubblenet: A Disperse Recurrent Structure To Recognize Activities—0
Pose-based Body Language Recognition for Emotion and Psychiatric Symptom Interpretation—0
CNN based Multistage Gated Average Fusion (MGAF) for Human Action Recognition Using Depth and Inertial SensorsCode0
SAR-NAS: Skeleton-based Action Recognition via Neural Architecture Searching—0
ElderSim: A Synthetic Data Generation Platform for Human Action Recognition in Eldercare Applications—0
Cycle-Contrast for Self-Supervised Video Representation Learning—0
RSPNet: Relative Speed Perception for Unsupervised Video Representation LearningCode1
Nested Grassmannians for Dimensionality Reduction with ApplicationsCode0
View-Invariant, Occlusion-Robust Probabilistic Embedding for Human PoseCode0
Temporal Attention-Augmented Graph Convolutional Network for Efficient Skeleton-Based Human Action Recognition—0
Deep Analysis of CNN-based Spatio-temporal Representations for Action RecognitionCode1
Learning to Sort Image Sequences via Accumulated Temporal Differences—0
Stronger, Faster and More Explainable: A Graph Convolutional Baseline for Skeleton-based Action RecognitionCode1
Depth Guided Adaptive Meta-Fusion Network for Few-shot Video RecognitionCode1
Self-supervised Co-training for Video Representation LearningCode1
Temporal Binary Representation for Event-Based Action RecognitionCode0
A Grid-based Representation for Human Action Recognition—0
Toward Accurate Person-level Action Recognition in Videos of Crowded Scenes—0
What Can You Learn from Your Muscles? Learning Visual Representation from Human InteractionsCode1
HPERL: 3D Human Pose Estimation from RGB and LiDARCode0
Pose And Joint-Aware Action RecognitionCode0
Pose Refinement Graph Convolutional Network for Skeleton-based Action Recognition—0
Back to the Future: Cycle Encoding Prediction for Self-supervised Contrastive Video Representation LearningCode0
Few-shot Action Recognition with Implicit Temporal Alignment and Pair Similarity Optimization—0
The MECCANO Dataset: Understanding Human-Object Interactions from Egocentric Videos in an Industrial-like DomainCode1
MS^2L: Multi-Task Self-Supervised Learning for Skeleton Based Action RecognitionCode1
Reconfigurable Cyber-Physical System for Lifestyle Video-Monitoring via Deep Learning—0
A Variational Information Bottleneck Based Method to Compress Sequential Networks for Human Action Recognition—0
Features Understanding in 3D CNNs for Actions Recognition in VideoCode0
InHARD - Industrial Human Action Recognition Dataset in the Context of Industrial Collaborative RoboticsCode1
Knowledge Fusion Transformers for Video Action Recognition—0
Action Concept Grounding Network for Semantically-Consistent Video Generation—0
PERF-Net: Pose Empowered RGB-Flow Net—0
Event-based Action Recognition Using Timestamp Image Encoding Network—0
Online Learnable Keyframe Extraction in Videos and its Application with Semantic Word Vector in Action Recognition—0
DeepActsNet: Spatial and Motion features from Face, Hands, and Body Combined with Convolutional and Graph Networks for Improved Action Recognition—0
Knowledge Guided Learning: Towards Open Domain Egocentric Action Recognition with Zero Supervision—0
Collaborative Distillation in the Parameter and Spectrum Domains for Video Action Recognition—0
Collaborative Attention Mechanism for Multi-View Action Recognition—0
Enhancing Unsupervised Video Representation Learning by Decoupling the Scene and the MotionCode1
HAA500: Human-Centric Atomic Action Dataset with Curated Videos—0
Unmanned Aerial Vehicle Control Through Domain-based Automatic Speech Recognition—0
A novel action recognition system for smart monitoring of elderly people using Action Pattern Image and Series CNN with transfer learning—0
Lifelong Graph LearningCode1
Semantics-aware Adaptive Knowledge Distillation for Sensor-to-Vision Action RecognitionCode1
Show:102550
← PrevPage 32 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
4DejaVidTop-1 Accuracy77.2—Unverified
5InternVideoTop-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
3VideoMAE V2-g3-fold Accuracy99.6—Unverified
4OmniVec3-fold Accuracy99.6—Unverified
5BIKE3-fold Accuracy98.8—Unverified
6SMART3-fold Accuracy98.64—Unverified
7OmniSource (SlowOnly-8x8-R101-RGB + I3D-Flow)3-fold Accuracy98.6—Unverified
8PERF-Net (multi-distilled S3D)3-fold Accuracy98.6—Unverified
9ZeroI2V ViT-L/143-fold Accuracy98.6—Unverified
10LGD-3D Two-stream3-fold Accuracy98.2—Unverified