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 751–800 of 2759 papers

TitleStatusHype
Ego-Vehicle Action Recognition based on Semi-Supervised Contrastive Learning—0
Texture-Based Input Feature Selection for Action Recognition—0
Open Set Action Recognition via Multi-Label Evidential Learning—0
Spatial-temporal Transformer-guided Diffusion based Data Augmentation for Efficient Skeleton-based Action Recognition—0
Temporal-Channel Topology Enhanced Network for Skeleton-Based Action RecognitionCode0
DMMG: Dual Min-Max Games for Self-Supervised Skeleton-Based Action Recognition—0
Analysis of Real-Time Hostile Activitiy Detection from Spatiotemporal Features Using Time Distributed Deep CNNs, RNNs and Attention-Based Mechanisms—0
Multi-scale Motion-Aware Module for Video Action Recognition—0
Table Tennis Stroke Detection and Recognition Using Ball Trajectory Data—0
Video Action Recognition Collaborative Learning with Dynamics via PSO-ConvNet TransformerCode0
Dynamic Spatial-temporal Hypergraph Convolutional Network for Skeleton-based Action Recognition—0
Self-supervised Action Representation Learning from Partial Spatio-Temporal Skeleton SequencesCode1
Audio-Visual Contrastive Learning with Temporal Self-Supervision—0
Fine-grained Affordance Annotation for Egocentric Hand-Object Interaction VideosCode0
AIM: Adapting Image Models for Efficient Video Action RecognitionCode2
Pyramid Self-attention Polymerization Learning for Semi-supervised Skeleton-based Action RecognitionCode0
Spatiotemporal Decouple-and-Squeeze Contrastive Learning for Semi-Supervised Skeleton-based Action Recognition—0
Epic-Sounds: A Large-scale Dataset of Actions That SoundCode1
Open-VCLIP: Transforming CLIP to an Open-vocabulary Video Model via Interpolated Weight OptimizationCode1
Skeleton-based Human Action Recognition via Convolutional Neural Networks (CNN)—0
Action Capsules: Human Skeleton Action Recognition—0
Team VI-I2R Technical Report on EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2022—0
Skeleton-based Action Recognition through Contrasting Two-Stream Spatial-Temporal Networks—0
Graph Contrastive Learning for Skeleton-based Action RecognitionCode1
Improving Zero-Shot Action Recognition using Human Instruction with Text Description—0
Revisiting the Spatial and Temporal Modeling for Few-shot Action Recognition—0
CNN-Based Action Recognition and Pose Estimation for Classifying Animal Behavior from Videos: A Survey—0
CMAE-V: Contrastive Masked Autoencoders for Video Action Recognition—0
Deep learning-based approaches for human motion decoding in smart walkers for rehabilitation—0
HyRSM++: Hybrid Relation Guided Temporal Set Matching for Few-shot Action RecognitionCode1
Simplifying Open-Set Video Domain Adaptation with Contrastive LearningCode0
STPrivacy: Spatio-Temporal Privacy-Preserving Action Recognition—0
HierVL: Learning Hierarchical Video-Language EmbeddingsCode1
Multi-View Action Recognition Using Contrastive LearningCode0
Efficient Robustness Assessment via Adversarial Spatial-Temporal Focus on VideosCode0
Ego-Only: Egocentric Action Detection without Exocentric Transferring—0
Look, Listen, and Attack: Backdoor Attacks Against Video Action Recognition—0
Growing a Brain with Sparsity-Inducing Generation for Continual LearningCode0
LoTE-Animal: A Long Time-span Dataset for Endangered Animal Behavior Understanding—0
Parallel Attention Interaction Network for Few-Shot Skeleton-Based Action Recognition—0
ReGen: A good Generative Zero-Shot Video Classifier Should be Rewarded—0
Modeling the Relative Visual Tempo for Self-supervised Skeleton-based Action RecognitionCode0
Non-Semantics Suppressed Mask Learning for Unsupervised Video Semantic CompressionCode1
SkeleTR: Towards Skeleton-based Action Recognition in the Wild—0
Transformer-Based Unified Recognition of Two Hands Manipulating ObjectsCode1
Leveraging Temporal Context in Low Representational Power Regimes—0
Active Exploration of Multimodal Complementarity for Few-Shot Action Recognition—0
MMG-Ego4D: Multimodal Generalization in Egocentric Action RecognitionCode0
A Large-Scale Robustness Analysis of Video Action Recognition Models—0
Neural Koopman Pooling: Control-Inspired Temporal Dynamics Encoding for Skeleton-Based Action RecognitionCode1
Show:102550
← PrevPage 16 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