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 2251–2300 of 2759 papers

TitleStatusHype
Privacy-Preserving Action Recognition for Smart Hospitals using Low-Resolution Depth Images—0
Privacy-Preserving Action Recognition using Coded Aperture Videos—0
PrivHAR: Recognizing Human Actions From Privacy-preserving Lens—0
Probabilistic Representations for Video Contrastive Learning—0
ProBio: A Protocol-guided Multimodal Dataset for Molecular Biology Lab—0
Language-Assisted Deep Learning for Autistic Behaviors Recognition—0
Procedural Generation of Videos to Train Deep Action Recognition Networks—0
Procedure Planning in Instructional Videos via Contextual Modeling and Model-based Policy Learning—0
Progressive Cross-modal Knowledge Distillation for Human Action Recognition—0
Progressively Parsing Interactional Objects for Fine Grained Action Detection—0
Progressive Spatio-Temporal Graph Convolutional Network for Skeleton-Based Human Action Recognition—0
Progressive Teacher-Student Learning for Early Action Prediction—0
Prompt-Guided Zero-Shot Anomaly Action Recognition using Pretrained Deep Skeleton Features—0
SCP: Soft Conditional Prompt Learning for Aerial Video Action Recognition—0
PromptonomyViT: Multi-Task Prompt Learning Improves Video Transformers using Synthetic Scene Data—0
ProtoGAN: Towards Few Shot Learning for Action Recognition—0
Proving the Potential of Skeleton Based Action Recognition to Automate the Analysis of Manual Processes—0
Proximal Control of UAVs with Federated Learning for Human-Robot Collaborative Domains—0
Pulling Actions out of Context: Explicit Separation for Effective Combination—0
PYSKL: Towards Good Practices for Skeleton Action Recognition—0
QORT-Former: Query-optimized Real-time Transformer for Understanding Two Hands Manipulating Objects—0
Quantifying and Learning Static vs. Dynamic Information in Deep Spatiotemporal Networks—0
Query Efficient Cross-Dataset Transferable Black-Box Attack on Action Recognition—0
Random Temporal Skipping for Multirate Video Analysis—0
Range-Sample Depth Feature for Action Recognition—0
REACT: Recognize Every Action Everywhere All At Once—0
ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding—0
Real Time Action Recognition from Video Footage—0
Real-time Action Recognition with Dissimilarity-based Training of Specialized Module Networks—0
Real-time Action Recognition with Enhanced Motion Vector CNNs—0
Real-Time Driver State Monitoring Using a CNN Based Spatio-Temporal Approach—0
Real-Time Elderly Monitoring for Senior Safety by Lightweight Human Action Recognition—0
Real-Time End-to-End Action Detection with Two-Stream Networks—0
Real-Time Human Action Recognition on Embedded Platforms—0
Real-time Human Action Recognition Using Locally Aggregated Kinematic-Guided Skeletonlet and Supervised Hashing-by-Analysis Model—0
Real-time Human Pose Estimation from Video with Convolutional Neural Networks—0
MorphMLP: An Efficient MLP-Like Backbone for Spatial-Temporal Representation LearningCode0
ADG-Pose: Automated Dataset Generation for Real-World Human Pose EstimationCode0
Adaptive frame selection in two dimensional convolutional neural network action recognitionCode0
UAV-GESTURE: A Dataset for UAV Control and Gesture RecognitionCode0
Multi-attention Networks for Temporal Localization of Video-level LabelsCode0
Asynchronous Temporal Fields for Action RecognitionCode0
Multi class activity classification in videos using Motion History Image generationCode0
More Is Less: Learning Efficient Video Representations by Big-Little Network and Depthwise Temporal AggregationCode0
Asymmetric Masked Distillation for Pre-Training Small Foundation ModelsCode0
UCF101: A Dataset of 101 Human Actions Classes From Videos in The WildCode0
Gate-Shift-Pose: Enhancing Action Recognition in Sports with Skeleton InformationCode0
Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action RecognitionCode0
A Bag-of-Words Equivalent Recurrent Neural Network for Action RecognitionCode0
Gate-Shift Networks for Video Action RecognitionCode0
Show:102550
← PrevPage 46 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