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
Using The Concept Hierarchy for Household Action Recognition—0
2D bidirectional gated recurrent unit convolutional Neural networks for end-to-end violence detection In videos—0
Data Collection-free Masked Video Modeling—0
Real-Time Human Action Recognition on Embedded Platforms—0
ReL-SAR: Representation Learning for Skeleton Action Recognition with Convolutional Transformers and BYOLCode0
Self-Supervised Contrastive Learning for Videos using Differentiable Local AlignmentCode0
SITAR: Semi-supervised Image Transformer for Action Recognition—0
Unfolding Videos Dynamics via Taylor Expansion—0
ReSpike: Residual Frames-based Hybrid Spiking Neural Networks for Efficient Action RecognitionCode0
ADHD diagnosis based on action characteristics recorded in videos using machine learning—0
Action-Based ADHD Diagnosis in Video—0
FinePseudo: Improving Pseudo-Labelling through Temporal-Alignablity for Semi-Supervised Fine-Grained Action Recognition—0
Text-Enhanced Zero-Shot Action Recognition: A training-free approach—0
Online pre-training with long-form videos—0
DEAR: Depth-Enhanced Action RecognitionCode0
Comparative Analysis: Violence Recognition from Videos using Transfer LearningCode0
HabitAction: A Video Dataset for Human Habitual Behavior Recognition—0
Frame Order Matters: A Temporal Sequence-Aware Model for Few-Shot Action Recognition—0
Joint Temporal Pooling for Improving Skeleton-based Action Recognition—0
Temporal Reversed Training for Spiking Neural Networks with Generalized Spatio-Temporal Representation—0
Flatten: Video Action Recognition is an Image Classification task—0
Towards Physical World Backdoor Attacks against Skeleton Action Recognition—0
Action Recognition for Privacy-Preserving Ambient Assisted LivingCode0
Prototype Learning for Micro-gesture Classification—0
From Recognition to Prediction: Leveraging Sequence Reasoning for Action AnticipationCode0
Enhancing Human Action Recognition and Violence Detection Through Deep Learning Audiovisual Fusion—0
MultiFuser: Multimodal Fusion Transformer for Enhanced Driver Action Recognition—0
Signal-SGN: A Spiking Graph Convolutional Network for Skeletal Action Recognition via Learning Temporal-Frequency Dynamics—0
Task-Adapter: Task-specific Adaptation of Image Models for Few-shot Action Recognition—0
How Effective are Self-Supervised Models for Contact Identification in Videos—0
Skeleton-Based Action Recognition with Spatial-Structural Graph ConvolutionCode0
Joint-Partition Group Attention for skeleton-based action recognitionCode0
Adversarial Robustness in RGB-Skeleton Action Recognition: Leveraging Attention Modality Reweighter—0
MARINE: A Computer Vision Model for Detecting Rare Predator-Prey Interactions in Animal VideosCode0
Trajectory-aligned Space-time Tokens for Few-shot Action Recognition—0
C3T: Cross-modal Transfer Through Time for Sensor-based Human Activity Recognition—0
SOAP: Enhancing Spatio-Temporal Relation and Motion Information Capturing for Few-Shot Action RecognitionCode0
A Comprehensive Review of Few-shot Action Recognition—0
Can VLMs be used on videos for action recognition? LLMs are Visual Reasoning Coordinators—0
Decoupled Prompt-Adapter Tuning for Continual Activity Recognition—0
LORTSAR: Low-Rank Transformer for Skeleton-based Action Recognition—0
QuIIL at T3 challenge: Towards Automation in Life-Saving Intervention Procedures from First-Person ViewCode0
Pose-guided multi-task video transformer for driver action recognition—0
Enhancing Split Computing and Early Exit Applications through Predefined SparsityCode0
Human-Centric Transformer for Domain Adaptive Action Recognition—0
Region-aware Image-based Human Action Retrieval with Transformers—0
Boosting Adversarial Transferability for Skeleton-based Action Recognition via Exploring the Model Posterior Space—0
EA-VTR: Event-Aware Video-Text Retrieval—0
Masked Video and Body-worn IMU Autoencoder for Egocentric Action Recognition—0
Rethinking Image-to-Video Adaptation: An Object-centric Perspective—0
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