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 551–600 of 2759 papers

TitleStatusHype
Reuse and Diffuse: Iterative Denoising for Text-to-Video GenerationCode1
EgoPCA: A New Framework for Egocentric Hand-Object Interaction Understanding—0
SOAR: Scene-debiasing Open-set Action RecognitionCode1
B2C-AFM: Bi-Directional Co-Temporal and Cross-Spatial Attention Fusion Model for Human Action RecognitionCode1
SiT-MLP: A Simple MLP with Point-wise Topology Feature Learning for Skeleton-based Action RecognitionCode1
IndGIC: Supervised Action Recognition under Low Illumination—0
Balanced Representation Learning for Long-tailed Skeleton-based Action RecognitionCode0
Sparse Models for Machine Learning—0
Improving Video Violence Recognition with Human Interaction Learning on 3D Skeleton Point Clouds—0
EventTransAct: A video transformer-based framework for Event-camera based action recognition—0
Eventful Transformers: Leveraging Temporal Redundancy in Vision TransformersCode1
DD-GCN: Directed Diffusion Graph Convolutional Network for Skeleton-based Human Action RecognitionCode0
POCO: 3D Pose and Shape Estimation with ConfidenceCode1
MOFO: MOtion FOcused Self-Supervision for Video UnderstandingCode0
Opening the Vocabulary of Egocentric ActionsCode0
Are current long-term video understanding datasets long-term?Code0
Video BagNet: short temporal receptive fields increase robustness in long-term action recognitionCode0
Temporal-Distributed Backdoor Attack Against Video Based Action Recognition—0
Local Spherical Harmonics Improve Skeleton-Based Hand Action RecognitionCode0
Joint learning of images and videos with a single Vision Transformer—0
Spatial-Temporal Alignment Network for Action Recognition—0
TTPOINT: A Tensorized Point Cloud Network for Lightweight Action Recognition with Event Cameras—0
Unlimited Knowledge Distillation for Action Recognition in the Dark—0
Boosting Few-shot Action Recognition with Graph-guided Hybrid MatchingCode0
The Unreasonable Effectiveness of Large Language-Vision Models for Source-free Video Domain AdaptationCode0
Ske2Grid: Skeleton-to-Grid Representation Learning for Action RecognitionCode1
Action Class Relation Detection and Classification Across Multiple Video Datasets—0
Masked Motion Predictors are Strong 3D Action Representation LearnersCode1
On the Importance of Spatial Relations for Few-shot Action Recognition—0
Hard No-Box Adversarial Attack on Skeleton-Based Human Action Recognition with Skeleton-Motion-Informed GradientCode1
Ensemble Modeling for Multimodal Visual Action RecognitionCode0
Temporally-Adaptive Models for Efficient Video Understanding—0
JEDI: Joint Expert Distillation in a Semi-Supervised Multi-Dataset Student-Teacher Scenario for Video Action Recognition—0
Seeing in Flowing: Adapting CLIP for Action Recognition with Motion Prompts Learning—0
ViLP: Knowledge Exploration using Vision, Language, and Pose Embeddings for Video Action RecognitionCode0
Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and MaximizationCode1
M^3Net: Multi-view Encoding, Matching, and Fusion for Few-shot Fine-grained Action Recognition—0
MA-FSAR: Multimodal Adaptation of CLIP for Few-Shot Action Recognition—0
SkateboardAI: The Coolest Video Action Recognition for SkateboardingCode0
TS-RGBD Dataset: a Novel Dataset for Theatre Scenes Description for People with Visual ImpairmentsCode0
MAiVAR-T: Multimodal Audio-image and Video Action Recognizer using Transformers—0
Capturing Co-existing Distortions in User-Generated Content for No-reference Video Quality Assessment—0
Sample Less, Learn More: Efficient Action Recognition via Frame Feature RestorationCode0
Human-centric Scene Understanding for 3D Large-scale ScenariosCode1
Event-based Vision for Early Prediction of Manipulation ActionsCode0
Spatiotemporal Modeling Encounters 3D Medical Image Analysis: Slice-Shift UNet with Multi-View Fusion—0
EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge: Mixed Sequences Prediction—0
Two-stream Multi-level Dynamic Point Transformer for Two-person Interaction Recognition—0
AI on the Road: A Comprehensive Analysis of Traffic Accidents and Accident Detection System in Smart Cities—0
An X3D Neural Network Analysis for Runner's Performance Assessment in a Wild Sporting Environment—0
Show:102550
← PrevPage 12 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