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 1401–1450 of 2759 papers

TitleStatusHype
Continuous Action Recognition Based on Sequence Alignment—0
Continuous Human Action Recognition for Human-Machine Interaction: A Review—0
Continuous Video to Simple Signals for Swimming Stroke Detection with Convolutional Neural Networks—0
Contrast and Order Representations for Video Self-Supervised Learning—0
Contrastive Language Video Time Pre-training—0
Contrastive Learning of Image Representations with Cross-Video Cycle-Consistency—0
Contrastive Predictive Autoencoders for Dynamic Point Cloud Self-Supervised Learning—0
Contrast-reconstruction Representation Learning for Self-supervised Skeleton-based Action Recognition—0
Controllable Attention for Structured Layered Video Decomposition—0
Controllable Augmentations for Video Representation Learning—0
Convolutional Architecture Exploration for Action Recognition and Image Classification—0
Co-occurrence Feature Learning for Skeleton based Action Recognition using Regularized Deep LSTM Networks—0
Cooking in the kitchen: Recognizing and Segmenting Human Activities in Videos—0
Cooperative Cross-Stream Network for Discriminative Action Representation—0
Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization—0
Cooperative Training of Deep Aggregation Networks for RGB-D Action Recognition—0
Correlation Net: Spatiotemporal multimodal deep learning for action recognition—0
Co-training Transformer with Videos and Images Improves Action Recognition—0
Could Giant Pretrained Image Models Extract Universal Representations?—0
Coupled Recurrent Network (CRN)—0
CPR-Coach: Recognizing Composite Error Actions based on Single-class Training—0
Cross-Block Fine-Grained Semantic Cascade for Skeleton-Based Sports Action Recognition—0
Cross-Domain First Person Audio-Visual Action Recognition through Relative Norm Alignment—0
Cross Domain Model Compression by Structurally Weight Sharing—0
Cross-Enhancement Transform Two-Stream 3D ConvNets for Action Recognition—0
CrossGLG: LLM Guides One-shot Skeleton-based 3D Action Recognition in a Cross-level Manner—0
Cross-modal knowledge distillation for action recognition—0
Cross-Modal Learning with 3D Deformable Attention for Action Recognition—0
Cross-Modal Message Passing for Two-stream Fusion—0
Cross-modal Representation Learning for Zero-shot Action Recognition—0
Cross-Model Pseudo-Labeling for Semi-Supervised Action Recognition—0
Cross-Stage Transformer for Video Learning—0
Cross-Stream Contrastive Learning for Self-Supervised Skeleton-Based Action Recognition—0
Cross-view Action Modeling, Learning and Recognition—0
Cross-view Action Recognition Understanding From Exocentric to Egocentric Perspective—0
Cross-View Action Recognition via a Continuous Virtual Path—0
Cross-view Action Recognition via Contrastive View-invariant Representation—0
Cross Your Body: A Cognitive Assessment System for Children—0
CTM: Collaborative Temporal Modeling for Action Recognition—0
Curvature: A signature for Action Recognition in Video Sequences—0
CVB: A Video Dataset of Cattle Visual Behaviors—0
Cycle-Contrast for Self-Supervised Video Representation Learning—0
DARE: AI-based Diver Action Recognition System using Multi-Channel CNNs for AUV Supervision—0
Dark Transformer: A Video Transformer for Action Recognition in the Dark—0
Data Collection-free Masked Video Modeling—0
Data-Folding and Hyperspace Coding for Multi-Dimensonal Time-Series Data Imaging—0
DAVE: Diverse Atomic Visual Elements Dataset with High Representation of Vulnerable Road Users in Complex and Unpredictable Environments—0
DDLSTM: Dual-Domain LSTM for Cross-Dataset Action Recognition—0
Deception Detection in Videos—0
Decision Support for Video-based Detection of Flu Symptoms—0
Show:102550
← PrevPage 29 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