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 1701–1750 of 2759 papers

TitleStatusHype
Scenes-Objects-Actions: A Multi-Task, Multi-Label Video Dataset—0
SCSampler: Sampling Salient Clips from Video for Efficient Action Recognition—0
MM-SEAL: A Large-scale Video Dataset of Multi-person Multi-grained Spatio-temporally Action Localization—0
Search-Map-Search: A Frame Selection Paradigm for Action Recognition—0
Second-order Temporal Pooling for Action Recognition—0
Seeing in Flowing: Adapting CLIP for Action Recognition with Motion Prompts Learning—0
Seeing What You're Told: Sentence-Guided Activity Recognition In Video—0
Segmental Spatiotemporal CNNs for Fine-grained Action Segmentation—0
Selective Feature Compression for Efficient Activity Recognition Inference—0
Selective, Interpretable, and Motion Consistent Privacy Attribute Obfuscation for Action Recognition—0
Selective Interpretable and Motion Consistent Privacy Attribute Obfuscation for Action Recognition—0
Self-Aligned Concave Curve: Illumination Enhancement for Unsupervised Adaptation—0
Self-attention based anchor proposal for skeleton-based action recognition—0
Self-Attention Network for Skeleton-based Human Action Recognition—0
Self-Supervised 3D Action Representation Learning with Skeleton Cloud Colorization—0
Self-Supervised 3D Skeleton Action Representation Learning With Motion Consistency and Continuity—0
Self-supervised Learning of Audio Representations from Audio-Visual Data using Spatial Alignment—0
Self-Supervised Learning of Motion-Informed Latents—0
Self-Supervised Learning via multi-Transformation Classification for Action Recognition—0
Self-supervised Motion Learning from Static Images—0
Self-supervised Motion Representation via Scattering Local Motion Cues—0
Self-Supervised Spatiotemporal Feature Learning via Video Rotation Prediction—0
Self-Supervised Spatiotemporal Learning via Video Clip Order Prediction—0
Self-supervised Spatiotemporal Representation Learning by Exploiting Video Continuity—0
Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles—0
Self-Supervised Video Representation Learning With Odd-One-Out Networks—0
Self-Supervised Video Representation Learning via Latent Time Navigation—0
Self-Supervised Video Representation Learning with Meta-Contrastive Network—0
Self-Supervised Video Representation Learning by Video Incoherence Detection—0
Semantically Video Coding: Instill Static-Dynamic Clues into Structured Bitstream for AI Tasks—0
Semantic-aware Video Representation for Few-shot Action Recognition—0
Semantic Embedding Space for Zero-Shot Action Recognition—0
Semantic-guided Cross-Modal Prompt Learning for Skeleton-based Zero-shot Action Recognition—0
Semantic Image Networks for Human Action Recognition—0
Semantic Labeling of Human Action For Visually Impaired And Blind People Scene Interaction—0
Semi-Coupled Two-Stream Fusion ConvNets for Action Recognition at Extremely Low Resolutions—0
Semi-Supervised Audio-Visual Video Action Recognition with Audio Source Localization Guided Mixup—0
Semi-supervised Fisher vector network—0
Sequence Summarization Using Order-constrained Kernelized Feature Subspaces—0
Sequential Deep Trajectory Descriptor for Action Recognition with Three-stream CNN—0
Sequential Feature Filtering Classifier—0
Shadow Augmentation for Handwashing Action Recognition: from Synthetic to Real Datasets—0
Shifted Chunk Transformer for Spatio-Temporal Representational Learning—0
SHREC 2021: Track on Skeleton-based Hand Gesture Recognition in the Wild—0
Shrinkage Optimized Directed Information using Pictorial Structures for Action Recognition—0
Shuffle and Attend: Video Domain Adaptation—0
Shuffle and Learn: Unsupervised Learning using Temporal Order Verification—0
Signal Alignment for Humanoid Skeletons via the Globally Optimal Reparameterization Algorithm—0
Similarity Min-Max: Zero-Shot Day-Night Domain Adaptation—0
Simplex-Based 3D Spatio-Temporal Feature Description for Action Recognition—0
Show:102550
← PrevPage 35 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