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
Self-supervised Video Representation Learning by Context and Motion DecouplingCode0
UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial VehiclesCode1
Beyond Short Clips: End-to-End Video-Level Learning with Collaborative Memories—0
Self-supervised Motion Learning from Static Images—0
Selective Feature Compression for Efficient Activity Recognition Inference—0
Composable Augmentation Encoding for Video Representation Learning—0
Motion Guided Attention Fusion to Recognize Interactions from Videos—0
Weakly Supervised Temporal Action Localization Through Learning Explicit Subspaces for Action and Context—0
Recognizing Actions in Videos from Unseen Viewpoints—0
Learning Representational Invariances for Data-Efficient Action RecognitionCode1
Robust Audio-Visual Instance Discrimination—0
Busy-Quiet Video Disentangling for Video ClassificationCode1
ViViT: A Video Vision TransformerCode1
No frame left behind: Full Video Action RecognitionCode1
GPRAR: Graph Convolutional Network based Pose Reconstruction and Action Recognition for Human Trajectory PredictionCode0
An Image is Worth 16x16 Words, What is a Video Worth?Code1
Learning Comprehensive Motion Representation for Action Recognition—0
AdaSGN: Adapting Joint Number and Model Size for Efficient Skeleton-Based Action Recognition—0
MoViNets: Mobile Video Networks for Efficient Video RecognitionCode1
Efficient Spatialtemporal Context Modeling for Action Recognition—0
Deep Learning for Vision-Based Fall Detection System: Enhanced Optical Dynamic Flow—0
CLTA: Contents and Length-based Temporal Attention for Few-shot Action Recognition—0
NAS-TC: Neural Architecture Search on Temporal Convolutions for Complex Action Recognition—0
ACTION-Net: Multipath Excitation for Action RecognitionCode1
VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial ExamplesCode1
BASAR:Black-box Attack on Skeletal Action RecognitionCode1
Understanding the Robustness of Skeleton-based Action Recognition under Adversarial AttackCode1
VIPriors 1: Visual Inductive Priors for Data-Efficient Deep Learning ChallengesCode1
Unsupervised Motion Representation Enhanced Network for Action Recognition—0
DeepFN: Towards Generalizable Facial Action Unit Recognition with Deep Face Normalization—0
Domain Generalization: A Survey—0
Domain and View-point Agnostic Hand Action RecognitionCode0
A Body Part Embedding Model With Datasets for Measuring 2D Human Motion SimilarityCode1
Learning Transferable Visual Models From Natural Language SupervisionCode2
Phase Space Reconstruction Network for Lane Intrusion Action Recognition—0
A Temporal Fusion Approach for Video Classification with Convolutional and LSTM Neural Networks Applied to Violence Detection—0
Self-Supervised Learning via multi-Transformation Classification for Action Recognition—0
One-shot action recognition in challenging therapy scenariosCode1
Learning to Recognize Actions on Objects in Egocentric Video with Attention Dictionaries—0
Win-Fail Action RecognitionCode0
Learning Self-Similarity in Space and Time as Generalized Motion for Video Action RecognitionCode1
AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognition—0
Negative Data AugmentationCode1
Is Space-Time Attention All You Need for Video Understanding?Code2
Video Action Recognition Using spatio-temporal optical flow video frames—0
Semi-Supervised Action Recognition with Temporal Contrastive LearningCode1
GCF-Net: Gated Clip Fusion Network for Video Action Recognition—0
Optical flow and scene flow estimation: A survey—0
Video Transformer NetworkCode0
Embedding Symbolic Temporal Knowledge into Deep Sequential Models—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