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 1801–1850 of 2759 papers

TitleStatusHype
Vision-based Fight Detection from Surveillance CamerasCode1
Self-Supervised Joint Encoding of Motion and Appearance for First Person Action Recognition—0
Weakly-Supervised Multi-Person Action Recognition in 360^ Videos—0
Dynamic Inference: A New Approach Toward Efficient Video Action Recognition—0
FSD-10: A Dataset for Competitive Sports Content Analysis—0
GradMix: Multi-source Transfer across Domains and Tasks—0
Symbiotic Attention with Privileged Information for Egocentric Action Recognition—0
CTM: Collaborative Temporal Modeling for Action Recognition—0
Learning Class Regularized Features for Action Recognition—0
Poisson Kernel Avoiding Self-Smoothing in Graph Convolutional Networks—0
An Information-rich Sampling Technique over Spatio-Temporal CNN for Classification of Human Actions in Videos—0
3D ResNet with Ranking Loss Function for Abnormal Activity Detection in Videos—0
Modality Compensation Network: Cross-Modal Adaptation for Action Recognition—0
Joint Visual-Temporal Embedding for Unsupervised Learning of Actions in Untrimmed Sequences—0
Human Action Performance using Deep Neuro-Fuzzy Recurrent Attention Model—0
Multi-Modal Domain Adaptation for Fine-Grained Action RecognitionCode1
Action Recognition and State Change Prediction in a Recipe Understanding Task Using a Lightweight Neural Network Model—0
Zero-Shot Activity Recognition with Videos—0
Context-Aware Cross-Attention for Skeleton-Based Human Action Recognition—0
MixTConv: Mixed Temporal Convolutional Kernels for Efficient Action Recogntion—0
Rethinking Motion Representation: Residual Frames with 3D ConvNets for Better Action RecognitionCode1
Learning Spatiotemporal Features via Video and Text Pair DiscriminationCode1
Recognizing Video Events with Varying RhythmsCode0
Actions as Moving PointsCode1
Self-supervising Action Recognition by Statistical Moment and Subspace Descriptors—0
Few-shot Action Recognition with Permutation-invariant AttentionCode0
An Emerging Coding Paradigm VCM: A Scalable Coding Approach Beyond Feature and Signal—0
PGCN-TCA: Pseudo Graph Convolutional Network With Temporal and Channel-Wise Attention for Skeleton-Based Action Recognition—0
Human Action Recognition and Assessment via Deep Neural Network Self-Organization—0
Video Cloze Procedure for Self-Supervised Spatio-Temporal LearningCode1
Focusing and Diffusion: Bidirectional Attentive Graph Convolutional Networks for Skeleton-based Action Recognition—0
DMCL: Distillation Multiple Choice Learning for Multimodal Action RecognitionCode0
Adversarial Cross-Domain Action Recognition with Co-Attention—0
Vertex Feature Encoding and Hierarchical Temporal Modeling in a Spatial-Temporal Graph Convolutional Network for Action Recognition—0
Something-Else: Compositional Action Recognition with Spatial-Temporal Interaction NetworksCode0
Self-Attention Network for Skeleton-based Human Action Recognition—0
Mimetics: Towards Understanding Human Actions Out of Context—0
Multi-task Deep Learning for Real-Time 3D Human Pose Estimation and Action RecognitionCode0
Skeleton-Based Action Recognition with Multi-Stream Adaptive Graph Convolutional NetworksCode0
Action Genome: Actions as Composition of Spatio-temporal Scene GraphsCode1
End-to-End Learning of Visual Representations from Uncurated Instructional VideosCode1
SPIN: A High Speed, High Resolution Vision Dataset for Tracking and Action Recognition in Ping Pong—0
Totally Deep Support Vector Machines—0
Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action RecognitionCode0
Violence Recognition from Videos using Deep Learning Techniques—0
Hidden Markov Model: Tutorial—0
Flow-Distilled IP Two-Stream Networks for Compressed Video Action Recognition—0
HalluciNet-ing Spatiotemporal Representations Using a 2D-CNNCode0
SoccerDB: A Large-Scale Database for Comprehensive Video UnderstandingCode0
Listen to Look: Action Recognition by Previewing AudioCode1
Show:102550
← PrevPage 37 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