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 951–1000 of 2759 papers

TitleStatusHype
Balancing Privacy and Action Performance: A Penalty-Driven Approach to Image Anonymization—0
FinePseudo: Improving Pseudo-Labelling through Temporal-Alignablity for Semi-Supervised Fine-Grained Action Recognition—0
First Person Action Recognition Using Deep Learned Descriptors—0
CLTA: Contents and Length-based Temporal Attention for Few-shot Action Recognition—0
First-Take-All: Temporal Order-Preserving Hashing for 3D Action Videos—0
Adversarial Robustness in RGB-Skeleton Action Recognition: Leveraging Attention Modality Reweighter—0
CMAE-V: Contrastive Masked Autoencoders for Video Action Recognition—0
An Approach to Pose-Based Action Recognition—0
Baidu-UTS Submission to the EPIC-Kitchens Action Recognition Challenge 2019—0
Fitting, Comparison, and Alignment of Trajectories on Positive Semi-Definite Matrices with Application to Action Recognition—0
Head and eye egocentric gesture recognition for human-robot interaction using eyewear cameras—0
Dynamic Matrix Decomposition for Action Recognition—0
Flip-Invariant Motion Representation—0
Dynamic Inference: A New Approach Toward Efficient Video Action Recognition—0
FlowCaps: Optical Flow Estimation with Capsule Networks For Action Recognition—0
Flow-Distilled IP Two-Stream Networks for Compressed Video Action Recognition—0
hear-your-action: human action recognition by ultrasound active sensing—0
Anchor-Based Spatio-Temporal Attention 3D Convolutional Networks for Dynamic 3D Point Cloud Sequences—0
HFGCN:Hypergraph Fusion Graph Convolutional Networks for Skeleton-Based Action Recognition—0
Focal and Global Spatial-Temporal Transformer for Skeleton-based Action Recognition—0
Focalized Contrastive View-invariant Learning for Self-supervised Skeleton-based Action Recognition—0
Focusing and Diffusion: Bidirectional Attentive Graph Convolutional Networks for Skeleton-based Action Recognition—0
Bag of Visual Words and Fusion Methods for Action Recognition: Comprehensive Study and Good Practice—0
ForcePose: A Deep Learning Approach for Force Calculation Based on Action Recognition Using MediaPipe Pose Estimation Combined with Object Detection—0
Dynamic Hypergraph Convolutional Networks for Skeleton-Based Action Recognition—0
Adversarial Domain Adaptation for Action Recognition Around the Clock—0
Dynamic Graph Modules for Modeling Object-Object Interactions in Activity Recognition—0
fpgaHART: A toolflow for throughput-oriented acceleration of 3D CNNs for HAR onto FPGAs—0
Collaborative Attention Mechanism for Multi-View Action Recognition—0
Frame Order Matters: A Temporal Sequence-Aware Model for Few-Shot Action Recognition—0
Free-Form Composition Networks for Egocentric Action Recognition—0
Knowledge Distillation for Human Action Anticipation—0
Frequency-aware Event Cloud Network—0
HAUAR: Home Automation Using Action Recognition—0
From Actions to Events: A Transfer Learning Approach Using Improved Deep Belief Networks—0
From CNNs to Transformers in Multimodal Human Action Recognition: A Survey—0
From Detection to Action Recognition: An Edge-Based Pipeline for Robot Human Perception—0
An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data—0
From Image to Video: An Empirical Study of Diffusion Representations—0
From Pose to Activity: Surveying Datasets and Introducing CONVERSE—0
Dynamic Appearance: A Video Representation for Action Recognition with Joint Training—0
Dynamically Encoded Actions Based on Spacetime Saliency—0
Adversarial Cross-Domain Action Recognition with Co-Attention—0
Dynamic Action Recognition: A convolutional neural network model for temporally organized joint location data—0
Actionness Estimation Using Hybrid Fully Convolutional Networks—0
DWnet: Deep-Wide Network for 3D Action Recognition—0
FSD-10: A Dataset for Competitive Sports Content Analysis—0
Combined CNN Transformer Encoder for Enhanced Fine-grained Human Action Recognition—0
Fully-Coupled Two-Stream Spatiotemporal Networks for Extremely Low Resolution Action Recognition—0
Baby Physical Safety Monitoring in Smart Home Using Action Recognition System—0
Show:102550
← PrevPage 20 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
4InternVideoTop-1 Accuracy77.2—Unverified
5DejaVidTop-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
3OmniVec3-fold Accuracy99.6—Unverified
4VideoMAE V2-g3-fold Accuracy99.6—Unverified
5BIKE3-fold Accuracy98.8—Unverified
6SMART3-fold Accuracy98.64—Unverified
7ZeroI2V ViT-L/143-fold Accuracy98.6—Unverified
8OmniSource (SlowOnly-8x8-R101-RGB + I3D-Flow)3-fold Accuracy98.6—Unverified
9PERF-Net (multi-distilled S3D)3-fold Accuracy98.6—Unverified
10Text4Vis3-fold Accuracy98.2—Unverified