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 51–100 of 2759 papers

TitleStatusHype
Revealing Single Frame Bias for Video-and-Language LearningCode2
EgoVideo: Exploring Egocentric Foundation Model and Downstream AdaptationCode2
ActionFormer: Localizing Moments of Actions with TransformersCode2
Omni-sourced Webly-supervised Learning for Video RecognitionCode2
HAKE: A Knowledge Engine Foundation for Human Activity UnderstandingCode2
Dynamic 3D Point Cloud Sequences as 2D VideosCode2
DeGCN: Deformable Graph Convolutional Networks for Skeleton-Based Action RecognitionCode2
Deep Architectures for Content Moderation and Movie Content RatingCode2
Egocentric Video-Language PretrainingCode2
Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language ModelsCode2
Contrastive Learning from Spatio-Temporal Mixed Skeleton Sequences for Self-Supervised Skeleton-Based Action RecognitionCode1
Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action RecognitionCode1
ConvNet Architecture Search for Spatiotemporal Feature LearningCode1
3D Human Action Representation Learning via Cross-View Consistency PursuitCode1
A Comprehensive Study of Deep Video Action RecognitionCode1
Context-Aware RCNN: A Baseline for Action Detection in VideosCode1
Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical AggregationCode1
Volterra Neural Networks (VNNs)Code1
Concatenated Masked Autoencoders as Spatial-Temporal LearnerCode1
Conquering the cnn over-parameterization dilemma: A volterra filtering approach for action recognitionCode1
Compressing Recurrent Neural Networks with Tensor Ring for Action RecognitionCode1
Complex Sequential Understanding through the Awareness of Spatial and Temporal ConceptsCode1
Computer Vision for Clinical Gait Analysis: A Gait Abnormality Video DatasetCode1
Constructing Stronger and Faster Baselines for Skeleton-based Action RecognitionCode1
Counterfactual Debiasing Inference for Compositional Action RecognitionCode1
A Closer Look at Spatiotemporal Convolutions for Action RecognitionCode1
CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual DistillationCode1
CoCon: Cooperative-Contrastive LearningCode1
CIDEr: Consensus-based Image Description EvaluationCode1
CIAGAN: Conditional Identity Anonymization Generative Adversarial NetworksCode1
CLIP-guided Prototype Modulating for Few-shot Action RecognitionCode1
CoFInAl: Enhancing Action Quality Assessment with Coarse-to-Fine Instruction AlignmentCode1
A Body Part Embedding Model With Datasets for Measuring 2D Human Motion SimilarityCode1
Challenges in Video-Based Infant Action Recognition: A Critical Examination of the State of the ArtCode1
Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action RecognitionCode1
CAST: Cross-Attention in Space and Time for Video Action RecognitionCode1
C2C: Component-to-Composition Learning for Zero-Shot Compositional Action RecognitionCode1
CDFSL-V: Cross-Domain Few-Shot Learning for VideosCode1
CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action RecognitionCode1
Collaborating Domain-shared and Target-specific Feature Clustering for Cross-domain 3D Action RecognitionCode1
Cross-Architecture Self-supervised Video Representation LearningCode1
ACTION-Net: Multipath Excitation for Action RecognitionCode1
BMN: Boundary-Matching Network for Temporal Action Proposal GenerationCode1
BEVT: BERT Pretraining of Video TransformersCode1
3D CNNs with Adaptive Temporal Feature ResolutionsCode1
Building an Open-Vocabulary Video CLIP Model with Better Architectures, Optimization and DataCode1
CAKES: Channel-wise Automatic KErnel Shrinking for Efficient 3D NetworksCode1
Blindly Assess Quality of In-the-Wild Videos via Quality-aware Pre-training and Motion PerceptionCode1
Full-Body Articulated Human-Object InteractionCode1
Bridging Video-text Retrieval with Multiple Choice QuestionsCode1
Show:102550
← PrevPage 2 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