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 301–350 of 2759 papers

TitleStatusHype
D^2ST-Adapter: Disentangled-and-Deformable Spatio-Temporal Adapter for Few-shot Action RecognitionCode1
DEVIAS: Learning Disentangled Video Representations of Action and SceneCode1
EgoExOR: An Ego-Exo-Centric Operating Room Dataset for Surgical Activity UnderstandingCode1
EgoNCE++: Do Egocentric Video-Language Models Really Understand Hand-Object Interactions?Code1
Compressing Recurrent Neural Networks with Tensor Ring for Action RecognitionCode1
EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the BackboneCode1
End-to-End Learning of Visual Representations from Uncurated Instructional VideosCode1
End-to-End Streaming Video Temporal Action Segmentation with Reinforce LearningCode1
Actor-Context-Actor Relation Network for Spatio-Temporal Action LocalizationCode1
Enlarging Instance-specific and Class-specific Information for Open-set Action RecognitionCode1
Action-Conditioned 3D Human Motion Synthesis with Transformer VAECode1
Complex Sequential Understanding through the Awareness of Spatial and Temporal ConceptsCode1
Mitigating and Evaluating Static Bias of Action Representations in the Background and the ForegroundCode1
Spiking Neural Networks for event-based action recognition: A new task to understand their advantageCode1
Event Stream based Human Action Recognition: A High-Definition Benchmark Dataset and AlgorithmsCode1
Evidential Deep Learning for Open Set Action RecognitionCode1
Computer Vision for Clinical Gait Analysis: A Gait Abnormality Video DatasetCode1
Explore Human Parsing Modality for Action RecognitionCode1
BEVT: BERT Pretraining of Video TransformersCode1
Few-shot Action Recognition with Prototype-centered Attentive LearningCode1
CoFInAl: Enhancing Action Quality Assessment with Coarse-to-Fine Instruction AlignmentCode1
Fisher Information guided Purification against Backdoor AttacksCode1
CoCon: Cooperative-Contrastive LearningCode1
Frequency Guidance Matters: Skeletal Action Recognition by Frequency-Aware Mixed TransformerCode1
Attention-Based Context Aware Reasoning for Situation RecognitionCode1
Collaborating Domain-shared and Target-specific Feature Clustering for Cross-domain 3D Action RecognitionCode1
Concatenated Masked Autoencoders as Spatial-Temporal LearnerCode1
CIDEr: Consensus-based Image Description EvaluationCode1
Attention Prompt Tuning: Parameter-efficient Adaptation of Pre-trained Models for Spatiotemporal ModelingCode1
3DV: 3D Dynamic Voxel for Action Recognition in Depth VideoCode1
Action Genome: Actions as Composition of Spatio-temporal Scene GraphsCode1
Graph Contrastive Learning for Skeleton-based Action RecognitionCode1
CIAGAN: Conditional Identity Anonymization Generative Adversarial NetworksCode1
Group Contextualization for Video RecognitionCode1
3DYoga90: A Hierarchical Video Dataset for Yoga Pose UnderstandingCode1
CLIP-guided Prototype Modulating for Few-shot Action RecognitionCode1
Hidden Two-Stream Convolutional Networks for Action RecognitionCode1
Hierarchical Consistent Contrastive Learning for Skeleton-Based Action Recognition with Growing AugmentationsCode1
Anonymization for Skeleton Action RecognitionCode1
Hierarchically Self-Supervised Transformer for Human Skeleton Representation LearningCode1
Hierarchical Temporal Transformer for 3D Hand Pose Estimation and Action Recognition from Egocentric RGB VideosCode1
Augmented Neural Fine-Tuning for Efficient Backdoor PurificationCode1
A Unified Multimodal De- and Re-coupling Framework for RGB-D Motion RecognitionCode1
Large Scale Holistic Video UnderstandingCode1
A Deeper Dive Into What Deep Spatiotemporal Networks Encode: Quantifying Static vs. Dynamic InformationCode1
CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action RecognitionCode1
Hybrid Relation Guided Set Matching for Few-shot Action RecognitionCode1
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action RepresentationsCode1
A Dense-Sparse Complementary Network for Human Action Recognition based on RGB and Skeleton ModalitiesCode1
CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual DistillationCode1
Show:102550
← PrevPage 7 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