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 151–200 of 2759 papers

TitleStatusHype
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology ModelingCode1
Action-Conditioned 3D Human Motion Synthesis with Transformer VAECode1
Dual Contrastive Prediction for Incomplete Multi-view Representation LearningCode1
Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action RecognitionCode1
Actor-Context-Actor Relation Network for Spatio-Temporal Action LocalizationCode1
Do Language Models Understand Time?Code1
Attention Prompt Tuning: Parameter-efficient Adaptation of Pre-trained Models for Spatiotemporal ModelingCode1
Dual-path Adaptation from Image to Video TransformersCode1
Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM for Unsupervised Action RecognitionCode1
Domain Knowledge-Informed Self-Supervised Representations for Workout Form AssessmentCode1
Augmented Neural Fine-Tuning for Efficient Backdoor PurificationCode1
BASAR:Black-box Attack on Skeletal Action RecognitionCode1
DSANet: Dynamic Segment Aggregation Network for Video-Level Representation LearningCode1
3DV: 3D Dynamic Voxel for Action Recognition in Depth VideoCode1
Dynamic Perceiver for Efficient Visual RecognitionCode1
A Unified Multimodal De- and Re-coupling Framework for RGB-D Motion RecognitionCode1
ArtEmis: Affective Language for Visual ArtCode1
AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual ActionsCode1
ActionCLIP: A New Paradigm for Video Action RecognitionCode1
AViD Dataset: Anonymized Videos from Diverse CountriesCode1
Disentangled Pre-training for Human-Object Interaction DetectionCode1
A Deeper Dive Into What Deep Spatiotemporal Networks Encode: Quantifying Static vs. Dynamic InformationCode1
BABEL: Bodies, Action and Behavior with English LabelsCode1
A Dense-Sparse Complementary Network for Human Action Recognition based on RGB and Skeleton ModalitiesCode1
Action knowledge for video captioning with graph neural networksCode1
ARID: A New Dataset for Recognizing Action in the DarkCode1
Benchmarking Micro-action Recognition: Dataset, Methods, and ApplicationsCode1
AR-Net: Adaptive Frame Resolution for Efficient Action RecognitionCode1
Disentangled Non-Local Neural NetworksCode1
Blindly Assess Quality of In-the-Wild Videos via Quality-aware Pre-training and Motion PerceptionCode1
Disentangling and Unifying Graph Convolutions for Skeleton-Based Action RecognitionCode1
End-to-End Learning of Visual Representations from Uncurated Instructional VideosCode1
BMN: Boundary-Matching Network for Temporal Action Proposal GenerationCode1
Bridging Video-text Retrieval with Multiple Choice QuestionsCode1
EPAM-Net: An Efficient Pose-driven Attention-guided Multimodal Network for Video Action RecognitionCode1
EPFL-Smart-Kitchen-30: Densely annotated cooking dataset with 3D kinematics to challenge video and language modelsCode1
ACTION-Net: Multipath Excitation for Action RecognitionCode1
Building a Multi-modal Spatiotemporal Expert for Zero-shot Action Recognition with CLIPCode1
BST: Badminton Stroke-type Transformer for Skeleton-based Action Recognition in Racket SportsCode1
Bringing Online Egocentric Action Recognition into the wildCode1
3D CNNs with Adaptive Temporal Feature ResolutionsCode1
Full-Body Articulated Human-Object InteractionCode1
CAST: Cross-Attention in Space and Time for Video Action RecognitionCode1
CDFSL-V: Cross-Domain Few-Shot Learning for VideosCode1
Challenges in Video-Based Infant Action Recognition: A Critical Examination of the State of the ArtCode1
CIDEr: Consensus-based Image Description EvaluationCode1
Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action RecognitionCode1
CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action RecognitionCode1
CLIP-guided Prototype Modulating for Few-shot Action RecognitionCode1
ARBEE: Towards Automated Recognition of Bodily Expression of Emotion In the WildCode1
Show:102550
← PrevPage 4 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
2OmniVec3-fold Accuracy99.6—Unverified
3VideoMAE V2-g3-fold Accuracy99.6—Unverified
4OmniVec23-fold Accuracy99.6—Unverified
5BIKE3-fold Accuracy98.8—Unverified
6SMART3-fold Accuracy98.64—Unverified
7ZeroI2V ViT-L/143-fold Accuracy98.6—Unverified
8PERF-Net (multi-distilled S3D)3-fold Accuracy98.6—Unverified
9OmniSource (SlowOnly-8x8-R101-RGB + I3D-Flow)3-fold Accuracy98.6—Unverified
10Text4Vis3-fold Accuracy98.2—Unverified