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 351–400 of 2759 papers

TitleStatusHype
D^2ST-Adapter: Disentangled-and-Deformable Spatio-Temporal Adapter for Few-shot Action RecognitionCode1
AutoLabel: CLIP-based framework for Open-set Video Domain AdaptationCode1
CAST: Cross-Attention in Space and Time for Video Action RecognitionCode1
Keeping Your Eye on the Ball: Trajectory Attention in Video TransformersCode1
CAKES: Channel-wise Automatic KErnel Shrinking for Efficient 3D NetworksCode1
AutoVideo: An Automated Video Action Recognition SystemCode1
AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual ActionsCode1
CZU-MHAD: A multimodal dataset for human action recognition utilizing a depth camera and 10 wearable inertial sensorsCode1
DailyDVS-200: A Comprehensive Benchmark Dataset for Event-Based Action RecognitionCode1
Learning Discriminative Representations for Skeleton Based Action RecognitionCode1
AViD Dataset: Anonymized Videos from Diverse CountriesCode1
Learning from Temporal Gradient for Semi-supervised Action RecognitionCode1
ViNet: Pushing the limits of Visual Modality for Audio-Visual Saliency PredictionCode1
Learning Self-Similarity in Space and Time as a Generalized Motion for Action RecognitionCode1
Decoupling GCN with DropGraph Module for Skeleton-Based Action RecognitionCode1
Counterfactual Debiasing Inference for Compositional Action RecognitionCode1
Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical AggregationCode1
BABEL: Bodies, Action and Behavior with English LabelsCode1
Cross-Architecture Self-supervised Video Representation LearningCode1
Anonymization for Skeleton Action RecognitionCode1
Contrastive Learning from Spatio-Temporal Mixed Skeleton Sequences for Self-Supervised Skeleton-Based Action RecognitionCode1
Leveraging Spatio-Temporal Dependency for Skeleton-Based Action RecognitionCode1
Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action RecognitionCode1
Lifelong Graph LearningCode1
ACTION-Net: Multipath Excitation for Action RecognitionCode1
Location-aware Graph Convolutional Networks for Video Question AnsweringCode1
Look More but Care Less in Video RecognitionCode1
BASAR:Black-box Attack on Skeletal Action RecognitionCode1
M^2DAR: Multi-View Multi-Scale Driver Action Recognition with Vision TransformerCode1
Make Skeleton-based Action Recognition Model Smaller, Faster and BetterCode1
ConvNet Architecture Search for Spatiotemporal Feature LearningCode1
MAR: Masked Autoencoders for Efficient Action RecognitionCode1
3D CNNs with Adaptive Temporal Feature ResolutionsCode1
Benchmarking Micro-action Recognition: Dataset, Methods, and ApplicationsCode1
CIAGAN: Conditional Identity Anonymization Generative Adversarial NetworksCode1
CT-Net: Channel Tensorization Network for Video ClassificationCode1
MGSampler: An Explainable Sampling Strategy for Video Action RecognitionCode1
BEVT: BERT Pretraining of Video TransformersCode1
Mitigating Representation Bias in Action Recognition: Algorithms and BenchmarksCode1
MM-Fi: Multi-Modal Non-Intrusive 4D Human Dataset for Versatile Wireless SensingCode1
Challenges in Video-Based Infant Action Recognition: A Critical Examination of the State of the ArtCode1
Deep Analysis of CNN-based Spatio-temporal Representations for Action RecognitionCode1
Motion Representation Using Residual Frames with 3D CNNCode1
MotionSqueeze: Neural Motion Feature Learning for Video UnderstandingCode1
MPTSNet: Integrating Multiscale Periodic Local Patterns and Global Dependencies for Multivariate Time Series ClassificationCode1
MS^2L: Multi-Task Self-Supervised Learning for Skeleton Based Action RecognitionCode1
Full-Body Articulated Human-Object InteractionCode1
Actor-agnostic Multi-label Action Recognition with Multi-modal QueryCode1
Multi-Modality Co-Learning for Efficient Skeleton-based Action RecognitionCode1
Conquering the cnn over-parameterization dilemma: A volterra filtering approach for action recognitionCode1
Show:102550
← PrevPage 8 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