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 801–850 of 2759 papers

TitleStatusHype
Local Spherical Harmonics Improve Skeleton-Based Hand Action RecognitionCode0
Detecting the Starting Frame of Actions in VideoCode0
Lightweight Recurrent Cross-modal Encoder for Video Question AnsweringCode0
LoCATe-GAT: Modeling Multi-Scale Local Context and Action Relationships for Zero-Shot Action RecognitionCode0
Detecting Object States vs Detecting Objects: A New Dataset and a Quantitative Experimental StudyCode0
Quantification of Occlusion Handling Capability of a 3D Human Pose Estimation FrameworkCode0
Describing Videos by Exploiting Temporal StructureCode0
Action Recognition Based on Optimal Joint Selection and Discriminative Depth DescriptorCode0
Learning Visual Actions Using Multiple Verb-Only LabelsCode0
Learning Video Representations from Correspondence ProposalsCode0
Attentive Semantic Video Generation using CaptionsCode0
Learning with privileged information via adversarial discriminative modality distillationCode0
Learning to Estimate Pose by Watching VideosCode0
Learning To Score Olympic EventsCode0
Learn to cycle: Time-consistent feature discovery for action recognitionCode0
Delving Deeper into Convolutional Networks for Learning Video RepresentationsCode0
Deja Vu: Motion Prediction in Static ImagesCode0
Recognizing Manipulation Actions from State-TransformationsCode0
DejaVid: Encoder-Agnostic Learned Temporal Matching for Video ClassificationCode0
Attention Bottlenecks for Multimodal FusionCode0
Adaptive frame selection in two dimensional convolutional neural network action recognitionCode0
Learning Skeletal Graph Neural Networks for Hard 3D Pose EstimationCode0
Learning Spatio-Temporal Features with 3D Residual Networks for Action RecognitionCode0
End-to-End Learning of Motion Representation for Video UnderstandingCode0
Learning Spatio-Temporal Representation with Local and Global DiffusionCode0
Adaptive and Iteratively Improving Recurrent Lateral ConnectionsCode0
Learning Mutual Excitation for Hand-to-Hand and Human-to-Human Interaction RecognitionCode0
End-to-end Video-level Representation Learning for Action RecognitionCode0
Learning long-term dependencies for action recognition with a biologically-inspired deep networkCode0
Attentional Pooling for Action RecognitionCode0
Long-Range Feedback Spiking Network Captures Dynamic and Static Representations of the Visual Cortex under Movie StimuliCode0
Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural SearchingCode0
Learning from Video and Text via Large-Scale Discriminative ClusteringCode0
Enhancing human action recognition with GAN-based data augmentationCode0
Learning from Temporal Spatial Cubism for Cross-Dataset Skeleton-based Action RecognitionCode0
Learning Gating ConvNet for Two-Stream based Methods in Action RecognitionCode0
Learning Human Action Recognition Representations Without Real HumansCode0
Deep Point-wise Prediction for Action Temporal ProposalCode0
Attack on Scene Flow using Point CloudsCode0
Attack-Augmentation Mixing-Contrastive Skeletal Representation LearningCode0
Ensemble Modeling for Multimodal Visual Action RecognitionCode0
RHM: Robot House Multi-view Human Activity Recognition DatasetCode0
Large-scale weakly-supervised pre-training for video action recognitionCode0
Learning Actor Relation Graphs for Group Activity RecognitionCode0
Large-scale Robustness Analysis of Video Action Recognition ModelsCode0
EV-Action: Electromyography-Vision Multi-Modal Action DatasetCode0
Learning deep representations for video-based intake gesture detectionCode0
Let's Dance: Learning From Online Dance VideosCode0
Joint-Partition Group Attention for skeleton-based action recognitionCode0
Joint Mixing Data Augmentation for Skeleton-based Action RecognitionCode0
Show:102550
← PrevPage 17 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