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 551–600 of 2759 papers

TitleStatusHype
ConvNet Architecture Search for Spatiotemporal Feature LearningCode1
Predictively Encoded Graph Convolutional Network for Noise-Robust Skeleton-based Action RecognitionCode1
Privacy-Preserving Action Recognition via Motion Difference QuantizationCode1
Privacy-Preserving Deep Action Recognition: An Adversarial Learning Framework and A New DatasetCode1
Rethinking Motion Representation: Residual Frames with 3D ConvNets for Better Action RecognitionCode1
Approximated Bilinear Modules for Temporal ModelingCode1
Actions as Moving PointsCode1
Prototypical Calibrating Ambiguous Samples for Micro-Action RecognitionCode1
ARBEE: Towards Automated Recognition of Bodily Expression of Emotion In the WildCode1
EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal TokensCode1
Skeleton-based Action Recognition via Temporal-Channel AggregationCode1
Quo Vadis, Skeleton Action Recognition ?Code1
Temporally Coherent Embeddings for Self-Supervised Video Representation LearningCode1
Counterfactual Debiasing Inference for Compositional Action RecognitionCode1
EgoNCE++: Do Egocentric Video-Language Models Really Understand Hand-Object Interactions?Code1
EgoExOR: An Ego-Exo-Centric Operating Room Dataset for Surgical Activity UnderstandingCode1
Action-slot: Visual Action-centric Representations for Multi-label Atomic Activity Recognition in Traffic ScenesCode1
Elaborative Rehearsal for Zero-shot Action RecognitionCode1
Cross-Architecture Self-supervised Video Representation LearningCode1
EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the BackboneCode1
Encoding Surgical Videos as Latent Spatiotemporal Graphs for Object and Anatomy-Driven ReasoningCode1
Region-based Non-local Operation for Video ClassificationCode1
End-to-End Streaming Video Temporal Action Segmentation with Reinforce LearningCode1
End-to-End Learning of Visual Representations from Uncurated Instructional VideosCode1
Action Transformer: A Self-Attention Model for Short-Time Pose-Based Human Action RecognitionCode1
Enlarging Instance-specific and Class-specific Information for Open-set Action RecognitionCode1
ARID: A New Dataset for Recognizing Action in the DarkCode1
Multi-Granularity Hand Action DetectionCode1
Multimodal Visual Concept Learning with Weakly Supervised TechniquesCode0
Multi-Moments in Time: Learning and Interpreting Models for Multi-Action Video UnderstandingCode0
Multimodal Task-Driven Dictionary Learning for Image ClassificationCode0
Multiple Human Tracking using Multi-Cues including Primitive Action FeaturesCode0
A New Split for Evaluating True Zero-Shot Action RecognitionCode0
Comparative Analysis: Violence Recognition from Videos using Transfer LearningCode0
Comparative Analysis of CNN-based Spatiotemporal Reasoning in VideosCode0
Multi-scale spatial–temporal convolutional neural network for skeleton-based action recognitionCode0
Multi class activity classification in videos using Motion History Image generationCode0
Multi-Level Feature Distillation of Joint Teachers Trained on Distinct Image DatasetsCode0
Are Spatial-Temporal Graph Convolution Networks for Human Action Recognition Over-Parameterized?Code0
Multi-attention Networks for Temporal Localization of Video-level LabelsCode0
Multi-level Second-order Few-shot LearningCode0
Action Recognition Using Volumetric Motion RepresentationsCode0
Multimodal Attack Detection for Action Recognition ModelsCode0
Collaborative Spatiotemporal Feature Learning for Video Action RecognitionCode0
Collaborative Spatio-temporal Feature Learning for Video Action RecognitionCode0
MorphMLP: An Efficient MLP-Like Backbone for Spatial-Temporal Representation LearningCode0
Action Recognition using Visual AttentionCode0
MOFO: MOtion FOcused Self-Supervision for Video UnderstandingCode0
Moments in Time Dataset: one million videos for event understandingCode0
MaCLR: Motion-aware Contrastive Learning of Representations for VideosCode0
Show:102550
← PrevPage 12 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