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
Compressing Recurrent Neural Networks with Tensor Ring for Action RecognitionCode1
Towards High Resolution Video Generation with Progressive Growing of Sliced Wasserstein GANsCode1
ARBEE: Towards Automated Recognition of Bodily Expression of Emotion In the WildCode1
Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot StudyCode1
Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical AggregationCode1
SoccerNet: A Scalable Dataset for Action Spotting in Soccer VideosCode1
Sparse Adversarial Perturbations for VideosCode1
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action RecognitionCode1
Multivariate LSTM-FCNs for Time Series ClassificationCode1
A Closer Look at Spatiotemporal Convolutions for Action RecognitionCode1
Learning Spatio-Temporal Representation with Pseudo-3D Residual NetworksCode1
Temporal 3D ConvNets: New Architecture and Transfer Learning for Video ClassificationCode1
Non-local Neural NetworksCode1
Grad-CAM++: Improved Visual Explanations for Deep Convolutional NetworksCode1
ConvNet Architecture Search for Spatiotemporal Feature LearningCode1
Spatiotemporal Multiplier Networks for Video Action RecognitionCode1
The "something something" video database for learning and evaluating visual common senseCode1
AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual ActionsCode1
Quo Vadis, Action Recognition? A New Model and the Kinetics DatasetCode1
Skeleton-based Action Recognition with Convolutional Neural NetworksCode1
Hidden Two-Stream Convolutional Networks for Action RecognitionCode1
Spatiotemporal Residual Networks for Video Action RecognitionCode1
YouTube-8M: A Large-Scale Video Classification BenchmarkCode1
Towards Good Practices for Very Deep Two-Stream ConvNetsCode1
Visual Semantic Role LabelingCode1
Unsupervised Learning of Video Representations using LSTMsCode1
CIDEr: Consensus-based Image Description EvaluationCode1
Large-Scale Video Classification with Convolutional Neural NetworksCode1
A Real-Time System for Egocentric Hand-Object Interaction Detection in Industrial Domains—0
EgoAdapt: Adaptive Multisensory Distillation and Policy Learning for Efficient Egocentric Perception—0
CARMA: Context-Aware Situational Grounding of Human-Robot Group Interactions by Combining Vision-Language Models with Object and Action Recognition—0
Feature Hallucination for Self-supervised Action Recognition—0
Including Semantic Information via Word Embeddings for Skeleton-based Action Recognition—0
Adapting Vision-Language Models for Evaluating World Models—0
Active Multimodal Distillation for Few-shot Action Recognition—0
An Effective End-to-End Solution for Multimodal Action Recognition—0
Time-Unified Diffusion Policy with Action Discrimination for Robotic Manipulation—0
HopaDIFF: Holistic-Partial Aware Fourier Conditioned Diffusion for Referring Human Action Segmentation in Multi-Person ScenariosCode0
ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding—0
3D Skeleton-Based Action Recognition: A Review—0
A Review on Coarse to Fine-Grained Animal Action Recognition—0
Spatio-Temporal Joint Density Driven Learning for Skeleton-Based Action RecognitionCode0
PHI: Bridging Domain Shift in Long-Term Action Quality Assessment via Progressive Hierarchical InstructionCode0
The Role of Video Generation in Enhancing Data-Limited Action Understanding—0
Temporal Consistency Constrained Transferable Adversarial Attacks with Background Mixup for Action RecognitionCode0
Leveraging Foundation Models for Multimodal Graph-Based Action Recognition—0
Egocentric Action-aware Inertial Localization in Point CloudsCode0
Are Spatial-Temporal Graph Convolution Networks for Human Action Recognition Over-Parameterized?Code0
Mission Balance: Generating Under-represented Class Samples using Video Diffusion ModelsCode0
Reinforcement Learning meets Masked Video Modeling : Trajectory-Guided Adaptive Token Selection—0
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