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 751–800 of 2759 papers

TitleStatusHype
MARS: Motion-Augmented RGB Stream for Action RecognitionCode0
Mamba Fusion: Learning Actions Through QuestioningCode0
Dynamic Normalization and Relay for Video Action RecognitionCode0
ADG-Pose: Automated Dataset Generation for Real-World Human Pose EstimationCode0
Mask and Compress: Efficient Skeleton-based Action Recognition in Continual LearningCode0
AutoGCN -- Towards Generic Human Activity Recognition with Neural Architecture SearchCode0
MFAS: Multimodal Fusion Architecture SearchCode0
More Is Less: Learning Efficient Video Representations by Big-Little Network and Depthwise Temporal AggregationCode0
Multi-view Distillation based on Multi-modal Fusion for Few-shot Action Recognition(CLIP-M^2DF)Code0
LSTA: Long Short-Term Attention for Egocentric Action RecognitionCode0
LSTA-Net: Long short-term Spatio-Temporal Aggregation Network for Skeleton-based Action RecognitionCode0
Bayesian Hierarchical Dynamic Model for Human Action RecognitionCode0
Low-light Environment Neural SurveillanceCode0
LSFB-CONT and LSFB-ISOL: Two New Datasets for Vision-Based Sign Language RecognitionCode0
Long-Term Feature Banks for Detailed Video UnderstandingCode0
ECO: Efficient Convolutional Network for Online Video UnderstandingCode0
Long-term Temporal Convolutions for Action RecognitionCode0
LoCATe-GAT: Modeling Multi-Scale Local Context and Action Relationships for Zero-Shot Action RecognitionCode0
Discriminating Spatial and Temporal Relevance in Deep Taylor Decompositions for Explainable Activity RecognitionCode0
Lightweight Recurrent Cross-modal Encoder for Video Question AnsweringCode0
Let's Dance: Learning From Online Dance VideosCode0
Local Spherical Harmonics Improve Skeleton-Based Hand Action RecognitionCode0
Audio-Visual Scene Analysis with Self-Supervised Multisensory FeaturesCode0
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action RecognitionCode0
Learning Video Representations from Correspondence ProposalsCode0
Learning Visual Actions Using Multiple Verb-Only LabelsCode0
Audio-Visual Model Distillation Using Acoustic ImagesCode0
Learning To Score Olympic EventsCode0
Efficient Human Vision Inspired Action Recognition using Adaptive Spatiotemporal SamplingCode0
DetReIDX: A Stress-Test Dataset for Real-World UAV-Based Person RecognitionCode0
Learning to Estimate Pose by Watching VideosCode0
Learning with privileged information via adversarial discriminative modality distillationCode0
Learning Spatio-Temporal Representation with Local and Global DiffusionCode0
Learning Spatio-Temporal Features with 3D Residual Networks for Action RecognitionCode0
Detecting the Starting Frame of Actions in VideoCode0
Detecting Object States vs Detecting Objects: A New Dataset and a Quantitative Experimental StudyCode0
Efficient Transfer Learning for Video-language Foundation ModelsCode0
Learning Skeletal Graph Neural Networks for Hard 3D Pose EstimationCode0
Action Recognition based on Cross-Situational Action-object StatisticsCode0
Describing Videos by Exploiting Temporal StructureCode0
Learn to cycle: Time-consistent feature discovery for action recognitionCode0
Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural SearchingCode0
Learning Human Action Recognition Representations Without Real HumansCode0
On Modality Bias Recognition and ReductionCode0
Learning from Video and Text via Large-Scale Discriminative ClusteringCode0
Egocentric RGB+Depth Action Recognition in Industry-Like SettingsCode0
Attentive Semantic Video Generation using CaptionsCode0
Beyond the Self: Using Grounded Affordances to Interpret and Describe Others' ActionsCode0
Learning Gating ConvNet for Two-Stream based Methods in Action RecognitionCode0
Learning long-term dependencies for action recognition with a biologically-inspired deep networkCode0
Show:102550
← PrevPage 16 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