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 2701–2750 of 2759 papers

TitleStatusHype
Manta: Enhancing Mamba for Few-Shot Action Recognition of Long Sub-Sequence—0
MAPLE: Masked Pseudo-Labeling autoEncoder for Semi-supervised Point Cloud Action Recognition—0
MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning—0
Activity Recognition on Avatar-Anonymized Datasets with Masked Differential Privacy—0
Masked Video and Body-worn IMU Autoencoder for Egocentric Action Recognition—0
Massively Parallel Video Networks—0
Matrix Manifold Neural Networks++—0
Maximizing Spatio-Temporal Entropy of Deep 3D CNNs for Efficient Video Recognition—0
Measuring Student Behavioral Engagement using Histogram of Actions—0
MECCANO: A Multimodal Egocentric Dataset for Humans Behavior Understanding in the Industrial-like Domain—0
Meet JEANIE: a Similarity Measure for 3D Skeleton Sequences via Temporal-Viewpoint Alignment—0
Memory-Augmented Temporal Dynamic Learning for Action Recognition—0
Memory Group Sampling Based Online Action Recognition Using Kinetic Skeleton Features—0
Metric-Based Few-Shot Learning for Video Action Recognition—0
MFAS: Multimodal Fusion Architecture Search—0
MiCT: Mixed 3D/2D Convolutional Tube for Human Action Recognition—0
Mimetics: Towards Understanding Human Actions Out of Context—0
Mimic The Raw Domain: Accelerating Action Recognition in the Compressed Domain—0
Miniaturized Graph Convolutional Networks with Topologically Consistent Pruning—0
Mining 3D Key-Pose-Motifs for Action Recognition—0
Mining Mid-level Features for Action Recognition Based on Effective Skeleton Representation—0
Mix Dimension in Poincaré Geometry for 3D Skeleton-based Action Recognition—0
MixTConv: Mixed Temporal Convolutional Kernels for Efficient Action Recogntion—0
MK-SGN: A Spiking Graph Convolutional Network with Multimodal Fusion and Knowledge Distillation for Skeleton-based Action Recognition—0
MLGCN: Multi-Laplacian Graph Convolutional Networks for Human Action Recognition—0
MMAct: A Large-Scale Dataset for Cross Modal Human Action Understanding—0
M&M Mix: A Multimodal Multiview Transformer Ensemble—0
MM-ViT: Multi-Modal Video Transformer for Compressed Video Action Recognition—0
Mobile Video Action Recognition—0
Modality-Collaborative Test-Time Adaptation for Action Recognition—0
Modality Compensation Network: Cross-Modal Adaptation for Action Recognition—0
Modality Mixer Exploiting Complementary Information for Multi-modal Action Recognition—0
Modality Mixer for Multi-modal Action Recognition—0
MODA: Motion-Drift Augmentation for Inertial Human Motion Analysis—0
Model-agnostic Multi-Domain Learning with Domain-Specific Adapters for Action Recognition—0
Modeling Actions through State Changes—0
Modeling Cross-view Interaction Consistency for Paired Egocentric Interaction Recognition—0
Modeling long-term interactions to enhance action recognition—0
Modeling Representation of Videos for Anomaly Detection using Deep Learning: A Review—0
Modeling Sub-Event Dynamics in First-Person Action Recognition—0
Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks—0
Modeling Video Evolution for Action Recognition—0
Modelling Spatio-Temporal Interactions for Compositional Action Recognition—0
Modelling Temporal Information Using Discrete Fourier Transform for Video Classification—0
MomentSeeker: A Task-Oriented Benchmark For Long-Video Moment Retrieval—0
MoQuad: Motion-focused Quadruple Construction for Video Contrastive Learning—0
Motion-Augmented Self-Training for Video Recognition at Smaller Scale—0
Motion-Aware Feature for Improved Video Anomaly Detection—0
Motion Feature Network: Fixed Motion Filter for Action Recognition—0
Motion Guided Attention Fusion to Recognize Interactions from Videos—0
Show:102550
← PrevPage 55 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