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 1301–1350 of 2759 papers

TitleStatusHype
Joint Visual-Temporal Embedding for Unsupervised Learning of Actions in Untrimmed Sequences—0
JOLO-GCN: Mining Joint-Centered Light-Weight Information for Skeleton-Based Action Recognition—0
IIP-Transformer: Intra-Inter-Part Transformer for Skeleton-Based Action Recognition—0
JUMPS: Joints Upsampling Method for Pose Sequences—0
Activity Recognition on a Large Scale in Short Videos - Moments in Time Dataset—0
IF-TTN: Information Fused Temporal Transformation Network for Video Action Recognition—0
Just One Moment: Structural Vulnerability of Deep Action Recognition against One Frame Attack—0
KAN-HyperpointNet for Point Cloud Sequence-Based 3D Human Action Recognition—0
Identity-free Artificial Emotional Intelligence via Micro-Gesture Understanding—0
Kernelized Covariance for Action Recognition—0
Dark Transformer: A Video Transformer for Action Recognition in the Dark—0
Learning Video-Conditioned Policies for Unseen Manipulation Tasks—0
Identifying Auxiliary or Adversarial Tasks Using Necessary Condition Analysis for Adversarial Multi-task Video Understanding—0
Knowing What, Where and When to Look: Efficient Video Action Modeling with Attention—0
Knowledge Distillation for Multimodal Egocentric Action Recognition Robust to Missing Modalities—0
Knowledge Fusion Transformers for Video Action Recognition—0
DARE: AI-based Diver Action Recognition System using Multi-Channel CNNs for AUV Supervision—0
Knowledge Integration Networks for Action Recognition—0
Learning to Score Sign Language with Two-stage Method—0
Know your sensORs -- A Modality Study For Surgical Action Classification—0
Koala: Key frame-conditioned long video-LLM—0
KPCA Spatio-temporal trajectory point cloud classifier for recognizing human actions in a CBVR system—0
iCub! Do you recognize what I am doing?: multimodal human action recognition on multisensory-enabled iCub robot—0
A Spectral Nonlocal Block for Neural Networks—0
Label Efficient Learning of Transferable Representations acrosss Domains and Tasks—0
Label Efficient Learning of Transferable Representations across Domains and Tasks—0
Learning to Sort Image Sequences via Accumulated Temporal Differences—0
3D ResNet with Ranking Loss Function for Abnormal Activity Detection in Videos—0
Language as the Medium: Multimodal Video Classification through text only—0
Language-based Action Concept Spaces Improve Video Self-Supervised Learning—0
Hypergraph-based Multi-View Action Recognition using Event Cameras—0
Learning to Recognize Actions on Objects in Egocentric Video with Attention Dictionaries—0
Depth2Action: Exploring Embedded Depth for Large-Scale Action Recognition—0
LS-HAR: Language Supervised Human Action Recognition with Salient Fusion, Construction Sites as a Use-Case—0
Learning Transferable Self-attentive Representations for Action Recognition in Untrimmed Videos with Weak Supervision—0
Large Language Models for Video Surveillance Applications—0
Depth-Aware Action Recognition: Pose-Motion Encoding through Temporal Heatmaps—0
Learning Video Representations by Transforming Time—0
Hyper-Fisher Vectors for Action Recognition—0
HyLiFormer: Hyperbolic Linear Attention for Skeleton-based Human Action Recognition—0
Lattice Long Short-Term Memory for Human Action Recognition—0
LAVA: Language Audio Vision Alignment for Contrastive Video Pre-Training—0
Cycle-Contrast for Self-Supervised Video Representation Learning—0
ASL Recognition with Metric-Learning based Lightweight Network—0
Learnable Irrelevant Modality Dropout for Multimodal Action Recognition on Modality-Specific Annotated Videos—0
Learnable Sampling 3D Convolution for Video Enhancement and Action Recognition—0
Learning a Condensed Frame for Memory-Efficient Video Class-Incremental Learning—0
Learning Actionness via Long-range Temporal Order Verification—0
Learning Action Recognition Model From Depth and Skeleton Videos—0
HumMUSS: Human Motion Understanding using State Space Models—0
Show:102550
← PrevPage 27 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