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 2626–2650 of 2759 papers

TitleStatusHype
Learning Representations from Audio-Visual Spatial Alignment—0
Learning Representative Temporal Features for Action Recognition—0
Learning Scene Flow With Skeleton Guidance For 3D Action Recognition—0
Learning Shape-Motion Representations from Geometric Algebra Spatio-Temporal Model for Skeleton-Based Action Recognition—0
Learning Spatiotemporal Features for Infrared Action Recognition with 3D Convolutional Neural Networks—0
Learning spatio-temporal representations with temporal squeeze pooling—0
Learning Speech Representations from Raw Audio by Joint Audiovisual Self-Supervision—0
Learning to Generalize without Bias for Open-Vocabulary Action Recognition—0
Learning to Learn from Noisy Web Videos—0
Learning to Recognize 3D Human Action from A New Skeleton-based Representation Using Deep Convolutional Neural Networks—0
Learning to Recognize Actions from Limited Training Examples Using a Recurrent Spiking Neural Model—0
Learning to Recognize Actions on Objects in Egocentric Video with Attention Dictionaries—0
Learning to Score Sign Language with Two-stage Method—0
Learning to Sort Image Sequences via Accumulated Temporal Differences—0
Learning Transferable Self-attentive Representations for Action Recognition in Untrimmed Videos with Weak Supervision—0
Learning Using Privileged Information for Zero-Shot Action Recognition—0
Learning Video-Conditioned Policies for Unseen Manipulation Tasks—0
Learning Video Representations by Transforming Time—0
Learning Video Representations from Textual Web Supervision—0
Learning Video Representations of Human Motion From Synthetic Data—0
Learning View-Disentangled Human Pose Representation by Contrastive Cross-View Mutual Information Maximization—0
Learning Visual Affordance Grounding from Demonstration Videos—0
Learning Visual Representation from Human Interactions—0
Learning without Prejudice: Avoiding Bias in Webly-Supervised Action Recognition—0
Learning zeroth class dictionary for human action recognition—0
Show:102550
← PrevPage 106 of 111Next →
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