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 2001–2050 of 2759 papers

TitleStatusHype
Trimmed Action Recognition, Dense-Captioning Events in Videos, and Spatio-temporal Action Localization with Focus on ActivityNet Challenge 2019—0
Hallucinating IDT Descriptors and I3D Optical Flow Features for Action Recognition with CNNs—0
Temporal Transformer Networks: Joint Learning of Invariant and Discriminative Time WarpingCode0
Learning Spatio-Temporal Representation with Local and Global DiffusionCode0
Recognizing Manipulation Actions from State-TransformationsCode0
Privacy-Preserving Deep Action Recognition: An Adversarial Learning Framework and A New DatasetCode1
Weakly-supervised Compositional FeatureAggregation for Few-shot Recognition—0
FASTER Recurrent Networks for Efficient Video Classification—0
The role of ego vision in view-invariant action recognition—0
Video Modeling with Correlation Networks—0
Detecting the Starting Frame of Actions in VideoCode0
Risky Action Recognition in Lane Change Video Clips using Deep Spatiotemporal Networks with Segmentation Mask TransferCode1
Scaling Autoregressive Video ModelsCode1
Two-Stream Region Convolutional 3D Network for Temporal Activity Detection—0
A Hybrid RNN-HMM Approach for Weakly Supervised Temporal Action Segmentation—0
Mining YouTube - A dataset for learning fine-grained action concepts from webly supervised video dataCode0
How Much Does Audio Matter to Recognize Egocentric Object Interactions?—0
Self-Supervised Spatiotemporal Learning via Video Clip Order Prediction—0
Action4D: Online Action Recognition in the Crowd and Clutter—0
Bayesian Hierarchical Dynamic Model for Human Action RecognitionCode0
Progressive Teacher-Student Learning for Early Action Prediction—0
MARS: Motion-Augmented RGB Stream for Action RecognitionCode0
MFAS: Multimodal Fusion Architecture SearchCode0
PA3D: Pose-Action 3D Machine for Video Recognition—0
Skeleton-Based Action Recognition With Directed Graph Neural NetworksCode0
Cross Domain Model Compression by Structurally Weight Sharing—0
Collaborative Spatiotemporal Feature Learning for Video Action RecognitionCode0
3DPalsyNet: A Facial Palsy Grading and Motion Recognition Framework using Fully 3D Convolutional Neural Networks—0
AssembleNet: Searching for Multi-Stream Neural Connectivity in Video ArchitecturesCode0
What Makes Training Multi-Modal Classification Networks Hard?Code0
Rethinking Full Connectivity in Recurrent Neural Networks—0
Clustering and Recognition of Spatiotemporal Features through Interpretable Embedding of Sequence to Sequence Recurrent Neural Networks—0
Hierarchical Feature Aggregation Networks for Video Action Recognition—0
Examining Interpretable Feature Relationships in Deep Networks for Action recognition—0
Unsupervised Learning from Video with Deep Neural EmbeddingsCode0
EfficientNet: Rethinking Model Scaling for Convolutional Neural NetworksCode3
Exploring Temporal Information for Improved Video UnderstandingCode0
What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality AttentionCode1
Lightweight Network Architecture for Real-Time Action RecognitionCode1
Learning Video Representations from Correspondence ProposalsCode0
Richly Activated Graph Convolutional Network for Action Recognition with Incomplete SkeletonsCode0
Towards a Skeleton-Based Action Recognition For Realistic Scenarios—0
NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity UnderstandingCode1
Large-scale weakly-supervised pre-training for video action recognitionCode0
Human Action Recognition with Deep Temporal Pyramids—0
Egocentric Hand Track and Object-based Human Action Recognition—0
Where and when to look? Spatial-temporal attention for action recognition in videos—0
Unseen Action Recognition with Unpaired Adversarial Multimodal Learning—0
Human Action Recognition Based on Spatial-Temporal Attention—0
Memory-Augmented Temporal Dynamic Learning for Action Recognition—0
Show:102550
← PrevPage 41 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