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 1701–1750 of 2759 papers

TitleStatusHype
FBK-HUPBA Submission to the EPIC-Kitchens Action Recognition 2020 Challenge—0
Rescaling Egocentric VisionCode1
Motion Representation Using Residual Frames with 3D CNNCode1
Sequential Feature Filtering Classifier—0
Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual RecognitionCode1
Video Playback Rate Perception for Self-supervisedSpatio-Temporal Representation LearningCode1
A Real-time Action Representation with Temporal Encoding and Deep Compression—0
Learn to cycle: Time-consistent feature discovery for action recognitionCode0
Actor-Context-Actor Relation Network for Spatio-Temporal Action LocalizationCode1
3DFCNN: Real-Time Action Recognition using 3D Deep Neural Networks with Raw Depth Information—0
Exploiting the ConvLSTM: Human Action Recognition using Raw Depth Video-Based Recurrent Neural Networks—0
DTG-Net: Differentiated Teachers Guided Self-Supervised Video Action Recognition—0
Iterate & Cluster: Iterative Semi-Supervised Action RecognitionCode1
Disentangled Non-Local Neural NetworksCode1
Interferometric Graph Transform: a Deep Unsupervised Graph RepresentationCode1
PNL: Efficient Long-Range Dependencies Extraction with Pyramid Non-Local Module for Action Recognition—0
Action Recognition with Deep Multiple Aggregation Networks—0
Deep hierarchical pooling design for cross-granularity action recognition—0
ARID: A New Dataset for Recognizing Action in the DarkCode1
WOAD: Weakly Supervised Online Action Detection in Untrimmed Videos—0
Action Genome: Actions As Compositions of Spatio-Temporal Scene Graphs—0
Skeleton-Based Action Recognition With Shift Graph Convolutional NetworkCode1
Attention-Based Context Aware Reasoning for Situation RecognitionCode1
Regularization on Spatio-Temporally Smoothed Feature for Action Recognition—0
Context Aware Graph Convolution for Skeleton-Based Action Recognition—0
Searching for Actions on the HyperboleCode1
Video Playback Rate Perception for Self-Supervised Spatio-Temporal Representation LearningCode1
Temporal Aggregate Representations for Long-Range Video UnderstandingCode1
In the Eye of the Beholder: Gaze and Actions in First Person Video—0
Complex Sequential Understanding through the Awareness of Spatial and Temporal ConceptsCode1
Unifying Few- and Zero-Shot Egocentric Action Recognition—0
Invariant 3D Shape Recognition using Predictive Modular Neural Networks—0
SpotFast Networks with Memory Augmented Lateral Transformers for LipreadingCode0
Intra- and Inter-Action Understanding via Temporal Action Parsing—0
Discriminative Dictionary Design for Action Classification in Still Images and Videos—0
CIAGAN: Conditional Identity Anonymization Generative Adversarial NetworksCode1
Retrieving and Highlighting Action with Spatiotemporal Reference—0
Graph Partitioning and Graph Neural Network based Hierarchical Graph Matching for Graph Similarity Computation—0
Towards Understanding the Adversarial Vulnerability of Skeleton-based Action Recognition—0
CoSimGNN: Towards Large-scale Graph Similarity Computation—0
TAM: Temporal Adaptive Module for Video RecognitionCode1
Project RISE: Recognizing Industrial Smoke EmissionsCode1
3DV: 3D Dynamic Voxel for Action Recognition in Depth VideoCode1
Human in Events: A Large-Scale Benchmark for Human-centric Video Analysis in Complex Events—0
Exploiting Inter-Frame Regional Correlation for Efficient Action Recognition—0
Rolling-Unrolling LSTMs for Action Anticipation from First-Person VideoCode1
Streaming Object Detection for 3-D Point Clouds—0
A Semantics-Guided Graph Convolutional Network for Skeleton-Based Action Recognition—0
HAPRec: Hybrid Activity and Plan Recognizer—0
Inferring Temporal Compositions of Actions Using Probabilistic Automata—0
Show:102550
← PrevPage 35 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