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 2151–2200 of 2759 papers

TitleStatusHype
Mutual Context Network for Jointly Estimating Egocentric Gaze and Actions—0
MV2MAE: Multi-View Video Masked Autoencoders—0
MV-GMN: State Space Model for Multi-View Action Recognition—0
MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Captures—0
MVP-Shot: Multi-Velocity Progressive-Alignment Framework for Few-Shot Action Recognition—0
MVSA-Net: Multi-View State-Action Recognition for Robust and Deployable Trajectory Generation—0
NAS-TC: Neural Architecture Search on Temporal Convolutions for Complex Action Recognition—0
Natural Language Descriptions for Human Activities in Video Streams—0
Neural Graph Matching Networks for Fewshot 3D Action Recognition—0
Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognition—0
No-audio speaking status detection in crowded settings via visual pose-based filtering and wearable acceleration—0
Noise-Tolerant Learning for Audio-Visual Action Recognition—0
Non-Linear Temporal Subspace Representations for Activity Recognition—0
Non-local Recurrent Neural Memory for Supervised Sequence Modeling—0
Normalized Human Pose Features for Human Action Video Alignment—0
Nrityantar: Pose oblivious Indian classical dance sequence classification system—0
NSNet: Non-saliency Suppression Sampler for Efficient Video Recognition—0
Nuisance-Label Supervision: Robustness Improvement by Free Labels—0
NUTA: Non-uniform Temporal Aggregation for Action Recognition—0
Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wild—0
Object-ABN: Learning to Generate Sharp Attention Maps for Action Recognition—0
Object Activity Scene Description, Construction and Recognition—0
Object-based (yet Class-agnostic) Video Domain Adaptation—0
ObjectMix: Data Augmentation by Copy-Pasting Objects in Videos for Action Recognition—0
Object Properties Inferring from and Transfer for Human Interaction Motions—0
Object-Relation Reasoning Graph for Action Recognition—0
ODN: Opening the Deep Network for Open-set Action Recognition—0
OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning—0
OmniVL:One Foundation Model for Image-Language and Video-Language Tasks—0
On Dropping Clusters to Regularize Graph Convolutional Neural Networks—0
One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matching—0
Online Action Recognition based on Incremental Learning of Weighted Covariance Descriptors—0
Online hand gesture recognition using Continual Graph Transformers—0
Online Learnable Keyframe Extraction in Videos and its Application with Semantic Word Vector in Action Recognition—0
Online pre-training with long-form videos—0
On Negative Sampling for Audio-Visual Contrastive Learning from Movies—0
On the Impact of Lossy Image and Video Compression on the Performance of Deep Convolutional Neural Network Architectures—0
On the Importance of Spatial Relations for Few-shot Action Recognition—0
On the Importance of Video Action Recognition for Visual Lipreading—0
On the Integration of Optical Flow and Action Recognition—0
Performance Evaluation of Action Recognition Models on Low Quality Videos—0
On the Role of Event Boundaries in Egocentric Activity Recognition from Photostreams—0
Open Set Action Recognition via Multi-Label Evidential Learning—0
Optical flow and scene flow estimation: A survey—0
Optimizing Human Pose Estimation Through Focused Human and Joint Regions—0
Optimizing ViViT Training: Time and Memory Reduction for Action Recognition—0
Order-aware Convolutional Pooling for Video Based Action Recognition—0
Ordered Pooling of Optical Flow Sequences for Action Recognition—0
Order-Preserving Wasserstein Discriminant Analysis—0
Origami: A 803 GOp/s/W Convolutional Network Accelerator—0
Show:102550
← PrevPage 44 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