SOTAVerified

Activity Recognition

Human Activity Recognition is the problem of identifying events performed by humans given a video input. It is formulated as a binary (or multiclass) classification problem of outputting activity class labels. Activity Recognition is an important problem with many societal applications including smart surveillance, video search/retrieval, intelligent robots, and other monitoring systems.

Source: Learning Latent Sub-events in Activity Videos Using Temporal Attention Filters

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 26–50 of 1322 papers

TitleStatusHype
Multi-stage Learning for Radar Pulse Activity SegmentationCode1
Online Semi-Supervised Learning of Composite Event Rules by Combining Structure and Mass-Based Predicate SimilarityCode1
Navigating Open Set Scenarios for Skeleton-based Action RecognitionCode1
Action-slot: Visual Action-centric Representations for Multi-label Atomic Activity Recognition in Traffic ScenesCode1
Temporal Action Localization for Inertial-based Human Activity RecognitionCode1
Quantized Distillation: Optimizing Driver Activity Recognition Models for Resource-Constrained EnvironmentsCode1
Optimization-Free Test-Time Adaptation for Cross-Person Activity RecognitionCode1
Finding Order in Chaos: A Novel Data Augmentation Method for Time Series in Contrastive LearningCode1
Human Activity Segmentation Challenge @ ECML/PKDD’23Code1
Hard No-Box Adversarial Attack on Skeleton-Based Human Action Recognition with Skeleton-Motion-Informed GradientCode1
milliFlow: Scene Flow Estimation on mmWave Radar Point Cloud for Human Motion SensingCode1
Vision-Language Models can Identify Distracted Driver Behavior from Naturalistic VideosCode1
MultiWave: Multiresolution Deep Architectures through Wavelet Decomposition for Multivariate Time Series PredictionCode1
TS-MoCo: Time-Series Momentum Contrast for Self-Supervised Physiological Representation LearningCode1
Human skeletons and change detection for efficient violence detection in surveillance videosCode1
Exploring Few-Shot Adaptation for Activity Recognition on Diverse DomainsCode1
Generating Virtual On-body Accelerometer Data from Virtual Textual Descriptions for Human Activity RecognitionCode1
Time Series Segmentation Applied to a New Data Set for Mobile Sensing of Human ActivitiesCode1
Multimodal video and IMU kinematic dataset on daily life activities using affordable devices (VIDIMU)Code1
Dual-path Adaptation from Image to Video TransformersCode1
Towards Activated Muscle Group Estimation in the WildCode1
Deep Learning for Time Series Classification and Extrinsic Regression: A Current SurveyCode1
LaMPP: Language Models as Probabilistic Priors for Perception and ActionCode1
Towards Continual Egocentric Activity Recognition: A Multi-modal Egocentric Activity Dataset for Continual LearningCode1
Self-Supervised PPG Representation Learning Shows High Inter-Subject VariabilityCode1
Show:102550
← PrevPage 2 of 53Next →
All datasetsRWF-2000Stanford40First-Person Hand Action BenchmarkSelf-stimulatory Behavior Dataset

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Structured Keypoint PoolingAccuracy93.4—Unverified
2Semi-Supervised Hard Attention (SSHA); pretrained on Deepmind Kinetics datasetAccuracy90.4—Unverified
3Human Skeletons + Change DetectionAccuracy90.25—Unverified
4Separable Convolutional LSTMAccuracy89.75—Unverified
5SPIL ConvolutionAccuracy89.3—Unverified
6Flow Gated NetworkAccuracy87.25—Unverified
#ModelMetricClaimedVerifiedStatus
1FocusCLIPTop-3 Accuracy (%)10.47—Unverified
2CLIPTop-3 Accuracy (%)6.49—Unverified
#ModelMetricClaimedVerifiedStatus
1Boutaleb et al.1:1 Accuracy97.91—Unverified
#ModelMetricClaimedVerifiedStatus
1all-landmark-modelActivity Recognition0.76—Unverified