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 76–100 of 1322 papers

TitleStatusHype
BASAR:Black-box Attack on Skeletal Action RecognitionCode1
Action-slot: Visual Action-centric Representations for Multi-label Atomic Activity Recognition in Traffic ScenesCode1
Efficient Two-Stream Network for Violence Detection Using Separable Convolutional LSTMCode1
IMUGPT 2.0: Language-Based Cross Modality Transfer for Sensor-Based Human Activity RecognitionCode1
A Federated Learning Aggregation Algorithm for Pervasive Computing: Evaluation and ComparisonCode1
Interpretable Deep Learning for the Remote Characterisation of Ambulation in Multiple Sclerosis using SmartphonesCode1
Knowledge Mining with Scene Text for Fine-Grained RecognitionCode1
Bridge-Prompt: Towards Ordinal Action Understanding in Instructional VideosCode1
CALDA: Improving Multi-Source Time Series Domain Adaptation with Contrastive Adversarial LearningCode1
Learning Generalizable Physiological Representations from Large-scale Wearable DataCode1
Challenges in Multi-centric Generalization: Phase and Step Recognition in Roux-en-Y Gastric Bypass SurgeryCode1
Exploring Contrastive Learning in Human Activity Recognition for HealthcareCode1
Comparing Self-Supervised Learning Techniques for Wearable Human Activity RecognitionCode1
COMODO: Cross-Modal Video-to-IMU Distillation for Efficient Egocentric Human Activity RecognitionCode1
Meta-HAR: Federated Representation Learning for Human Activity RecognitionCode1
COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only ModalityCode1
MOMA-LRG: Language-Refined Graphs for Multi-Object Multi-Actor Activity ParsingCode1
Contrastive Learning with Cross-Modal Knowledge Mining for Multimodal Human Activity RecognitionCode1
Multimodal Transformer for Nursing Activity RecognitionCode1
Hard No-Box Adversarial Attack on Skeleton-Based Human Action Recognition with Skeleton-Motion-Informed GradientCode1
DATTA: Domain-Adversarial Test-Time Adaptation for Cross-Domain WiFi-Based Human Activity RecognitionCode1
IMU2CLIP: Multimodal Contrastive Learning for IMU Motion Sensors from Egocentric Videos and TextCode1
DANA: Dimension-Adaptive Neural Architecture for Multivariate Sensor DataCode1
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
Show:102550
← PrevPage 4 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