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 1226–1250 of 1322 papers

TitleStatusHype
Eidetic 3D LSTM: A Model for Video Prediction and BeyondCode0
A Matter of Annotation: An Empirical Study on In Situ and Self-Recall Activity Annotations from Wearable SensorsCode0
Hybrid CNN-Dilated Self-attention Model Using Inertial and Body-Area Electrostatic Sensing for Gym Workout Recognition, Counting, and User AuthentificationCode0
Transfer Learning for Activity Recognition in Mobile HealthCode0
Multimodal Explanations: Justifying Decisions and Pointing to the EvidenceCode0
Multimodal Generation of Novel Action Appearances for Synthetic-to-Real Recognition of Activities of Daily LivingCode0
Im2Flow: Motion Hallucination from Static Images for Action RecognitionCode0
PriMask: Cascadable and Collusion-Resilient Data Masking for Mobile Cloud InferenceCode0
Big-Little Adaptive Neural Networks on Low-Power Near-Subthreshold ProcessorsCode0
Decomposing and Fusing Intra- and Inter-Sensor Spatio-Temporal Signal for Multi-Sensor Wearable Human Activity RecognitionCode0
Temporal Relational Reasoning in VideosCode0
AssembleNet++: Assembling Modality Representations via Attention ConnectionsCode0
Easy Ensemble: Simple Deep Ensemble Learning for Sensor-Based Human Activity RecognitionCode0
ASM2TV: An Adaptive Semi-Supervised Multi-Task Multi-View Learning Framework for Human Activity RecognitionCode0
Improving state estimation through projection post-processing for activity recognition with application to footballCode0
WiDistill: Distilling Large-scale Wi-Fi Datasets with Trajectory MatchingCode0
DYSAN: Dynamically sanitizing motion sensor data against sensitive inferences through adversarial networksCode0
Dynamic Vision Sensors for Human Activity RecognitionCode0
Uncertainty-aware Bridge based Mobile-Former Network for Event-based Pattern RecognitionCode0
ProActive: Self-Attentive Temporal Point Process Flows for Activity SequencesCode0
Incremental Learning of Event Definitions with Inductive Logic ProgrammingCode0
Probabilistic Event Calculus for Event RecognitionCode0
A Probabilistic Logic Programming Event CalculusCode0
ActNetFormer: Transformer-ResNet Hybrid Method for Semi-Supervised Action Recognition in VideosCode0
DECOMPL: Decompositional Learning with Attention Pooling for Group Activity Recognition from a Single Volleyball ImageCode0
Show:102550
← PrevPage 50 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