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 51–75 of 1322 papers

TitleStatusHype
MOMA-LRG: Language-Refined Graphs for Multi-Object Multi-Actor Activity ParsingCode1
SWL-Adapt: An Unsupervised Domain Adaptation Model with Sample Weight Learning for Cross-User Wearable Human Activity RecognitionCode1
Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box AttackCode1
Wearable-based Human Activity Recognition with Spatio-Temporal Spiking Neural NetworksCode1
IMU2CLIP: Multimodal Contrastive Learning for IMU Motion Sensors from Egocentric Videos and TextCode1
Temporal Feature Alignment in Contrastive Self-Supervised Learning for Human Activity RecognitionCode1
Lightweight Transformers for Human Activity Recognition on Mobile DevicesCode1
SFusion: Self-attention based N-to-One Multimodal Fusion BlockCode1
Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and ApplicationsCode1
Self-supervised Learning for Human Activity Recognition Using 700,000 Person-days of Wearable DataCode1
Contrastive Learning with Cross-Modal Knowledge Mining for Multimodal Human Activity RecognitionCode1
CholecTriplet2021: A benchmark challenge for surgical action triplet recognitionCode1
Multimodal Transformer for Nursing Activity RecognitionCode1
SPAct: Self-supervised Privacy Preservation for Action RecognitionCode1
Audio-Adaptive Activity Recognition Across Video DomainsCode1
Knowledge Mining with Scene Text for Fine-Grained RecognitionCode1
Bridge-Prompt: Towards Ordinal Action Understanding in Instructional VideosCode1
SemiPFL: Personalized Semi-Supervised Federated Learning Framework for Edge IntelligenceCode1
Panoramic Human Activity RecognitionCode1
HAR-GCNN: Deep Graph CNNs for Human Activity Recognition From Highly Unlabeled Mobile Sensor DataCode1
TransDARC: Transformer-based Driver Activity Recognition with Latent Space Feature CalibrationCode1
Wearable Sensor-Based Human Activity Recognition with Transformer ModelCode1
Learning Disentangled Behaviour Patterns for Wearable-based Human Activity RecognitionCode1
What Makes Good Contrastive Learning on Small-Scale Wearable-based Tasks?Code1
COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only ModalityCode1
Show:102550
← PrevPage 3 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