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 876–900 of 1322 papers

TitleStatusHype
STS Classification with Dual-stream CNN—0
Student Activity Recognition in Classroom Environments using Transfer Learning—0
Super Normal Vector for Activity Recognition Using Depth Sequences—0
Surgical Activity Recognition in Robot-Assisted Radical Prostatectomy using Deep Learning—0
SurgicalVLM-Agent: Towards an Interactive AI Co-Pilot for Pituitary Surgery—0
SWTF: Sparse Weighted Temporal Fusion for Drone-Based Activity Recognition—0
Tapestry of Time and Actions: Modeling Human Activity Sequences using Temporal Point Process Flows—0
TASKED: Transformer-based Adversarial learning for human activity recognition using wearable sensors via Self-KnowledgE Distillation—0
WiFi-TCN: Temporal Convolution for Human Interaction Recognition based on WiFi signal—0
Template co-updating in multi-modal human activity recognition systems—0
Temporal Action Segmentation with High-level Complex Activity Labels—0
Temporal DINO: A Self-supervised Video Strategy to Enhance Action Prediction—0
Temporally Consistent Dynamic Scene Graphs: An End-to-End Approach for Action Tracklet Generation—0
Temporally Robust Global Motion Compensation by Keypoint-based Congealing—0
Temporal Reasoning Graph for Activity Recognition—0
TENT: Connect Language Models with IoT Sensors for Zero-Shot Activity Recognition—0
Text me the data: Generating Ground Pressure Sequence from Textual Descriptions for HAR—0
The ACM Multimedia 2022 Computational Paralinguistics Challenge: Vocalisations, Stuttering, Activity, & Mosquitoes—0
The ActivityNet Large-Scale Activity Recognition Challenge 2018 Summary—0
The Evolution of First Person Vision Methods: A Survey—0
The Potential of Vision-Language Models for Content Moderation of Children's Videos—0
The Sweet-Home speech and multimodal corpus for home automation interaction—0
Three Branches: Detecting Actions With Richer Features—0
Three-Stream Fusion Network for First-Person Interaction Recognition—0
Three-stream network for enriched Action Recognition—0
Show:102550
← PrevPage 36 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