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 551–575 of 1322 papers

TitleStatusHype
From Movements to Metrics: Evaluating Explainable AI Methods in Skeleton-Based Human Activity Recognition—0
Comparative Analysis of XGBoost and Minirocket Algortihms for Human Activity Recognition—0
Fullie and Wiselie: A Dual-Stream Recurrent Convolutional Attention Model for Activity Recognition—0
Complex Activity Recognition using Granger Constrained DBN (GCDBN) in Sports and Surveillance Video—0
From Motion Signals to Insights: A Unified Framework for Student Behavior Analysis and Feedback in Physical Education Classes—0
C3T: Cross-modal Transfer Through Time for Sensor-based Human Activity Recognition—0
Fusion of Deep Neural Networks for Activity Recognition: A Regular Vine Copula Based Approach—0
Game of LLMs: Discovering Structural Constructs in Activities using Large Language Models—0
Game Theory Solutions in Sensor-Based Human Activity Recognition: A Review—0
Gated networks: an inventory—0
Gated Recurrent Neural Networks with Weighted Time-Delay Feedback—0
Generalizable Indoor Human Activity Recognition Method Based on Micro-Doppler Corner Point Cloud and Dynamic Graph Learning—0
Generalizable Low-Resource Activity Recognition with Diverse and Discriminative Representation Learning—0
Generalizable Sensor-Based Activity Recognition via Categorical Concept Invariant Learning—0
Generalization Ability Analysis of Through-the-Wall Radar Human Activity Recognition—0
Generalized Rank Pooling for Activity Recognition—0
Context Aware Active Learning of Activity Recognition Models—0
Out-of-Distribution Representation Learning for Time Series Classification—0
Frequency-Aware Masked Autoencoders for Human Activity Recognition using Accelerometers—0
Generative AI based Secure Wireless Sensing for ISAC Networks—0
A Deep Learning Method for Complex Human Activity Recognition Using Virtual Wearable Sensors—0
Generative Resident Separation and Multi-label Classification for Multi-person Activity Recognition—0
Generic Semi-Supervised Adversarial Subject Translation for Sensor-Based Human Activity Recognition—0
Action Recognition based Industrial Safety Violation Detection—0
Compact CNN for Indexing Egocentric Videos—0
Show:102550
← PrevPage 23 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