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 226–250 of 1322 papers

TitleStatusHype
Multimodal Explanations: Justifying Decisions and Pointing to the EvidenceCode0
Attention-Refined Unrolling for Sparse Sequential micro-Doppler ReconstructionCode0
Evaluating Spiking Neural Network On Neuromorphic Platform For Human Activity RecognitionCode0
Generative Pretrained Embedding and Hierarchical Irregular Time Series Representation for Daily Living Activity RecognitionCode0
Multi-view Video-Pose Pretraining for Operating Room Surgical Activity RecognitionCode0
Human Activity Recognition using Continuous Wavelet Transform and Convolutional Neural NetworksCode0
AssembleNet++: Assembling Modality Representations via Attention ConnectionsCode0
ASM2TV: An Adaptive Semi-Supervised Multi-Task Multi-View Learning Framework for Human Activity RecognitionCode0
Adversarial Domain Adaptation for Cross-user Activity Recognition Using Diffusion-based Noise-centred LearningCode0
Domain Adaptation Under Behavioral and Temporal Shifts for Natural Time Series Mobile Activity RecognitionCode0
Object Level Visual Reasoning in VideosCode0
Domain Adaptation with Representation Learning and Nonlinear Relation for Time SeriesCode0
Online Learning Probabilistic Event Calculus Theories in Answer Set ProgrammingCode0
Cadence: A Practical Time-series Partitioning Algorithm for Unlabeled IoT Sensor StreamsCode0
Distributed Online Learning of Event DefinitionsCode0
MONAQ: Multi-Objective Neural Architecture Querying for Time-Series Analysis on Resource-Constrained DevicesCode0
DiTMoS: Delving into Diverse Tiny-Model Selection on MicrocontrollersCode0
Adversarial Attacks on Deep Neural Networks for Time Series ClassificationCode0
PI-Net: A Deep Learning Approach to Extract Topological Persistence ImagesCode0
Pose And Joint-Aware Action RecognitionCode0
PoseTrack: A Benchmark for Human Pose Estimation and TrackingCode0
Discriminatively Learned Hierarchical Rank Pooling NetworksCode0
Does SpatioTemporal information benefit Two video summarization benchmarks?Code0
An IoT Based Framework For Activity Recognition Using Deep Learning TechniqueCode0
Dynamic Vision Sensors for Human Activity RecognitionCode0
Show:102550
← PrevPage 10 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