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 426–450 of 1322 papers

TitleStatusHype
Batch-Based Activity Recognition from Egocentric Photo-Streams—0
EAGLE: Egocentric AGgregated Language-video Engine—0
EarDA: Towards Accurate and Data-Efficient Earable Activity Sensing—0
Early Improving Recurrent Elastic Highway Network—0
Early Mobility Recognition for Intensive Care Unit Patients Using Accelerometers—0
Benchmarking Classical, Deep, and Generative Models for Human Activity Recognition—0
Eco-Friendly Sensing for Human Activity Recognition—0
EdgeServe: A Streaming System for Decentralized Model Serving—0
Effective Human Activity Recognition Based on Small Datasets—0
Layer-wise training convolutional neural networks with smaller filters for human activity recognition using wearable sensors—0
Efficient data-driven encoding of scene motion using Eccentricity—0
EfficientFi: Towards Large-Scale Lightweight WiFi Sensing via CSI Compression—0
Efficient Multi-stream Temporal Learning and Post-fusion Strategy for 3D Skeleton-based Hand Activity Recognition—0
Efficient Retail Video Annotation: A Robust Key Frame Generation Approach for Product and Customer Interaction Analysis—0
ConViViT -- A Deep Neural Network Combining Convolutions and Factorized Self-Attention for Human Activity Recognition—0
Egocentric Activity Recognition and Localization on a 3D Map—0
Egocentric Activity Recognition on a Budget—0
Egocentric Activity Recognition with Multimodal Fisher Vector—0
Are Accelerometers for Activity Recognition a Dead-end?—0
Egok360: A 360 Egocentric Kinetic Human Activity Video Dataset—0
Bi-Causal: Group Activity Recognition via Bidirectional Causality—0
EMAHA-DB1: A New Upper Limb sEMG Dataset for Classification of Activities of Daily Living—0
Embedding Symbolic Temporal Knowledge into Deep Sequential Models—0
EmbraceNet for Activity: A Deep Multimodal Fusion Architecture for Activity Recognition—0
Babel: A Scalable Pre-trained Model for Multi-Modal Sensing via Expandable Modality Alignment—0
Show:102550
← PrevPage 18 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