Publications
Article · Sensors · February 22, 2024
Faces in Event Streams (FES): An Annotated Face Dataset for Event Cameras
Ulzhan Bissarinova, Tomiris Rakhimzhanova, Daulet Kenzhebalin, Hüseyin Atakan Varol
Abstract
Faces in Event Streams dataset contains 689 minutes of recorded event streams, and 1.6 million annotated faces with bounding box and five point facial landmarks. Tha paper presents the dataset and corresponding models for detecting face and facial landmakrs directly from event stream data.
Face Recognition and PerceptionBiometric Identification and SecurityAdvanced Memory and Neural ComputingLandmarkComputer scienceEvent (particle physics)
Related publications
- CSDS: AI-Based Construction Site Detection and Segmentation tool for Satellite Images2025 · Same author: Ulzhan Bissarinova
- DL-SLICER: Deep Learning for Satellite-Based Identification of Cities with Enhanced ResemblanceBuildings · 2024 · Citations: 5 · Same author: Ulzhan Bissarinova
- Faces in Event Streams (FES): An Annotated Face Dataset for Event Cameras2023 · Same author: Ulzhan Bissarinova
- One-to-Many Synchronization in High-Drift IoT Devices Using Reinforcement LearningIEEE Transactions on Instrumentation and Measurement · 2025 · Citations: 1 · Shared topic: Advanced Memory and Neural Computing