Papers with Code 아카이브
Face Identification
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 5
- 보존된 평가 기록
- 29
Face identification is the task of matching a given face image to one in an existing database of faces. It is the second part of face recognition (the first part being detection). It is a one-to-many mapping: you have to find an unknown person in a database to find who that person is.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
GoDP: Globally optimized dual pathway system for facial landmark localization in-the-wild
Deep 3D Face Identification
Active Self-Paced Learning for Cost-Effective and Progressive Face Identification
Pooling Faces: Template based Face Recognition with Pooled Face Images
ASP Vision: Optically Computing the First Layer of Convolutional Neural Networks using Angle Sensitive Pixels
Robust and Low-Rank Representation for Fast Face Identification with Occlusions
Training Region-based Object Detectors with Online Hard Example Mining
Neural Aggregation Network for Video Face Recognition
Template Adaptation for Face Verification and Identification
Improved Eigenfeature Regularization for Face Identification
Studying Very Low Resolution Recognition Using Deep Networks
Bidirectional Warping of Active Appearance Model
A Light CNN for Deep Face Representation with Noisy Labels
Leveraging the Power of Gabor Phase for Face Identification: A Block Matching Approach
Face Prediction Model for an Automatic Age-invariant Face Recognition System
FaceNet: A Unified Embedding for Face Recognition and Clustering
DeepID3: Face Recognition with Very Deep Neural Networks
FAME: Face Association through Model Evolution
Face Identification with Second-Order Pooling
Web-Scale Training for Face Identification
Deep Learning Face Representation by Joint Identification-Verification
Multi-Directional Multi-Level Dual-Cross Patterns for Robust Face Recognition
Network In Network
Large Scale Correlation Clustering Optimization
Face Identification from Manipulated Facial Images using SIFT
Face Identification by SIFT-based Complete Graph Topology
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.