https://github.com/mvillarreal14/confoc
공식 코드ConFoc: Content-Focus Protection Against Trojan Attacks on Neural Networks
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Facial tasks in machine learning operate based on images or video frames (or other datasets) focussed on human faces.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
ConFoc: Content-Focus Protection Against Trojan Attacks on Neural Networks
Orthonormal Product Quantization Network for Scalable Face Image Retrieval
Dockerface: an Easy to Install and Use Faster R-CNN Face Detector in a Docker Container
MobileFace: 3D Face Reconstruction with Efficient CNN Regression
AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectors
FRCSyn Challenge at WACV 2024:Face Recognition Challenge in the Era of Synthetic Data
Learning Diversified Feature Representations for Facial Expression Recognition in the Wild
Object Detection with Pixel Intensity Comparisons Organized in Decision Trees
HPRNet: Hierarchical Point Regression for Whole-Body Human Pose Estimation
Unveiling the Two-Faced Truth: Disentangling Morphed Identities for Face Morphing Detection
OrthoMAD: Morphing Attack Detection Through Orthogonal Identity Disentanglement
SimSwap: An Efficient Framework For High Fidelity Face Swapping
A Framework for Event-based Computer Vision on a Mobile Device
Moving Window Regression: A Novel Approach to Ordinal Regression
EmoCLIP: A Vision-Language Method for Zero-Shot Video Facial Expression Recognition
AfriHuBERT: A self-supervised speech representation model for African languages
Exploring Self-Supervised Vision Transformers for Deepfake Detection: A Comparative Analysis
PTW: Pivotal Tuning Watermarking for Pre-Trained Image Generators
Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data
T2V-DDPM: Thermal to Visible Face Translation using Denoising Diffusion Probabilistic Models
PedRecNet: Multi-task deep neural network for full 3D human pose and orientation estimation
A survey and classification of face alignment methods based on face models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.