https://github.com/ZJULearning/CariFaceParsing
공식 코드Weakly-supervised Caricature Face Parsing through Domain Adaptation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Weakly-supervised Caricature Face Parsing through Domain Adaptation
Learning Interpretable Representation for Controllable Polyphonic Music Generation
Artwork Protection Against Neural Style Transfer Using Locally Adaptive Adversarial Color Attack
Puff-Net: Efficient Style Transfer with Pure Content and Style Feature Fusion Network
GTSinger: A Global Multi-Technique Singing Corpus with Realistic Music Scores for All Singing Tasks
TCSinger 2: Customizable Multilingual Zero-shot Singing Voice Synthesis
He Said, She Said: Style Transfer for Shifting the Perspective of Dialogues
So Different Yet So Alike! Constrained Unsupervised Text Style Transfer
HyperGAN-CLIP: A Unified Framework for Domain Adaptation, Image Synthesis and Manipulation
Generating Text through Adversarial Training using Skip-Thought Vectors
PEMA: An Offsite-Tunable Plug-in External Memory Adaptation for Language Models
On the Fly Neural Style Smoothing for Risk-Averse Domain Generalization
BACON: Deep-Learning Powered AI for Poetry Generation with Author Linguistic Style Transfer
Enhancing Perceptual Attributes with Bayesian Style Generation
EEC: Learning to Encode and Regenerate Images for Continual Learning
S2WAT: Image Style Transfer via Hierarchical Vision Transformer using Strips Window Attention
Tailor: Generating and Perturbing Text with Semantic Controls
Fusion of complementary 2D and 3D mesostructural datasets using generative adversarial networks
Diffusion-based Image Translation using Disentangled Style and Content Representation
Design What You Desire: Icon Generation from Orthogonal Application and Theme Labels
FastBlend: a Powerful Model-Free Toolkit Making Video Stylization Easier
ICLEF: In-Context Learning with Expert Feedback for Explainable Style Transfer
ArtFacePoints: High-resolution Facial Landmark Detection in Paintings and Prints
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.