https://github.com/alexa/amazon-voice-conversion-voicy
공식 코드Voicy: Zero-Shot Non-Parallel Voice Conversion in Noisy Reverberant Environments
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Voicy: Zero-Shot Non-Parallel Voice Conversion in Noisy Reverberant Environments
Modeling Camera Effects to Improve Visual Learning from Synthetic Data
Cross-domain and Cross-dimension Learning for Image-to-Graph Transformers
AdaPool: Exponential Adaptive Pooling for Information-Retaining Downsampling
Help the Blind See: Assistance for the Visually Impaired through Augmented Acoustic Simulation
BACON: Deep-Learning Powered AI for Poetry Generation with Author Linguistic Style Transfer
Adaptive Bounding Box Uncertainties via Two-Step Conformal Prediction
EventGAN: Leveraging Large Scale Image Datasets for Event Cameras
Image Restoration with Mean-Reverting Stochastic Differential Equations
ChatDiT: A Training-Free Baseline for Task-Agnostic Free-Form Chatting with Diffusion Transformers
Enhancing Perceptual Attributes with Bayesian Style Generation
EEC: Learning to Encode and Regenerate Images for Continual Learning
YOLOX-PAI: An Improved YOLOX, Stronger and Faster than YOLOv6
COCO-O: A Benchmark for Object Detectors under Natural Distribution Shifts
Enhance the Visual Representation via Discrete Adversarial Training
ESOD: Efficient Small Object Detection on High-Resolution Images
Revisiting Personalized Federated Learning: Robustness Against Backdoor Attacks
MAE-DET: Revisiting Maximum Entropy Principle in Zero-Shot NAS for Efficient Object Detection
Sensitivity of Average Precision to Bounding Box Perturbations
S2WAT: Image Style Transfer via Hierarchical Vision Transformer using Strips Window Attention
SVBR-NET: A Non-Blind Spatially Varying Defocus Blur Removal Network
Underwater Object Detection Enhancement via Channel Stabilization
MN-DS: A Multilabeled News Dataset for News Articles Hierarchical Classification
Patch-level Representation Learning for Self-supervised Vision Transformers
Drastically Reducing the Number of Trainable Parameters in Deep CNNs by Inter-layer Kernel-sharing
Iranis: A Large-scale Dataset of Farsi License Plate Characters
Mixture Dense Regression for Object Detection and Human Pose Estimation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.