https://github.com/forgi86/sysid-neural-transformers
공식 코드From system models to class models: An in-context learning paradigm
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
From system models to class models: An in-context learning paradigm
From system models to class models: An in-context learning paradigm
Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation
Predicting Music Hierarchies with a Graph-Based Neural Decoder
Enhancing Automated Audio Captioning via Large Language Models with Optimized Audio Encoding
A Simple and Efficient Multi-task Network for 3D Object Detection and Road Understanding
TBFormer: Two-Branch Transformer for Image Forgery Localization
FreeStyle: Free Lunch for Text-guided Style Transfer using Diffusion Models
Espresso: A Fast End-to-end Neural Speech Recognition Toolkit
Dynamic Linear Transformer for 3D Biomedical Image Segmentation
PrimDiffusion: Volumetric Primitives Diffusion for 3D Human Generation
4K-NeRF: High Fidelity Neural Radiance Fields at Ultra High Resolutions
Fast and Adaptive Questionnaires for Voting Advice Applications
Latent Structured Hopfield Network for Semantic Association and Retrieval
Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
DeepInteraction: 3D Object Detection via Modality Interaction
A 7K Parameter Model for Underwater Image Enhancement based on Transmission Map Prior
Uni-Perceiver v2: A Generalist Model for Large-Scale Vision and Vision-Language Tasks
StyleTalk: One-shot Talking Head Generation with Controllable Speaking Styles
HQDec: Self-Supervised Monocular Depth Estimation Based on a High-Quality Decoder
Fast Convergence of DETR with Spatially Modulated Co-Attention
AlphaDesign: A graph protein design method and benchmark on AlphaFoldDB
DuEDL: Dual-Branch Evidential Deep Learning for Scribble-Supervised Medical Image Segmentation
RTA-Former: Reverse Transformer Attention for Polyp Segmentation
RoboSignature: Robust Signature and Watermarking on Network Attacks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.