https://github.com/yuchuantian/u-dit
Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Models
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Models
Visual Parser: Representing Part-whole Hierarchies with Transformers
CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation
Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning
Integrally Migrating Pre-trained Transformer Encoder-decoders for Visual Object Detection
Interactive Video Object Segmentation Using Global and Local Transfer Modules
English-Japanese Neural Machine Translation with Encoder-Decoder-Reconstructor
Predicting Aircraft Trajectories: A Deep Generative Convolutional Recurrent Neural Networks Approach
Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond
Neural Machine Translation by Jointly Learning to Align and Translate
Hybrid Reasoning Network for Video-based Commonsense Captioning
Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Images
Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillation
TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation
Temporal Convolutional Networks for Action Segmentation and Detection
Dynamic Neural Representational Decoders for High-Resolution Semantic Segmentation
Text-Only Training for Image Captioning using Noise-Injected CLIP
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.