https://github.com/layumi/Image-Text-Embedding
공식 코드Dual-Path Convolutional Image-Text Embeddings with Instance Loss
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Dual-Path Convolutional Image-Text Embeddings with Instance Loss
When Counting Meets HMER: Counting-Aware Network for Handwritten Mathematical Expression Recognition
Emulation of greenhouse-gas sensitivities using variational autoencoders
Nice perfume. How long did you marinate in it? Multimodal Sarcasm Explanation
Redesigning the Transformer Architecture with Insights from Multi-particle Dynamical Systems
MISC: Ultra-low Bitrate Image Semantic Compression Driven by Large Multimodal Model
GSVA: Generalized Segmentation via Multimodal Large Language Models
MultiMed: Multilingual Medical Speech Recognition via Attention Encoder Decoder
wav2graph: A Framework for Supervised Learning Knowledge Graph from Speech
FocusLLM: Precise Understanding of Long Context by Dynamic Condensing
DPDnet: A Robust People Detector using Deep Learning with an Overhead Depth Camera
DialogVED: A Pre-trained Latent Variable Encoder-Decoder Model for Dialog Response Generation
Hurricane Forecasting: A Novel Multimodal Machine Learning Framework
Distilling Knowledge for Designing Computational Imaging Systems
Learning Signed Hyper Surfaces for Oriented Point Cloud Normal Estimation
Decoding a Neural Retriever's Latent Space for Query Suggestion
Motion-to-Matching: A Mixed Paradigm for 3D Single Object Tracking
Patching Leaks in the Charformer for Efficient Character-Level Generation
Performance Evaluation of Channel Decoding With Deep Neural Networks
MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection
Contrastive Representation Learning for Exemplar-Guided Paraphrase Generation
LORS: Low-rank Residual Structure for Parameter-Efficient Network Stacking
A new baseline for edge detection: Make Encoder-Decoder great again
Multi-Decoder Attention Model with Embedding Glimpse for Solving Vehicle Routing Problems
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.