会员服务
图像字幕（Image Captioning）,是指从图像生成文本描述的过程，主要根据图像中物体和物体的动作。
Continual Learning for Image Captioning through Improved Image-Text Alignment
Arxiv
0+阅读 · 10月7日
ZoDIAC: Zoneout Dropout Injection Attention Calculation
Arxiv
0+阅读 · 9月30日
Describe Anything in Medical Images
Arxiv
0+阅读 · 5月9日
ComicsPAP: understanding comic strips by picking the correct panel
Arxiv
0+阅读 · 7月30日
A Deep Learning Approach for Augmenting Perceptional Understanding of Histopathology Images
Arxiv
0+阅读 · 7月23日
Image Embedding Sampling Method for Diverse Captioning
Arxiv
0+阅读 · 9月4日
A Conformal Risk Control Framework for Granular Word Assessment and Uncertainty Calibration of CLIPScore Quality Estimates
Arxiv
0+阅读 · 6月2日
RS-RAG: Bridging Remote Sensing Imagery and Comprehensive Knowledge with a Multi-Modal Dataset and Retrieval-Augmented Generation Model
Arxiv
0+阅读 · 4月7日
Image captioning in different languages
Arxiv
0+阅读 · 4月2日
Group-based Distinctive Image Captioning with Memory Difference Encoding and Attention
Group-based Distinctive Image Captioning with Memory Difference Encoding and Attention
Arxiv
0+阅读 · 4月3日
A Conformal Risk Control Framework for Granular Word Assessment and Uncertainty Calibration of CLIPScore Quality Estimates
A Conformal Risk Control Framework for Granular Word Assessment and Uncertainty Calibration of CLIPScore Quality Estimates
Arxiv
0+阅读 · 4月1日
JEEM: Vision-Language Understanding in Four Arabic Dialects
Arxiv
0+阅读 · 3月27日
BACON: Improving Clarity of Image Captions via Bag-of-Concept Graphs
Arxiv
0+阅读 · 3月27日
ComicsPAP: understanding comic strips by picking the correct panel
Arxiv
0+阅读 · 3月11日
A Deep Learning Approach for Augmenting Perceptional Understanding of Histopathology Images
Arxiv
0+阅读 · 3月19日
参考链接
微信扫码咨询专知VIP会员
Top