Cross-Domain Image Captioning with Discriminative Finetuning

Author:

Dessì Roberto1,Bevilacqua Michele2,Gualdoni Eleonora3,Rakotonirina Nathanaël Carraz3,Franzon Francesca3,Baroni Marco4

Affiliation:

1. Meta AI / UPF

2. Samaya AI

3. UPF

4. UPF / ICREA

Funder

European Research Council (ERC)

Publisher

IEEE

Reference50 articles.

1. An image is worth 16×16 words: Transformers for image recognition at scale;dosovitskiy;International Conference on Learning Representations,2021

2. Long-Term Recurrent Convolutional Networks for Visual Recognition and Description

3. CapWAP: Image captioning with a pur-pose;fisch;Proceedings of EMNLP,2020

4. Communication break-down: On the low mutual intelligibility between human and neural captioning;dessì;Proceedings of EMNLP,2022

Cited by 4 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Cross-Domain Text Classification: Transfer Learning Approaches;2024 International Conference on Emerging Smart Computing and Informatics (ESCI);2024-03-05

2. Learning Scene Graph for Better Cross-Domain Image Captioning;Pattern Recognition and Computer Vision;2023-12-24

3. Simulated mental imagery for robotic task planning;Frontiers in Neurorobotics;2023-08-24

4. Toward More Human-Like AI Communication: A Review of Emergent Communication Research;IEEE Access;2023

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3