Visually-Aware Context Modeling for News Image Captioning | allainews.com

March 22, 2024, 4:46 a.m. | Tingyu Qu, Tinne Tuytelaars, Marie-Francine Moens

cs.CV updates on arXiv.org arxiv.org

arXiv:2308.08325v2 Announce Type: replace
Abstract: News Image Captioning aims to create captions from news articles and images, emphasizing the connection between textual context and visual elements. Recognizing the significance of human faces in news images and the face-name co-occurrence pattern in existing datasets, we propose a face-naming module for learning better name embeddings. Apart from names, which can be directly linked to an image area (faces), news image captions mostly contain context information that can only be found in the …

arxiv captioning context cs.cv image modeling type

More from arxiv.org / cs.CV updates on arXiv.org

A survey on deep learning in medical image registration: new technologies, uncertainty, evaluation metrics, and … 9 hours ago | arxiv.org

abstract arxiv beyond cs.cv +16

Enhancing Super-Resolution Networks through Realistic Thick-Slice CT Simulation 9 hours ago | arxiv.org

abstract acquisition arxiv cs.ai +20

TransRUPNet for Improved Polyp Segmentation 9 hours ago | arxiv.org

arxiv cs.cv eess.iv segmentation +1

An interpretable machine learning system for colorectal cancer diagnosis from pathology slides 9 hours ago | arxiv.org

abstract artificial artificial intelligence arxiv +19

Attention is All They Need: Exploring the Media Archaeology of the Computer Vision Research Paper 9 hours ago | arxiv.org

abstract archaeology arxiv attention +22

Refining Remote Photoplethysmography Architectures using CKA and Empirical Methods 9 hours ago | arxiv.org

abstract architecture architectures arxiv +8

Learning to Complement with Multiple Humans 9 hours ago | arxiv.org

abstract adoption arxiv assumptions +12

HiH: A Multi-modal Hierarchy in Hierarchy Network for Unconstrained Gait Recognition 9 hours ago | arxiv.org

abstract advances arxiv challenges +12

Image-Based Virtual Try-On: A Survey 9 hours ago | arxiv.org

arxiv cs.cv image survey +3

Data Architect

@ University of Texas at Austin | Austin, TX

View on ai-jobs.net

Data ETL Engineer

@ University of Texas at Austin | Austin, TX

View on ai-jobs.net

Lead GNSS Data Scientist

@ Lurra Systems | Melbourne

View on ai-jobs.net

Senior Machine Learning Engineer (MLOps)

@ Promaton | Remote, Europe

View on ai-jobs.net

Business Data Scientist, gTech Ads

@ Google | Mexico City, CDMX, Mexico

View on ai-jobs.net

Lead, Data Analytics Operations

@ Zocdoc | Pune, Maharashtra, India

View on ai-jobs.net