paper-with-me

Papers

Context-Infused Visual Grounding for Art

2024-10-16 · Selina Khan, Nanne van Noord

Many artwork collections contain textual attributes that provide rich and contextualised descriptions of artworks. Visual grounding offers the potential for localising subjects within these descriptions on images, however, existing approaches are trained on natural images and generalise poorly to art. In this paper, we present CIGAr (Context-Infused GroundingDINO for Art), a visual grounding approach which utilises the artwork descriptions during training as context, thereby enabling visual grounding on art. In addition, we present a new dataset, Ukiyo-eVG, with manually annotated phrase-grounding annotations, and we set a new state-of-the-art for object detection on two artwork datasets.

📄 PDF Abstract BibTeX arXiv:2410.12369

Code (1)

selinakhan/CIGAr 공식 구현 pytorch

Tasks

object-detectionObject DetectionPhrase GroundingVisual Grounding

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

KSAT: Knowledge-infused Self Attention Transformer -- Integrating Multiple Domain-Specific Contexts

2022-10-09 · Kaushik Roy, Yuxin Zi, Vignesh Narayanan, Manas Gaur 외

Domain-specific language understanding requires integrating multiple pieces of relevant contextual information. For example, we see both suicide and depression-related behavior (multiple contexts) in the text ``I have a …

Specificity

Vision-Infused Deep Audio Inpainting

2019-10-24 · ICCV 2019 10 · Hang Zhou, Ziwei Liu, Xudong Xu, Ping Luo 외

Multi-modality perception is essential to develop interactive intelligence. In this work, we consider a new task of visual information-infused audio inpainting, \ie synthesizing missing audio segments that correspond to …

Audio inpaintingImage Inpainting

Knowledge Infused Policy Gradients with Upper Confidence Bound for Relational Bandits

2021-06-25 · Kaushik Roy, Qi Zhang, Manas Gaur, Amit Sheth

Contextual Bandits find important use cases in various real-life scenarios such as online advertising, recommendation systems, healthcare, etc. However, most of the algorithms use flat feature vectors to represent contex…

DescriptiveMulti-Armed BanditsMusic RecommendationRecommendation Systems

The Context of Crash Occurrence: A Complexity-Infused Approach Integrating Semantic, Contextual, and Kinematic Features

2024-11-26 · Meng Wang, Zach Noonan, Pnina Gershon, Bruce Mehler 외

Understanding the context of crash occurrence in complex driving environments is essential for improving traffic safety and advancing automated driving. Previous studies have used statistical models and deep learning to …

Autonomous DrivingLanguage ModelingLanguage ModellingLarge Language Model

Learning Cross-modal Context Graph for Visual Grounding

2020-02-13 · AAAI-2020 2020 2 · Yongfei Liu; Bo Wan; Xiaodan Zhu; Xuming He

Visual grounding is a ubiquitous building block in many vision-language tasks and yet remains challenging due to large variations in visual and linguistic features of grounding entities, strong context effect and the res…

Graph MatchingGraph Neural NetworkLanguage ModellingNatural Language Visual Grounding+2