arXiv:1606.06164
공식 코드 · Papers with Code
Pragmatic factors in image description: the case of negations
원문 초록
We provide a qualitative analysis of the descriptions containing negations (no, not, n't, nobody, etc) in the Flickr30K corpus, and a categorization of negation uses. Based on this analysis, we provide a set of requirements that an image description system should have in order to generate negation sentences. As a pilot experiment, we used our categorization to manually annotate sentences containing negations in the Flickr30K corpus, with an agreement score of K=0.67. With this paper, we hope to open up a broader discussion of subjective language in image descriptions.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Task Vector Bases: A Unified and Scalable Framework for Compressed Task Arithmetic
Text-Visual Semantic Constrained AI-Generated Image Quality Assessment
Probing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Question Answering Tasks
Mitigating Hallucinations in Vision-Language Models through Image-Guided Head Suppression
CROC: Evaluating and Training T2I Metrics with Pseudo- and Human-Labeled Contrastive Robustness Checks
Patho-R1: A Multimodal Reinforcement Learning-Based Pathology Expert Reasoner
토론
이 논문과 연결된 포럼 글이 아직 없습니다.