paper-with-me

홈 › Papers

Exploring Contextual Attribute Density in Referring Expression Counting

2025-01-01 · CVPR 2025 1 · Zhicheng Wang, Zhiyu Pan, Zhan Peng, Jian Cheng, Liwen Xiao, Wei Jiang, Zhiguo Cao

Referring expression counting (REC) algorithms are for more flexible and interactive counting ability across varied fine-grained text expressions. However, the requirement for fine-grained attribute understanding poses challenges for prior arts, as they struggle to accurately align attribute information with correct visual patterns. Given the proven importance of "visual density", it is presumed that the limitations of current REC approaches stem from an under-exploration of "contextual attribute density" (CAD). In the scope of REC, we define the CAD as the measure of the information intensity of one certain fine-grained attribute in visual regions. To model the the CAD, we propose a U-shape CAD estimator in which referring expression and multi-scale visual features from GroundingDINO can interact with each other. With additional density supervisions, we can effectively encode CAD, which is subsequently decoded via a novel attention procedure with CAD-refined queries. Integrating all these contributions, our framework significantly outperforms state-of-the-art REC methods, achieves 30% error reduction in counting metics and a 10% improvement in localization accuracy. The surprising results shed lights on the significance of contextual attribute density for REC. Code will be at github.com/Xu3XiWang/CAD-GD.

📄 PDF Abstract BibTeX

Code (1)

xu3xiwang/cad-gd 공식 구현 pytorch

Tasks

AttributeReferring Expression

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Exploring Contextual Attribute Density in Referring Expression Counting

2025-03-16 · Zhicheng Wang, Zhiyu Pan, Zhan Peng, Jian Cheng 외

Referring expression counting (REC) algorithms are for more flexible and interactive counting ability across varied fine-grained text expressions. However, the requirement for fine-grained attribute understanding poses c…

AttributeReferring Expression

A case study on context-bound referring expression generation

2019-10-01 · WS 2019 10 · Maurice Langner

In recent years, Bayesian models of referring expression generation have gained prominence in order to produce situationally more adequate referring expressions. Basically, these models enable the integration of differen…

Referring ExpressionReferring expression generation

Referring Expression Generation and Comprehension via Attributes

2017-10-01 · ICCV 2017 10 · Jingyu Liu, Liang Wang, Ming-Hsuan Yang

Referring expression is a kind of language expression that used for referring to particular objects.To make the expression without ambiguation, people often use attributes to describe the particular object. In this paper…

AttributeReferring ExpressionReferring expression generation

Joint Visual Grounding with Language Scene Graphs

2019-06-09 · Daqing Liu, Hanwang Zhang, Zheng-Jun Zha, Meng Wang 외

Visual grounding is a task to ground referring expressions in images, e.g., localize "the white truck in front of the yellow one". To resolve this task fundamentally, the model should first find out the contextual object…

Referring ExpressionVisual Grounding

Corpus-based Referring Expressions Generation

2012-05-01 · LREC 2012 5 · Hilder Pereira, Eder Novais, Andr{\'e} Mariotti, Iv Paraboni 외

In Natural Language Generation, the task of attribute selection (AS) consists of determining the appropriate attribute-value pairs (or semantic properties) that represent the contents of a referring expression. Existing …

AttributeReferring ExpressionText Generation