paper-with-me

홈 › Papers

Visual Grounding via Accumulated Attention

2018-06-01 · CVPR 2018 6 · Chaorui Deng, Qi Wu, Qingyao Wu, Fuyuan Hu, Fan Lyu, Mingkui Tan

Visual Grounding (VG) aims to locate the most relevant object or region in an image, based on a natural language query. The query can be a phrase, a sentence or even a multi-round dialogue. There are three main challenges in VG: 1) what is the main focus in a query; 2) how to understand an image; 3) how to locate an object. Most existing methods combine all the information curtly, which may suffer from the problem of information redundancy (i.e. ambiguous query, complicated image and a large number of objects). In this paper, we formulate these challenges as three attention problems and propose an accumulated attention (A-ATT) mechanism to reason among them jointly. Our A-ATT mechanism can circularly accumulate the attention for useful information in image, query, and objects, while the noises are ignored gradually. We evaluate the performance of A-ATT on four popular datasets (namely ReferCOCO, ReferCOCO+, ReferCOCOg, and Guesswhat?!), and the experimental results show the superiority of the proposed method in term of accuracy.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

SentenceVisual Grounding

Similar Papers 제목 키워드 기반

Learning to Assemble Neural Module Tree Networks for Visual Grounding

2018-12-08 · ICCV 2019 10 · Daqing Liu, Hanwang Zhang, Feng Wu, Zheng-Jun Zha

Visual grounding, a task to ground (i.e., localize) natural language in images, essentially requires composite visual reasoning. However, existing methods over-simplify the composite nature of language into a monolithic …

Dependency ParsingNatural Language Visual GroundingSentenceSentence Embedding+4

Learning to Compose and Reason with Language Tree Structures for Visual Grounding

2019-06-05 · Richang Hong, Daqing Liu, Xiaoyu Mo, Xiangnan He 외

Grounding natural language in images, such as localizing "the black dog on the left of the tree", is one of the core problems in artificial intelligence, as it needs to comprehend the fine-grained and compositional langu…

Visual GroundingVisual Reasoning

Dynamic Accumulated Attention Map for Interpreting Evolution of Decision-Making in Vision Transformer

2025-03-18 · Yi Liao, Yongsheng Gao, Weichuan Zhang

Various Vision Transformer (ViT) models have been widely used for image recognition tasks. However, existing visual explanation methods can not display the attention flow hidden inside the inner structure of ViT models, …

Decision Making

Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding

2025-03-08 · CVPR 2025 1 · Seil Kang, Jinyeong Kim, Junhyeok Kim, Seong Jae Hwang

Visual grounding seeks to localize the image region corresponding to a free-form text description. Recently, the strong multimodal capabilities of Large Vision-Language Models (LVLMs) have driven substantial improvements…

Language ModelingLanguage ModellingVisual Grounding

Word2Pix: Word to Pixel Cross Attention Transformer in Visual Grounding

2021-07-31 · Heng Zhao, Joey Tianyi Zhou, Yew-Soon Ong

Current one-stage methods for visual grounding encode the language query as one holistic sentence embedding before fusion with visual feature. Such a formulation does not treat each word of a query sentence on par when m…

DecoderSentenceSentence EmbeddingSentence-Embedding+1