English
Related papers

Related papers: ChartGaze: Enhancing Chart Understanding in LVLMs …

200 papers

Building cross-model intelligence that can understand charts and communicate the salient information hidden behind them is an appealing challenge in the vision and language(V+L) community. The capability to uncover the underlined table data…

Computation and Language · Computer Science 2023-05-31 Mingyang Zhou , Yi R. Fung , Long Chen , Christopher Thomas , Heng Ji , Shih-Fu Chang

Analyzing the gaze accuracy characteristics of an eye tracker is a critical task as its gaze data is frequently affected by non-ideal operating conditions in various consumer eye tracking applications. In this study, gaze error patterns…

Signal Processing · Electrical Eng. & Systems 2020-05-11 Anuradha Kar

Gaze following and social gaze prediction are fundamental tasks providing insights into human communication behaviors, intent, and social interactions. Most previous approaches addressed these tasks separately, either by designing highly…

Computer Vision and Pattern Recognition · Computer Science 2024-03-18 Anshul Gupta , Samy Tafasca , Arya Farkhondeh , Pierre Vuillecard , Jean-Marc Odobez

Streaming video understanding requires models not only to process temporally incoming frames, but also to anticipate user intention for realistic applications such as Augmented Reality (AR) glasses. While prior streaming benchmarks evaluate…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Daeun Lee , Subhojyoti Mukherjee , Branislav Kveton , Ryan A. Rossi , Viet Dac Lai , Seunghyun Yoon , Trung Bui , Franck Dernoncourt , Mohit Bansal

Attention mechanisms have been widely used in Visual Question Answering (VQA) solutions due to their capacity to model deep cross-domain interactions. Analyzing attention maps offers us a perspective to find out limitations of current VQA…

Computer Vision and Pattern Recognition · Computer Science 2018-10-10 Wei Li , Zehuan Yuan , Xiangzhong Fang , Changhu Wang

Recent advancements have enhanced the capability of Multimodal Large Language Models (MLLMs) to comprehend multi-image information. However, existing benchmarks primarily evaluate answer correctness, overlooking whether models genuinely…

Computer Vision and Pattern Recognition · Computer Science 2025-05-26 Pengfei Wang , Guohai Xu , Weinong Wang , Junjie Yang , Jie Lou , Yunhua Xue

It is well known that human gaze carries significant information about visual attention. However, there are three main difficulties in incorporating the gaze data in an attention mechanism of deep neural networks: 1) the gaze fixation…

Computer Vision and Pattern Recognition · Computer Science 2020-11-10 Kyle Min , Jason J. Corso

Large Vision-Language Models (LVLMs) are an extension of Large Language Models (LLMs) that facilitate processing both image and text inputs, expanding AI capabilities. However, LVLMs struggle with object hallucinations due to their reliance…

Computation and Language · Computer Science 2024-08-12 Avshalom Manevich , Reut Tsarfaty

Vision Language Models (VLMs) have achieved remarkable progress in multimodal tasks, yet they often struggle with visual arithmetic, seemingly simple capabilities like object counting or length comparison, which are essential for relevant…

Artificial Intelligence · Computer Science 2025-05-27 Kung-Hsiang Huang , Can Qin , Haoyi Qiu , Philippe Laban , Shafiq Joty , Caiming Xiong , Chien-Sheng Wu

World-wide-web, with the website and webpage as the main interface, facilitates the dissemination of important information. Hence it is crucial to optimize them for better user interaction, which is primarily done by analyzing users'…

Computer Vision and Pattern Recognition · Computer Science 2023-01-09 Ciheng Zhang , Decky Aspandi , Steffen Staab

We study how vision-language models (VLMs) trained on web-scale data can be integrated into end-to-end driving systems to boost generalization and enable interactivity with human users. While recent approaches adapt VLMs to driving via…

Computer Vision and Pattern Recognition · Computer Science 2025-01-17 Chonghao Sima , Katrin Renz , Kashyap Chitta , Li Chen , Hanxue Zhang , Chengen Xie , Jens Beißwenger , Ping Luo , Andreas Geiger , Hongyang Li

Large language model (LLM) agents are increasingly deployed as scalable user simulators for recommender system evaluation. Yet existing simulators perceive recommendations through text or structured metadata rather than the visual…

Multimedia · Computer Science 2026-04-13 Lingfeng Huang , Huizhong Guo , Tianjun Wei , Yingpeng Du , Zhu Sun

Vision language models (VLMs) often generate hallucination, i.e., content that cannot be substantiated by either textual or visual inputs. Prior work primarily attributes this to over-reliance on linguistic prior knowledge rather than…

Computer Vision and Pattern Recognition · Computer Science 2025-11-11 Zheng Qi , Chao Shang , Evangelia Spiliopoulou , Nikolaos Pappas

Structured image understanding, such as interpreting tables and charts, requires strategically refocusing across various structures and texts within an image, forming a reasoning sequence to arrive at the final answer. However, current…

Computer Vision and Pattern Recognition · Computer Science 2025-01-10 Xingyu Fu , Minqian Liu , Zhengyuan Yang , John Corring , Yijuan Lu , Jianwei Yang , Dan Roth , Dinei Florencio , Cha Zhang

While Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities for reasoning and self-correction at the textual level, these strengths provide minimal benefits for complex tasks centered on visual perception, such as…

Computer Vision and Pattern Recognition · Computer Science 2026-02-19 Jinsong Li , Xiaoyi Dong , Yuhang Zang , Yuhang Cao , Jiaqi Wang , Dahua Lin

We explore the internal mechanisms of how bias emerges in large language models (LLMs) when provided with ambiguous comparative prompts: inputs that compare or enforce choosing between two or more entities without providing clear context…

Computation and Language · Computer Science 2024-10-31 Rishabh Adiga , Besmira Nushi , Varun Chandrasekaran

Chart understanding plays a pivotal role when applying Multimodal Large Language Models (MLLMs) to real-world tasks such as analyzing scientific papers or financial reports. However, existing datasets often focus on oversimplified and…

The ability of gaze estimation models to generalize is often significantly hindered by various factors unrelated to gaze, especially when the training dataset is limited. Current strategies aim to address this challenge through different…

Computer Vision and Pattern Recognition · Computer Science 2024-11-14 Pengwei Yin , Jingjing Wang , Guanzhong Zeng , Di Xie , Jiang Zhu

Vision Language Models (VLMs) face challenges in effectively coordinating diverse attention mechanisms for cross-modal embedding learning, leading to mismatched attention and suboptimal performance. We propose Consistent Cross-layer…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Yifan Wang , Hongfeng Ai , Quangao Liu , Maowei Jiang , Ruiyuan Kang , Ruiqi Li , Jiahua Dong , Mengting Xiao , Cheng Jiang , Chenzhong Li

Chart understanding is a quintessential information fusion task, requiring the seamless integration of graphical and textual data to extract meaning. The advent of Multimodal Large Language Models (MLLMs) has revolutionized this domain, yet…

Computer Vision and Pattern Recognition · Computer Science 2026-02-12 Zhihang Yi , Jian Zhao , Jiancheng Lv , Tao Wang