English
Related papers

Related papers: Exploring Spatial Language Grounding Through Refer…

200 papers

Current state-of-the-art spatial reasoning-enhanced VLMs are trained to excel at spatial visual question answering (VQA). However, we believe that higher-level 3D-aware tasks, such as articulating dynamic scene changes and motion planning,…

Computer Vision and Pattern Recognition · Computer Science 2024-10-31 Chenyang Ma , Kai Lu , Ta-Ying Cheng , Niki Trigoni , Andrew Markham

Genuine spatial reasoning relies on the capacity to construct and manipulate coherent internal spatial representations, often conceptualized as mental models, rather than merely processing surface linguistic associations. While large…

Artificial Intelligence · Computer Science 2026-03-04 Peiyao Jiang , Zequn Qin , Xi Li

We present a conceptual framework for training Vision-Language Models (VLMs) to perform Visual Perspective Taking (VPT), a core capability for embodied cognition essential for Human-Robot Interaction (HRI). As a first step toward this goal,…

Artificial Intelligence · Computer Science 2025-05-21 Joel Currie , Gioele Migno , Enrico Piacenti , Maria Elena Giannaccini , Patric Bach , Davide De Tommaso , Agnieszka Wykowska

Puzzles have long served as compact and revealing probes of human cognition, isolating abstraction, rule discovery, and systematic reasoning with minimal reliance on prior knowledge. Leveraging these properties, visual puzzles have recently…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Maria Lymperaiou , Vasileios Karampinis , Giorgos Filandrianos , Angelos Vlachos , Chrysoula Zerva , Athanasios Voulodimos

Despite the impressive performance of vision-language models (VLMs) on downstream tasks, their ability to understand and reason about causal relationships in visual inputs remains unclear. Robust causal reasoning is fundamental to solving…

Computation and Language · Computer Science 2026-02-05 Zhaotian Weng , Haoxuan Li , Xin Eric Wang , Kuan-Hao Huang , Jieyu Zhao

Language grounding aims at linking the symbolic representation of language (e.g., words) into the rich perceptual knowledge of the outside world. The general approach is to embed both textual and visual information into a common space -the…

Computation and Language · Computer Science 2021-09-15 Hassan Shahmohammadi , Hendrik P. A. Lensch , R. Harald Baayen

We deal with the navigation problem where the agent follows natural language instructions while observing the environment. Focusing on language understanding, we show the importance of spatial semantics in grounding navigation instructions…

Computation and Language · Computer Science 2021-05-17 Yue Zhang , Quan Guo , Parisa Kordjamshidi

CAPTCHA, originally designed to distinguish humans from robots, has evolved into a real-world benchmark for assessing the spatial reasoning capabilities of vision-language models. In this work, we first show that step-by-step reasoning is…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Python Song , Luke Tenyi Chang , Yun-Yun Tsai , Penghui Li , Junfeng Yang

We investigate the ability of Vision Language Models (VLMs) to perform visual perspective taking using a new set of visual tasks inspired by established human tests. Our approach leverages carefully controlled scenes in which a single…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Gracjan Góral , Alicja Ziarko , Piotr Miłoś , Michał Nauman , Maciej Wołczyk , Michał Kosiński

Vision-Language Models (VLMs) encode knowledge and reasoning capabilities for robotic manipulation within high-dimensional representation spaces. However, current approaches often project them into compressed intermediate representations,…

Robotics · Computer Science 2025-06-25 Wenbo Li , Shiyi Wang , Yiteng Chen , Huiping Zhuang , Qingyao Wu

We focus on grounding (i.e., localizing or linking) referring expressions in images, e.g., ``largest elephant standing behind baby elephant''. This is a general yet challenging vision-language task since it does not only require the…

Computer Vision and Pattern Recognition · Computer Science 2019-07-09 Yulei Niu , Hanwang Zhang , Zhiwu Lu , Shih-Fu Chang

Perspective-aware spatial reasoning involves understanding spatial relationships from specific viewpoints-either egocentric (observer-centered) or allocentric (object-centered). While vision-language models (VLMs) perform well in egocentric…

Computer Vision and Pattern Recognition · Computer Science 2026-02-25 Jaeyun Jang , Seunghui Shin , Taeho Park , Hyoseok Hwang

Conventional phrase grounding aims to localize noun phrases mentioned in a given caption to their corresponding image regions, which has achieved great success recently. Apparently, sole noun phrase grounding is not enough for cross-modal…

Computation and Language · Computer Science 2022-10-25 Panzhong Lu , Xin Zhang , Meishan Zhang , Min Zhang

We introduce GroundNet, a neural network for referring expression recognition -- the task of localizing (or grounding) in an image the object referred to by a natural language expression. Our approach to this task is the first to rely on a…

Computer Vision and Pattern Recognition · Computer Science 2018-05-29 Volkan Cirik , Taylor Berg-Kirkpatrick , Louis-Philippe Morency

Spatial cognition is fundamental to real-world multimodal intelligence, allowing models to effectively interact with the physical environment. While multimodal large language models (MLLMs) have made significant strides, existing benchmarks…

Artificial Intelligence · Computer Science 2026-05-08 Peiran Xu , Sudong Wang , Yao Zhu , Jianing Li , Gege Qi , Yunjian Zhang

Humans possess the visual-spatial intelligence to remember spaces from sequential visual observations. However, can Multimodal Large Language Models (MLLMs) trained on million-scale video datasets also ``think in space'' from videos? We…

Computer Vision and Pattern Recognition · Computer Science 2025-07-04 Jihan Yang , Shusheng Yang , Anjali W. Gupta , Rilyn Han , Li Fei-Fei , Saining Xie

Vision language models (VLMs) have shown significant promise in visual grounding for images as well as videos. In medical imaging research, VLMs represent a bridge between object detection and segmentation, and report understanding and…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Andrew Seohwan Yu , Mohsen Hariri , Kunio Nakamura , Mingrui Yang , Xiaojuan Li , Vipin Chaudhary

Grounding referring expressions in images aims to locate the object instance in an image described by a referring expression. It involves a joint understanding of natural language and image content, and is essential for a range of visual…

Computer Vision and Pattern Recognition · Computer Science 2020-04-21 Sibei Yang , Guanbin Li , Yizhou Yu

The recent rapid development of Large Vision-Language Models (LVLMs) has indicated their potential for embodied tasks.However, the critical skill of spatial understanding in embodied environments has not been thoroughly evaluated, leaving…

Artificial Intelligence · Computer Science 2024-06-11 Mengfei Du , Binhao Wu , Zejun Li , Xuanjing Huang , Zhongyu Wei

Multimodal large language models (MLLMs) have achieved remarkable progress in vision-language tasks, but they continue to struggle with spatial understanding. Existing spatial MLLMs often rely on explicit 3D inputs or architecture-specific…

Computer Vision and Pattern Recognition · Computer Science 2025-11-11 Hunar Batra , Haoqin Tu , Hardy Chen , Yuanze Lin , Cihang Xie , Ronald Clark