English
Related papers

Related papers: Geometry without Position? When Positional Embeddi…

200 papers

Several works have proposed to learn a two-path neural network that maps images and texts, respectively, to a same shared Euclidean space where geometry captures useful semantic relationships. Such a multi-modal embedding can be trained and…

Computer Vision and Pattern Recognition · Computer Science 2018-04-09 Martin Engilberge , Louis Chevallier , Patrick Pérez , Matthieu Cord

Recent advances in machine learning offer new ways to represent and study scholarly works and the space of knowledge. Graph and text embeddings provide a convenient vector representation of scholarly works based on citations and text. Yet,…

Social and Information Networks · Computer Science 2025-02-14 Isabel Constantino , Sadamori Kojaku , Santo Fortunato , Yong-Yeol Ahn

Neural language models process sequences of words, but the mathematical operations inside them are insensitive to the order in which words appear. Positional encodings are the component added to remedy this. Despite their importance,…

Machine Learning · Computer Science 2026-04-08 Giansalvo Cirrincione

Top-view perspective denotes a typical way in which humans read and reason over different types of maps, and it is vital for localization and navigation of humans as well as of `non-human' agents, such as the ones backed by large…

Computation and Language · Computer Science 2024-06-05 Chengzu Li , Caiqi Zhang , Han Zhou , Nigel Collier , Anna Korhonen , Ivan Vulić

Accurate global localization is critical for autonomous driving and robotics, but GNSS-based approaches often degrade due to occlusion and multipath effects. As an emerging alternative, cross-view pose estimation predicts the 3-DoF camera…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Juhye Park , Wooju Lee , Dasol Hong , Changki Sung , Youngwoo Seo , Dongwan Kang , Hyun Myung

Inter-object relations underpin spatial intelligence, yet existing representations -- linguistic prepositions or object-level scene graphs -- are too coarse to specify which regions actually support, contain, or contact one another, leading…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Yinuo Bai , Peijun Xu , Kuixiang Shao , Yuyang Jiao , Jingxuan Zhang , Kaixin Yao , Jiayuan Gu , Jingyi Yu

Semantic embeddings have advanced the state of the art for countless natural language processing tasks, and various extensions to multimodal domains, such as visual-semantic embeddings, have been proposed. While the power of visual-semantic…

Machine Learning · Computer Science 2021-02-23 Adam Dahlgren Lindström , Suna Bensch , Johanna Björklund , Frank Drewes

Recent advances in Transformer models allow for unprecedented sequence lengths, due to linear space and time complexity. In the meantime, relative positional encoding (RPE) was proposed as beneficial for classical Transformers and consists…

Machine Learning · Computer Science 2021-06-11 Antoine Liutkus , Ondřej Cífka , Shih-Lun Wu , Umut Şimşekli , Yi-Hsuan Yang , Gaël Richard

Vision Transformers trained only on image classification routinely transfer to tasks that demand spatial understanding, yet they receive no spatial supervision during pretraining. We ask where and how robustly such structure is encoded.…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Jainum Sanghavi

Vision Transformers must resolve figure-ground organization by choosing between completions driven by local geometric evidence and those favored by global organizational priors, giving rise to a characteristic perceptual ambiguity. We aim…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Stefan Arnold , René Gröbner

Vision-language models (VLMs) have advanced rapidly, yet they still struggle with basic spatial reasoning. Despite strong performance on general benchmarks, modern VLMs remain brittle at understanding 2D spatial relationships such as…

Computer Vision and Pattern Recognition · Computer Science 2026-04-02 Nahid Alam , Leema Krishna Murali , Siddhant Bharadwaj , Patrick Liu , Timothy Chung , Drishti Sharma , Akshata A. , Kranthi Kiran , Wesley Tam , Bala Krishna S Vegesna

Human physical reasoning relies on internal "body" representations - coarse, volumetric approximations that capture an object's extent and support intuitive predictions about motion and physics. While psychophysical evidence suggests humans…

Computer Vision and Pattern Recognition · Computer Science 2025-12-02 Andrey Gizdov , Andrea Procopio , Yichen Li , Daniel Harari , Tomer Ullman

Most computational accounts of cognitive maps assume that stability is achieved primarily through sensory anchoring, with self-motion contributing to incremental positional updates only. However, biological spatial representations often…

Neurons and Cognition · Quantitative Biology 2025-12-24 Yingchao Yu , Pengfei Sun , Yaochu Jin , Kuangrong Hao , Hao Zhang , Yifeng Zhang , Wenxuan Pan , Wei Chen , Danyal Akarca , Yuchen Xiao

We investigate the robustness of vision transformers (ViTs) through the lens of their special patch-based architectural structure, i.e., they process an image as a sequence of image patches. We find that ViTs are surprisingly insensitive to…

Machine Learning · Computer Science 2023-02-23 Yao Qin , Chiyuan Zhang , Ting Chen , Balaji Lakshminarayanan , Alex Beutel , Xuezhi Wang

There exists a correlation between geospatial activity temporal patterns and type of land use. A novel self-supervised approach is proposed to stratify landscape based on mobility activity time series. First, the time series signal is…

Computer Vision and Pattern Recognition · Computer Science 2024-01-18 Yi Cao , Swetava Ganguli , Vipul Pandey

Multimodal large language models (MLLMs) have achieved strong performance on vision-language tasks, yet often suffer from inefficiencies due to redundant visual tokens. Existing token merging methods reduce sequence length but frequently…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Mouxiao Huang , Borui Jiang , Dehua Zheng , Hailin Hu , Kai Han , Xinghao Chen

Multimodal large language models (MLLMs) have made significant advancements in vision understanding and reasoning. However, the autoregressive Transformer architecture used by MLLMs requries tokenization on input images, which limits their…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Xiangxuan Ren , Zhongdao Wang , Liping Hou , Pin Tang , Guoqing Wang , Chao Ma

It is well known that perspective alignment plays a major role in the planning and interpretation of spatial language. In order to understand the role of perspective alignment and the cognitive processes involved, we have made precise…

Artificial Intelligence · Computer Science 2008-02-13 L. Steels , M. Loetzsch

Vision Transformers (ViTs) have demonstrated exceptional performance in various vision tasks. However, they tend to underperform on smaller datasets due to their inherent lack of inductive biases. Current approaches address this limitation…

Computer Vision and Pattern Recognition · Computer Science 2026-02-20 Alan Luo , Kaiwen Yuan

Computer vision has achieved remarkable success by (a) representing images as uniformly-arranged pixel arrays and (b) convolving highly-localized features. However, convolutions treat all image pixels equally regardless of importance;…

Computer Vision and Pattern Recognition · Computer Science 2020-11-23 Bichen Wu , Chenfeng Xu , Xiaoliang Dai , Alvin Wan , Peizhao Zhang , Zhicheng Yan , Masayoshi Tomizuka , Joseph Gonzalez , Kurt Keutzer , Peter Vajda
‹ Prev 1 8 9 10 Next ›