English
Related papers

Related papers: LaVIDE: A Language-Vision Discriminator for Detect…

200 papers

We introduce a new task called Defeasible Visual Entailment (DVE), where the goal is to allow the modification of the entailment relationship between an image premise and a text hypothesis based on an additional update. While this concept…

Computer Vision and Pattern Recognition · Computer Science 2025-02-11 Yue Zhang , Liqiang Jing , Vibhav Gogate

Machine translation between many languages at once is highly challenging, since training with ground truth requires supervision between all language pairs, which is difficult to obtain. Our key insight is that, while languages may vary…

Computation and Language · Computer Science 2022-04-04 Dídac Surís , Dave Epstein , Carl Vondrick

Accurate localization and 3D maps are increasingly needed for various artificial intelligence based IoT applications such as augmented reality, intelligent transportation, crowd monitoring, robotics, etc. This article proposes a novel…

Robotics · Computer Science 2021-03-23 Max Jwo Lem Lee , Li-Ta Hsu

We investigate the problem of identifying objects that have been added, removed, or moved between a pair of captures (images or videos) of the same scene at different times. Accurately identifying verifiable changes is extremely challenging…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Yuqun Wu , Chih-hao Lin , Henry Che , Aditi Tiwari , Chuhang Zou , Shenlong Wang , Derek Hoiem

Describing images with text is a fundamental problem in vision-language research. Current studies in this domain mostly focus on single image captioning. However, in various real applications (e.g., image editing, difference interpretation,…

Computation and Language · Computer Science 2019-06-20 Hao Tan , Franck Dernoncourt , Zhe Lin , Trung Bui , Mohit Bansal

The vast amount of unlabeled multi-temporal and multi-sensor remote sensing data acquired by the many Earth Observation satellites present a challenge for change detection. Recently, many generative model-based methods have been proposed…

Image and Video Processing · Electrical Eng. & Systems 2022-02-16 Yuxing Chen , Lorenzo Bruzzone

Visual Spatial Description (VSD) aims to generate texts that describe the spatial relationships between objects within images. Traditional visual spatial relationship classification (VSRC) methods typically output the spatial relationship…

Computer Vision and Pattern Recognition · Computer Science 2024-10-31 Yizhang Jin , Jian Li , Jiangning Zhang , Jianlong Hu , Zhenye Gan , Xin Tan , Yong Liu , Yabiao Wang , Chengjie Wang , Lizhuang Ma

Change Captioning is a task that aims to describe the difference between images with natural language. Most existing methods treat this problem as a difference judgment without the existence of distractors, such as viewpoint changes.…

Computer Vision and Pattern Recognition · Computer Science 2020-10-01 Xiangxi Shi , Xu Yang , Jiuxiang Gu , Shafiq Joty , Jianfei Cai

Publicly available satellite imagery can be an ubiquitous, cheap, and powerful tool for vehicle localisation when a prior sensor map is unavailable. However, satellite images are not directly comparable to data from ground range sensors…

Robotics · Computer Science 2020-09-24 Tim Y. Tang , Daniele De Martini , Shangzhe Wu , Paul Newman

Despite recent progress in computer vision, fine-grained interpretation of satellite images remains challenging because of a lack of labeled training data. To overcome this limitation, we propose using Wikipedia as a previously untapped…

Computer Vision and Pattern Recognition · Computer Science 2018-09-28 Evan Sheehan , Burak Uzkent , Chenlin Meng , Zhongyi Tang , Marshall Burke , David Lobell , Stefano Ermon

Detecting changed regions in paired satellite images plays a key role in many remote sensing applications. The evolution of recent techniques could provide satellite images with very high spatial resolution (VHR) but made it challenging to…

Image and Video Processing · Electrical Eng. & Systems 2021-12-08 Caijun Ren , Xiangyu Wang , Jian Gao , Huanhuan Chen

Up-to-date High-Definition (HD) maps are essential for self-driving cars. To achieve constantly updated HD maps, we present a deep neural network (DNN), Diff-Net, to detect changes in them. Compared to traditional methods based on object…

Computer Vision and Pattern Recognition · Computer Science 2021-10-19 Lei He , Shengjie Jiang , Xiaoqing Liang , Ning Wang , Shiyu Song

With the growing capabilities of modern object detection networks and datasets to train them, it has gotten more straightforward and, importantly, less laborious to get up and running with a model that is quite adept at detecting any number…

Machine Learning · Computer Science 2023-12-19 Grant Rosario , David Noever

Accurately maintaining digital street maps is labor-intensive. To address this challenge, much work has studied automatically processing geospatial data sources such as GPS trajectories and satellite images to reduce the cost of maintaining…

Computer Vision and Pattern Recognition · Computer Science 2021-10-14 Favyen Bastani , Songtao He , Satvat Jagwani , Mohammad Alizadeh , Hari Balakrishnan , Sanjay Chawla , Sam Madden , Mohammad Amin Sadeghi

Recent multi-modal contrastive learning models have demonstrated the ability to learn an embedding space suitable for building strong vision classifiers, by leveraging the rich information in large-scale image-caption datasets. Our work…

Machine Learning · Computer Science 2023-02-09 Yuhui Zhang , Jeff Z. HaoChen , Shih-Cheng Huang , Kuan-Chieh Wang , James Zou , Serena Yeung

For change detection in remote sensing, constructing a training dataset for deep learning models is difficult due to the requirements of bi-temporal supervision. To overcome this issue, single-temporal supervision which treats change labels…

Computer Vision and Pattern Recognition · Computer Science 2022-12-21 Minseok Seo , Hakjin Lee , Yongjin Jeon , Junghoon Seo

Contrastive pre-trained vision-language models, such as CLIP, demonstrate strong generalization abilities in zero-shot classification by leveraging embeddings extracted from image and text encoders. This paper aims to robustly fine-tune…

Computer Vision and Pattern Recognition · Computer Science 2025-11-14 Satoshi Suzuki , Shin'ya Yamaguchi , Shoichiro Takeda , Taiga Yamane , Naoki Makishima , Naotaka Kawata , Mana Ihori , Tomohiro Tanaka , Shota Orihashi , Ryo Masumura

Change detection (CD) identifies scene changes from multi-temporal observations and is widely used in urban development and environmental monitoring. Most existing CD methods rely on supervised learning, making performance strongly…

Computer Vision and Pattern Recognition · Computer Science 2025-12-19 Ziqiang Zhu , Bowei Yang

The goal of this paper is to detect what has changed, if anything, between two "in the wild" images of the same 3D scene acquired from different camera positions and at different temporal instances. The open-set nature of this problem,…

Computer Vision and Pattern Recognition · Computer Science 2023-09-12 Ragav Sachdeva , Andrew Zisserman

In recent years, the satellite videos have been captured by a moving satellite platform. In contrast to consumer, movie, and common surveillance videos, satellite video can record the snapshot of the city-scale scene. In a broad…

Computer Vision and Pattern Recognition · Computer Science 2018-07-06 Wei Ao , Yanwei Fu , Feng Xu