中文
相关论文

相关论文: Discriminative Triad Matching and Reconstruction f…

200 篇论文

Most models tasked to ground referential utterances in 2D and 3D scenes learn to select the referred object from a pool of object proposals provided by a pre-trained detector. This is limiting because an utterance may refer to visual…

计算机视觉与模式识别 · 计算机科学 2022-07-22 Ayush Jain , Nikolaos Gkanatsios , Ishita Mediratta , Katerina Fragkiadaki

We present DRACO, a method for Dense Reconstruction And Canonicalization of Object shape from one or more RGB images. Canonical shape reconstruction, estimating 3D object shape in a coordinate space canonicalized for scale, rotation, and…

计算机视觉与模式识别 · 计算机科学 2020-11-26 Rahul Sajnani , AadilMehdi Sanchawala , Krishna Murthy Jatavallabhula , Srinath Sridhar , K. Madhava Krishna

Most referring object detection (ROD) models, especially the modern grounding detectors, are designed for data-rich conditions, yet many practical deployments, such as robotics, augmented reality, and other specialized domains, would face…

计算机视觉与模式识别 · 计算机科学 2026-03-26 Xu Zhang , Zhe Chen , Jing Zhang , Dacheng Tao

Referring Expression Comprehension (REC) links language to region level visual perception. Standard benchmarks (RefCOCO, RefCOCO+, RefCOCOg) have progressed rapidly with multimodal LLMs but remain weak tests of visual reasoning and…

计算机视觉与模式识别 · 计算机科学 2026-03-02 Qihua Dong , Kuo Yang , Lin Ju , Handong Zhao , Yitian Zhang , Yizhou Wang , Huimin Zeng , Jianglin Lu , Yun Fu

In this paper, we investigate how to achieve better visual grounding with modern vision-language transformers, and propose a simple yet powerful Selective Retraining (SiRi) mechanism for this challenging task. Particularly, SiRi conveys a…

计算机视觉与模式识别 · 计算机科学 2022-07-28 Mengxue Qu , Yu Wu , Wu Liu , Qiqi Gong , Xiaodan Liang , Olga Russakovsky , Yao Zhao , Yunchao Wei

One common belief is that with complex models and pre-training on large-scale datasets, transformer-based methods for referring expression comprehension (REC) perform much better than existing graph-based methods. We observe that since most…

计算机视觉与模式识别 · 计算机科学 2024-09-06 Jingcheng Ke , Dele Wang , Jun-Cheng Chen , I-Hong Jhuo , Chia-Wen Lin , Yen-Yu Lin

In this paper, we address the problem of referring expression comprehension in videos, which is challenging due to complex expression and scene dynamics. Unlike previous methods which solve the problem in multiple stages (i.e., tracking,…

计算机视觉与模式识别 · 计算机科学 2021-03-24 Sijie Song , Xudong Lin , Jiaying Liu , Zongming Guo , Shih-Fu Chang

This paper explores the weakly-supervised referring image segmentation (WRIS) problem, and focuses on a challenging setup where target localization is learned directly from image-text pairs. We note that the input text description typically…

计算机视觉与模式识别 · 计算机科学 2024-12-05 Zaiquan Yang , Yuhao Liu , Jiaying Lin , Gerhard Hancke , Rynson W. H. Lau

3D visual grounding aims to automatically locate the 3D region of the specified object given the corresponding textual description. Existing works fail to distinguish similar objects especially when multiple referred objects are involved in…

计算机视觉与模式识别 · 计算机科学 2024-03-14 Feng Xiao , Hongbin Xu , Qiuxia Wu , Wenxiong Kang

We study the problem of weakly supervised grounded image captioning. That is, given an image, the goal is to automatically generate a sentence describing the context of the image with each noun word grounded to the corresponding region in…

计算机视觉与模式识别 · 计算机科学 2021-08-24 Nenglun Chen , Xingjia Pan , Runnan Chen , Lei Yang , Zhiwen Lin , Yuqiang Ren , Haolei Yuan , Xiaowei Guo , Feiyue Huang , Wenping Wang

Sentence representation models trained only on language could potentially suffer from the grounding problem. Recent work has shown promising results in improving the qualities of sentence representations by jointly training them with…

计算与语言 · 计算机科学 2017-12-05 Kang Min Yoo , Youhyun Shin , Sang-goo Lee

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…

计算机视觉与模式识别 · 计算机科学 2019-07-03 Hanwang Zhang , Yulei Niu , Shih-Fu Chang

Symbolic regression aims to recover closed-form expressions from numerical data, but in differentiable symbolic regression the recovered expression depends not only on the grammar but also on the fixed architecture through which variables…

神经与进化计算 · 计算机科学 2026-05-29 Chakshu Gupta , Theodore J. LaGrow

Different from universal object detection, referring expression comprehension (REC) aims to locate specific objects referred to by natural language expressions. The expression provides high-level concepts of relevant visual and contextual…

计算机视觉与模式识别 · 计算机科学 2023-06-08 Wei Su , Peihan Miao , Huanzhang Dou , Yongjian Fu , Xi Li

3D Visual Grounding (3DVG) aims to localize the referent of natural language referring expressions through two core tasks: Referring Expression Comprehension (3DREC) and Segmentation (3DRES). While existing methods achieve high accuracy in…

计算机视觉与模式识别 · 计算机科学 2026-03-19 Wenbin Tan , Jiawen Lin , Fangyong Wang , Yuan Xie , Yong Xie , Yachao Zhang , Yanyun Qu

Referring expression segmentation (RES) aims at segmenting the foreground masks of the entities that match the descriptive natural language expression. Previous datasets and methods for classic RES task heavily rely on the prior assumption…

计算机视觉与模式识别 · 计算机科学 2024-03-22 Wenxuan Wang , Tongtian Yue , Yisi Zhang , Longteng Guo , Xingjian He , Xinlong Wang , Jing Liu

Video moment localization aims to retrieve the target segment of an untrimmed video according to the natural language query. Weakly supervised methods gains attention recently, as the precise temporal location of the target segment is not…

计算机视觉与模式识别 · 计算机科学 2023-10-17 Zezhong Lv , Bing Su , Ji-Rong Wen

Capturing the 3D geometry of transparent objects is a challenging task, ill-suited for general-purpose scanning and reconstruction techniques, since these cannot handle specular light transport phenomena. Existing state-of-the-art methods,…

图形学 · 计算机科学 2020-09-22 Jiahui Lyu , Bojian Wu , Dani Lischinski , Daniel Cohen-Or , Hui Huang

Weakly Supervised Object Localization (WSOL) aims to localize objects with image-level supervision. Existing works mainly rely on Class Activation Mapping (CAM) derived from a classification model. However, CAM-based methods usually focus…

计算机视觉与模式识别 · 计算机科学 2022-05-30 Jilan Xu , Junlin Hou , Yuejie Zhang , Rui Feng , Rui-Wei Zhao , Tao Zhang , Xuequan Lu , Shang Gao

Referring Camouflaged Object Detection (Ref-COD) segments specified camouflaged objects in a scene by leveraging a small set of referring images. Though effective, current systems adopt a dual-branch design that requires reference images at…

计算机视觉与模式识别 · 计算机科学 2025-11-27 Yu-Huan Wu , Zi-Xuan Zhu , Yan Wang , Liangli Zhen , Deng-Ping Fan