English
Related papers

Related papers: SeCG: Semantic-Enhanced 3D Visual Grounding via Cr…

200 papers

Today's most accurate language models are trained on orders of magnitude more language data than human language learners receive - but with no supervision from other sensory modalities that play a crucial role in human learning. Can we make…

Computation and Language · Computer Science 2024-03-22 Chengxu Zhuang , Evelina Fedorenko , Jacob Andreas

When connecting objects and their language referents in an embodied 3D environment, it is important to note that: (1) an object can be better characterized by leveraging comparative information between itself and other objects, and (2) an…

Computation and Language · Computer Science 2024-04-11 Chancharik Mitra , Abrar Anwar , Rodolfo Corona , Dan Klein , Trevor Darrell , Jesse Thomason

3D object grounding aims to locate the most relevant target object in a raw point cloud scene based on a free-form language description. Understanding complex and diverse descriptions, and lifting them directly to a point cloud is a new and…

Computer Vision and Pattern Recognition · Computer Science 2021-03-31 Mingtao Feng , Zhen Li , Qi Li , Liang Zhang , XiangDong Zhang , Guangming Zhu , Hui Zhang , Yaonan Wang , Ajmal Mian

Object rearrangement has recently emerged as a key competency in robot manipulation, with practical solutions generally involving object detection, recognition, grasping and high-level planning. Goal-images describing a desired scene…

Robotics · Computer Science 2021-11-16 Walter Goodwin , Sagar Vaze , Ioannis Havoutis , Ingmar Posner

Aiming to link natural language descriptions to specific regions in a 3D scene represented as 3D point clouds, 3D visual grounding is a very fundamental task for human-robot interaction. The recognition errors can significantly impact the…

Computer Vision and Pattern Recognition · Computer Science 2023-03-24 Ziyang Lu , Yunqiang Pei , Guoqing Wang , Yang Yang , Zheng Wang , Heng Tao Shen

In natural language processing, most models try to learn semantic representations merely from texts. The learned representations encode the distributional semantics but fail to connect to any knowledge about the physical world. In contrast,…

Computation and Language · Computer Science 2021-11-16 Yizhen Zhang , Minkyu Choi , Kuan Han , Zhongming Liu

Visual grounding tasks, such as referring image segmentation (RIS) and referring expression comprehension (REC), aim to localize a target object based on a given textual description. The target object in an image can be described in…

Computer Vision and Pattern Recognition · Computer Science 2025-08-19 Seonghoon Yu , Junbeom Hong , Joonseok Lee , Jeany Son

Multi-modal 3D object understanding has gained significant attention, yet current approaches often assume complete data availability and rigid alignment across all modalities. We present CrossOver, a novel framework for cross-modal 3D scene…

Computer Vision and Pattern Recognition · Computer Science 2025-04-08 Sayan Deb Sarkar , Ondrej Miksik , Marc Pollefeys , Daniel Barath , Iro Armeni

In this work, we focus on the problem of grounding language by training an agent to follow a set of natural language instructions and navigate to a target object in an environment. The agent receives visual information through raw pixels…

Computation and Language · Computer Science 2018-12-27 Akilesh B , Abhishek Sinha , Mausoom Sarkar , Balaji Krishnamurthy

The 3D weakly-supervised visual grounding task aims to localize oriented 3D boxes in point clouds based on natural language descriptions without requiring annotations to guide model learning. This setting presents two primary challenges:…

Computer Vision and Pattern Recognition · Computer Science 2025-05-06 Xiaoqi Li , Jiaming Liu , Nuowei Han , Liang Heng , Yandong Guo , Hao Dong , Yang Liu

Understanding 3D scenes from multi-view inputs has been proven to alleviate the view discrepancy issue in 3D visual grounding. However, existing methods normally neglect the view cues embedded in the text modality and fail to weigh the…

Computer Vision and Pattern Recognition · Computer Science 2023-12-06 Zoey Guo , Yiwen Tang , Ray Zhang , Dong Wang , Zhigang Wang , Bin Zhao , Xuelong Li

We introduce a novel problem, i.e., the localization of an input image within a multi-modal reference map represented by a database of 3D scene graphs. These graphs comprise multiple modalities, including object-level point clouds, images,…

Computer Vision and Pattern Recognition · Computer Science 2024-07-15 Yang Miao , Francis Engelmann , Olga Vysotska , Federico Tombari , Marc Pollefeys , Dániel Béla Baráth

3D Visual Grounding (3DVG) aims to localize objects in 3D scenes using natural language descriptions. Although supervised methods achieve higher accuracy in constrained settings, zero-shot 3DVG holds greater promise for real-world…

Computer Vision and Pattern Recognition · Computer Science 2025-08-29 Jiawen Lin , Shiran Bian , Yihang Zhu , Wenbin Tan , Yachao Zhang , Yuan Xie , Yanyun Qu

We present a new method, PARsing And visual GrOuNding (ParaGon), for grounding natural language in object placement tasks. Natural language generally describes objects and spatial relations with compositionality and ambiguity, two major…

Robotics · Computer Science 2023-03-14 Zirui Zhao , Wee Sun Lee , David Hsu

Text-guided 3D visual grounding (T-3DVG), which aims to locate a specific object that semantically corresponds to a language query from a complicated 3D scene, has drawn increasing attention in the 3D research community over the past few…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Daizong Liu , Yang Liu , Wencan Huang , Wei Hu

Visual grounding is a task that aims to locate a target object according to a natural language expression. As a multi-modal task, feature interaction between textual and visual inputs is vital. However, previous solutions mainly handle each…

Computer Vision and Pattern Recognition · Computer Science 2022-06-23 Chonghan Chen , Qi Jiang , Chih-Hao Wang , Noel Chen , Haohan Wang , Xiang Li , Bhiksha Raj

Monocular 3D Visual Grounding (Mono3DVG) is an emerging task that locates 3D objects in RGB images using text descriptions with geometric cues. However, existing methods face two key limitations. Firstly, they often over-rely on…

Computer Vision and Pattern Recognition · Computer Science 2025-11-11 Yuzhen Li , Min Liu , Zhaoyang Li , Yuan Bian , Xueping Wang , Erbo Zhai , Yaonan Wang

Multi-label image and video classification are fundamental yet challenging tasks in computer vision. The main challenges lie in capturing spatial or temporal dependencies between labels and discovering the locations of discriminative…

Computer Vision and Pattern Recognition · Computer Science 2020-03-30 Renchun You , Zhiyao Guo , Lei Cui , Xiang Long , Yingze Bao , Shilei Wen

In this paper, we study the problem of learning Graph Convolutional Networks (GCNs) for regression. Current architectures of GCNs are limited to the small receptive field of convolution filters and shared transformation matrix for each…

Computer Vision and Pattern Recognition · Computer Science 2020-03-10 Long Zhao , Xi Peng , Yu Tian , Mubbasir Kapadia , Dimitris N. Metaxas

Systems that can find correspondences between multiple modalities, such as between speech and images, have great potential to solve different recognition and data analysis tasks in an unsupervised manner. This work studies multimodal…

Computer Vision and Pattern Recognition · Computer Science 2024-03-08 Khazar Khorrami , Okko Räsänen