English
Related papers

Related papers: Embodied Intelligence for 3D Understanding: A Surv…

200 papers

As interest in "reformulating" the 3D Visual Question Answering (VQA) problem in the context of foundation models grows, it is imperative to assess how these new paradigms influence existing closed-vocabulary datasets. In this case study,…

Computer Vision and Pattern Recognition · Computer Science 2024-05-30 Simranjit Singh , Georgios Pavlakos , Dimitrios Stamoulis

Answering questions about the spatial properties of the environment poses challenges for existing language and vision foundation models due to a lack of understanding of the 3D world notably in terms of relationships between objects. To…

Computer Vision and Pattern Recognition · Computer Science 2024-09-17 Emilia Szymanska , Mihai Dusmanu , Jan-Willem Buurlage , Mahdi Rad , Marc Pollefeys

Video-based Question Answering (Video QA) is a challenging task and becomes even more intricate when addressing Socially Intelligent Question Answering (SIQA). SIQA requires context understanding, temporal reasoning, and the integration of…

Computer Vision and Pattern Recognition · Computer Science 2024-04-23 Aviral Agrawal , Carlos Mateo Samudio Lezcano , Iqui Balam Heredia-Marin , Prabhdeep Singh Sethi

The ability to understand and reason the 3D real world is a crucial milestone towards artificial general intelligence. The current common practice is to finetune Large Language Models (LLMs) with 3D data and texts to enable 3D…

Computer Vision and Pattern Recognition · Computer Science 2024-03-19 Sha Zhang , Di Huang , Jiajun Deng , Shixiang Tang , Wanli Ouyang , Tong He , Yanyong Zhang

The remarkable potential of multi-modal large language models (MLLMs) in comprehending both vision and language information has been widely acknowledged. However, the scarcity of 3D scenes-language pairs in comparison to their 2D…

Computer Vision and Pattern Recognition · Computer Science 2024-01-17 Zeju Li , Chao Zhang , Xiaoyan Wang , Ruilong Ren , Yifan Xu , Ruifei Ma , Xiangde Liu

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

This paper presents stacked attention networks (SANs) that learn to answer natural language questions from images. SANs use semantic representation of a question as query to search for the regions in an image that are related to the answer.…

Machine Learning · Computer Science 2016-01-27 Zichao Yang , Xiaodong He , Jianfeng Gao , Li Deng , Alex Smola

We introduce GQA, a new dataset for real-world visual reasoning and compositional question answering, seeking to address key shortcomings of previous VQA datasets. We have developed a strong and robust question engine that leverages scene…

Computation and Language · Computer Science 2019-07-12 Drew A. Hudson , Christopher D. Manning

Visual question answering (VQA) refers to the problem where, given an image and a natural language question about the image, a correct natural language answer has to be generated. A VQA model has to demonstrate both the visual understanding…

Computer Vision and Pattern Recognition · Computer Science 2024-11-19 Raihan Kabir , Naznin Haque , Md Saiful Islam , Marium-E-Jannat

3D scene understanding has gained significant attention due to its wide range of applications. However, existing methods for 3D scene understanding are limited to specific downstream tasks, which hinders their practicality in real-world…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Zehan Wang , Haifeng Huang , Yang Zhao , Ziang Zhang , Zhou Zhao

Understanding 3D scenes requires flexible combinations of visual reasoning tasks, including depth estimation, novel view synthesis, and object manipulation, all of which are essential for perception and interaction. Existing approaches have…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Wanhee Lee , Klemen Kotar , Rahul Mysore Venkatesh , Jared Watrous , Honglin Chen , Khai Loong Aw , Daniel L. K. Yamins

Robotics, autonomous driving, augmented reality, and many embodied computer vision applications must quickly react to user-defined events unfolding in real time. We address this setting by proposing a novel task for multimodal video…

Computer Vision and Pattern Recognition · Computer Science 2024-12-05 Cristobal Eyzaguirre , Eric Tang , Shyamal Buch , Adrien Gaidon , Jiajun Wu , Juan Carlos Niebles

Interactive 3D scenes are increasingly vital for embodied intelligence, yet existing datasets remain limited due to the labor-intensive process of annotating part segmentation, kinematic types, and motion trajectories. We present REACT3D, a…

Computer Vision and Pattern Recognition · Computer Science 2026-04-13 Zhao Huang , Boyang Sun , Alexandros Delitzas , Jiaqi Chen , Marc Pollefeys

Multimodal models integrating speech and vision hold significant potential for advancing human-computer interaction, particularly in Speech-Based Visual Question Answering (SBVQA) where spoken questions about images require direct…

Computer Vision and Pattern Recognition · Computer Science 2025-04-03 Bingxin Li

3D point cloud understanding is an important component in autonomous driving and robotics. In this paper, we present a novel Embedding-Querying paradigm (EQ- Paradigm) for 3D understanding tasks including detection, segmentation, and…

Computer Vision and Pattern Recognition · Computer Science 2022-05-10 Zetong Yang , Li Jiang , Yanan Sun , Bernt Schiele , Jiaya Jia

Commonsense question answering (CQA) aims to test if models can answer questions regarding commonsense knowledge that everyone knows. Prior works that incorporate external knowledge bases have shown promising results, but knowledge bases…

Computation and Language · Computer Science 2022-01-04 Zi-Yi Dou , Nanyun Peng

The matching of 3D shapes has been extensively studied for shapes represented as surface meshes, as well as for shapes represented as point clouds. While point clouds are a common representation of raw real-world 3D data (e.g. from laser…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Dongliang Cao , Florian Bernard

Recent research advances in Computer Vision and Natural Language Processing have introduced novel tasks that are paving the way for solving AI-complete problems. One of those tasks is called Visual Question Answering (VQA). A VQA system…

Computer Vision and Pattern Recognition · Computer Science 2020-07-30 Camila Kolling , Jônatas Wehrmann , Rodrigo C. Barros

This study explores innovative methods for improving Visual Question Answering (VQA) using Generative Adversarial Networks (GANs), autoencoders, and attention mechanisms. Leveraging a balanced VQA dataset, we investigate three distinct…

Computer Vision and Pattern Recognition · Computer Science 2024-11-13 Panfeng Li , Qikai Yang , Xieming Geng , Wenjing Zhou , Zhicheng Ding , Yi Nian

Large-scale pre-trained models (PTMs) show great zero-shot capabilities. In this paper, we study how to leverage them for zero-shot visual question answering (VQA). Our approach is motivated by a few observations. First, VQA questions often…

Computer Vision and Pattern Recognition · Computer Science 2024-01-25 Rui Cao , Jing Jiang