English
Related papers

Related papers: ZSON: Zero-Shot Object-Goal Navigation using Multi…

200 papers

Object detection is considered as one of the most challenging problems in computer vision, since it requires correct prediction of both classes and locations of objects in images. In this study, we define a more difficult scenario, namely…

Computer Vision and Pattern Recognition · Computer Science 2019-07-16 Berkan Demirel , Ramazan Gokberk Cinbis , Nazli Ikizler-Cinbis

In this paper we consider a version of the zero-shot learning problem where seen class source and target domain data are provided. The goal during test-time is to accurately predict the class label of an unseen target domain instance based…

Computer Vision and Pattern Recognition · Computer Science 2015-09-29 Ziming Zhang , Venkatesh Saligrama

This paper presents a framework for training an agent to actively request help in object-goal navigation tasks, with feedback indicating the location of the target object in its field of view. To make the agent more robust in scenarios…

Machine Learning · Computer Science 2023-03-29 Jenny Zhang , Samson Yu , Jiafei Duan , Cheston Tan

Zero-shot learning (ZSL) for image classification focuses on recognizing novel categories that have no labeled data available for training. The learning is generally carried out with the help of mid-level semantic descriptors associated…

Computer Vision and Pattern Recognition · Computer Science 2019-03-29 Debasmit Das , C. S. George Lee

Learning to navigate in a realistic setting where an agent must rely solely on visual inputs is a challenging task, in part because the lack of position information makes it difficult to provide supervision during training. In this paper,…

Computer Vision and Pattern Recognition · Computer Science 2023-01-06 Lina Mezghani , Sainbayar Sukhbaatar , Arthur Szlam , Armand Joulin , Piotr Bojanowski

Visual navigation in unknown environments based solely on natural language descriptions is a key capability for intelligent robots. In this work, we propose a navigation framework built upon off-the-shelf Visual Language Models (VLMs),…

Robotics · Computer Science 2025-08-08 Weifan Zhang , Tingguang Li , Yuzhen Liu

In this paper, we introduce the Semantic Environment Atlas (SEA), a novel mapping approach designed to enhance visual navigation capabilities of embodied agents. The SEA utilizes semantic graph maps that intricately delineate the…

Artificial Intelligence · Computer Science 2024-10-15 Nuri Kim , Jeongho Park , Mineui Hong , Songhwai Oh

Deep-learning and large scale language-image training have produced image object detectors that generalise well to diverse environments and semantic classes. However, single-image object detectors trained on internet data are not optimally…

Robotics · Computer Science 2024-02-07 Nicolas Harvey Chapman , Feras Dayoub , Will Browne , Chris Lehnert

Image-goal navigation aims to steer an agent towards the goal location specified by an image. Most prior methods tackle this task by learning a navigation policy, which extracts visual features of goal and observation images, compares their…

Computer Vision and Pattern Recognition · Computer Science 2025-02-18 Pengna Li , Kangyi Wu , Jingwen Fu , Sanping Zhou

For embodied agents, navigation is an important ability but not an isolated goal. Agents are also expected to perform specific tasks after reaching the target location, such as picking up objects and assembling them into a particular…

Computation and Language · Computer Science 2020-11-17 Hyounghun Kim , Abhay Zala , Graham Burri , Hao Tan , Mohit Bansal

Vision-and-Language Navigation (VLN) tasks require an agent to follow textual instructions to navigate through 3D environments. Traditional approaches use supervised learning methods, relying heavily on domain-specific datasets to train VLN…

Robotics · Computer Science 2025-02-12 Yanyuan Qiao , Wenqi Lyu , Hui Wang , Zixu Wang , Zerui Li , Yuan Zhang , Mingkui Tan , Qi Wu

Interpreting object-referential language and grounding objects in 3D with spatial relations and attributes is essential for robots operating alongside humans. However, this task is often challenging due to the diversity of scenes, large…

Computer Vision and Pattern Recognition · Computer Science 2025-08-18 Nader Zantout , Haochen Zhang , Pujith Kachana , Jinkai Qiu , Guofei Chen , Ji Zhang , Wenshan Wang

Generalization is a pivotal challenge for agents following natural language instructions. To approach this goal, we leverage a vision-language model (VLM) for visual grounding and transfer its vision-language knowledge into reinforcement…

Artificial Intelligence · Computer Science 2024-08-06 Haobin Jiang , Zongqing Lu

Object-oriented embodied navigation aims to locate specific objects, defined by category or depicted in images. Existing methods often struggle to generalize to open vocabulary goals without extensive training data. While recent advances in…

Robotics · Computer Science 2024-07-15 Meng Wei , Tai Wang , Yilun Chen , Hanqing Wang , Jiangmiao Pang , Xihui Liu

How can we build robots for open-world semantic navigation tasks, like searching for target objects in novel scenes? While foundation models have the rich knowledge and generalisation needed for these tasks, a suitable scene representation…

Robotics · Computer Science 2024-07-03 Joel Loo , Zhanxin Wu , David Hsu

We propose a learning-based navigation system for reaching visually indicated goals and demonstrate this system on a real mobile robot platform. Learning provides an appealing alternative to conventional methods for robotic navigation:…

Robotics · Computer Science 2022-10-11 Dhruv Shah , Benjamin Eysenbach , Gregory Kahn , Nicholas Rhinehart , Sergey Levine

While spatial reasoning has made progress in object localization relationships, it often overlooks object orientation-a key factor in 6-DoF fine-grained manipulation. Traditional pose representations rely on pre-defined frames or templates,…

3D Visual Grounding (3DVG) is an essential capability for embodied AI, requiring agents to localize objects in 3D scenes based on natural language descriptions. Recent zero-shot methods leverage 2D vision-language models (LVLMs). However,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Cuong Huynh , Maxim Popov , Denis Gridusov , Sergey Kolyubin

This paper focuses on visual semantic navigation, the task of producing actions for an active agent to navigate to a specified target object category in an unknown environment. To complete this task, the algorithm should simultaneously…

Computer Vision and Pattern Recognition · Computer Science 2021-03-23 Yiqing Liang , Boyuan Chen , Shuran Song

As an important and challenging problem in computer vision, zero-shot learning (ZSL) aims at automatically recognizing the instances from unseen object classes without training data. To address this problem, ZSL is usually carried out in…

Computer Vision and Pattern Recognition · Computer Science 2017-03-28 Yunlong Yu , Zhong Ji , Xi Li , Jichang Guo , Zhongfei Zhang , Haibin Ling , Fei Wu