paper-with-me

Papers

Agent-Centric Relation Graph for Object Visual Navigation

2021-11-29 · Xiaobo Hu, Youfang Lin, Shuo Wang, Zhihao Wu, Kai Lv

Object visual navigation aims to steer an agent toward a target object based on visual observations. It is highly desirable to reasonably perceive the environment and accurately control the agent. In the navigation task, we introduce an Agent-Centric Relation Graph (ACRG) for learning the visual representation based on the relationships in the environment. ACRG is a highly effective structure that consists of two relationships, i.e., the horizontal relationship among objects and the distance relationship between the agent and objects . On the one hand, we design the Object Horizontal Relationship Graph (OHRG) that stores the relative horizontal location among objects. On the other hand, we propose the Agent-Target Distance Relationship Graph (ATDRG) that enables the agent to perceive the distance between the target and objects. For ATDRG, we utilize image depth to obtain the target distance and imply the vertical location to capture the distance relationship among objects in the vertical direction. With the above graphs, the agent can perceive the environment and output navigation actions. Experimental results in the artificial environment AI2-THOR demonstrate that ACRG significantly outperforms other state-of-the-art methods in unseen testing environments.

📄 PDF Abstract BibTeX arXiv:2111.14422

Code (0)

등록된 구현이 없습니다.

Tasks

ObjectRelationVisual Navigation

Similar Papers 제목 키워드 기반

Zero-Shot Object Goal Visual Navigation With Class-Independent Relationship Network

2023-10-15 · Xinting Li, Shiguang Zhang, Yue Lu, Kerry Dang 외

This paper investigates the zero-shot object goal visual navigation problem. In the object goal visual navigation task, the agent needs to locate navigation targets from its egocentric visual input. "Zero-shot" means tha…

ObjectSemantic SimilaritySemantic Textual SimilarityVisual Navigation

Deep Reinforcement Learning via Object-Centric Attention

2025-04-03 · Jannis Blüml, Cedric Derstroff, Bjarne Gregori, Elisabeth Dillies 외

Deep reinforcement learning agents, trained on raw pixel inputs, often fail to generalize beyond their training environments, relying on spurious correlations and irrelevant background details. To address this issue, obj…

Deep Reinforcement LearningInductive BiasObjectreinforcement-learning+1

Image-Level Attentional Context Modeling Using Nested-Graph Neural Networks

2018-11-09 · Guillaume Jaume, Behzad Bozorgtabar, Hazim Kemal Ekenel, Jean-Philippe Thiran 외

We introduce a new scene graph generation method called image-level attentional context modeling (ILAC). Our model includes an attentional graph network that effectively propagates contextual information across the graph…

Graph GenerationGraph Neural NetworkObjectScene Graph Generation

UNO: Unifying One-stage Video Scene Graph Generation via Object-Centric Visual Representation Learning

2025-09-07 · Huy Le, Nhat Chung, Tung Kieu, Jingkang Yang 외 arxiv

Video Scene Graph Generation (VidSGG) aims to represent dynamic visual content by detecting objects and modeling their temporal interactions as structured graphs. Prior studies typically target either coarse-grained box-…

Video scene graph generationRepresentation Learning

SEMBED: Semantic Embedding of Egocentric Action Videos

2016-07-28 · Michael Wray, Davide Moltisanti, Walterio Mayol-Cuevas, Dima Damen

We present SEMBED, an approach for embedding an egocentric object interaction video in a semantic-visual graph to estimate the probability distribution over its potential semantic labels. When object interactions are ann…

General ClassificationObject