paper-with-me

홈 › Papers

Room-and-Object Aware Knowledge Reasoning for Remote Embodied Referring Expression

2021-06-19 · CVPR 2021 1 · Chen Gao, Jinyu Chen, Si Liu, Luting Wang, Qiong Zhang, Qi Wu

The Remote Embodied Referring Expression (REVERIE) is a recently raised task that requires an agent to navigate to and localise a referred remote object according to a high-level language instruction. Different from related VLN tasks, the key to REVERIE is to conduct goal-oriented exploration instead of strict instruction-following, due to the lack of step-by-step navigation guidance. In this paper, we propose a novel Cross-modality Knowledge Reasoning (CKR) model to address the unique challenges of this task. The CKR, based on a transformer-architecture, learns to generate scene memory tokens and utilise these informative history clues for exploration. Particularly, a Room-and-Object Aware Attention (ROAA) mechanism is devised to explicitly perceive the room- and object-type information from both linguistic and visual observations. Moreover, through incorporating commonsense knowledge, we propose a Knowledge-enabled Entity Relationship Reasoning (KERR) module to learn the internal-external correlations among room- and object-entities for agent to make proper action at each viewpoint. Evaluation on REVERIE benchmark demonstrates the superiority of the CKR model, which significantly boosts SPL and REVERIE-success rate by 64.67% and 46.05%, respectively. Code is available at: https://github.com/alloldman/CKR.

📄 PDF Abstract BibTeX

Code (1)

alloldman/CKR 공식 구현 pytorch

Tasks

Instruction FollowingNavigateObjectReferring Expression

Methods 이 논문이 사용한 방법론

AWARE We propose to theoretically and empirically examine the effect of incorporating weighting schemes into walk-aggregating GNNs. To this end, we propose a simple, interpretable, and…

Similar Papers 제목 키워드 기반

Layout-aware Dreamer for Embodied Referring Expression Grounding

2022-11-30 · Mingxiao Li, Zehao Wang, Tinne Tuytelaars, Marie-Francine Moens

In this work, we study the problem of Embodied Referring Expression Grounding, where an agent needs to navigate in a previously unseen environment and localize a remote object described by a concise high-level natural la…

Common Sense ReasoningNavigateReferring Expression

MMR: A Large-scale Benchmark Dataset for Multi-target and Multi-granularity Reasoning Segmentation

2025-03-18 · Donggon Jang, Yucheol Cho, SuIn Lee, Taehyeon Kim 외

The fusion of Large Language Models with vision models is pioneering new possibilities in user-interactive vision-language tasks. A notable application is reasoning segmentation, where models generate pixel-level segment…

ObjectReasoning SegmentationSegmentation

CAIRN: Cross-Room 3D Scene Understanding with Topology-Aware Large Multimodal Models

2026-07-07 · He Liang, Chenyang Ma, Yiming Zhang, Sangyun Shin 외 arxiv

Existing 3D scene-grounded Large Language Models (3D-LLMs) focus on answering questions grounded in simplified single-room 3D scenes, lacking the ability to reason over real-world household environments containing multip…

Graph Neural NetworkScene Understanding

March in Chat: Interactive Prompting for Remote Embodied Referring Expression

2023-08-20 · ICCV 2023 1 · Yanyuan Qiao, Yuankai Qi, Zheng Yu, Jing Liu 외

Many Vision-and-Language Navigation (VLN) tasks have been proposed in recent years, from room-based to object-based and indoor to outdoor. The REVERIE (Remote Embodied Referring Expression) is interesting since it only p…

Referring ExpressionVision and Language Navigation

Think and Answer ME: Benchmarking and Exploring Multi-Entity Reasoning Grounding in Remote Sensing

2026-03-13 · Shuchang Lyu, Haiquan Wen, Guangliang Cheng, Meng Li 외 arxiv

Recent advances in reasoning language models and reinforcement learning with verifiable rewards have significantly enhanced multi-step reasoning capabilities. This progress motivates the extension of reasoning paradigms …

Reinforcement LearningVisual Grounding