大模型推理能力 - arXivDaily 专题

2206.08500 2022-06-20 cs.CV cs.LG cs.RO 57%

What do navigation agents learn about their environment?

Kshitij Dwivedi, Gemma Roig, Aniruddha Kembhavi, Roozbeh Mottaghi

专题命中视觉空间推理：reasoning(abstract)；分类 cs.LG

Comments CVPR 2022

2206.00393 2022-06-02 cs.SD cs.CV cs.LG cs.RO eess.AS 57%

Towards Generalisable Audio Representations for Audio-Visual Navigation

Shunqi Mao, Chaoyi Zhang, Heng Wang, Weidong Cai

专题命中视觉空间推理：planning(abstract)；分类 cs.LG

Comments CVPR 2022 Embodied AI Workshop

2204.00879 2022-04-05 cs.CL 57%

Co-VQA : Answering by Interactive Sub Question Sequence

Ruonan Wang, Yuxi Qian, Fangxiang Feng, Xiaojie Wang, Huixing Jiang

专题命中视觉空间推理：reasoning(abstract)；分类 cs.CL

Comments Accepted by Findings of ACL 2022

2203.05784 2022-03-14 eess.IV cs.AI cs.CV 57%

AI-enabled Automatic Multimodal Fusion of Cone-Beam CT and Intraoral Scans for Intelligent 3D Tooth-Bone Reconstruction and Clinical Applications

Jin Hao, Jiaxiang Liu, Jin Li, Wei Pan, Ruizhe Chen, Huimin Xiong, Kaiwei Sun, Hangzheng Lin, Wanlu Liu, Wanghui Ding, Jianfei Yang, Haoji Hu, Yueling Zhang, Yang Feng, Zeyu Zhao, Huikai Wu, Youyi Zheng, Bing Fang, Zuozhu Liu, Zhihe Zhao

专题命中视觉空间推理：planning(abstract)；分类 cs.AI

Comments 30 pages, 6 figures, 3 tables

2106.08417 2022-03-08 cs.CV cs.LG cs.RO 57%

Scene Transformer: A unified architecture for predicting multiple agent trajectories

Jiquan Ngiam, Benjamin Caine, Vijay Vasudevan, Zhengdong Zhang, Hao-Tien Lewis Chiang, Jeffrey Ling, Rebecca Roelofs, Alex Bewley, Chenxi Liu, Ashish Venugopal, David Weiss, Ben Sapp, Zhifeng Chen, Jonathon Shlens

专题命中视觉空间推理：planning(abstract)；分类 cs.LG

Comments ICLR 2022

2104.12446 2022-03-04 cs.CV cs.LG cs.RO 57%

Heterogeneous-Agent Trajectory Forecasting Incorporating Class Uncertainty

Boris Ivanovic, Kuan-Hui Lee, Pavel Tokmakov, Blake Wulfe, Rowan McAllister, Adrien Gaidon, Marco Pavone

专题命中视觉空间推理：reasoning(abstract)；分类 cs.LG

Comments 15 pages, 15 figures, 6 tables

2111.13299 2022-03-01 eess.IV cs.CV cs.LG 57%

Exploiting full Resolution Feature Context for Liver Tumor and Vessel Segmentation via Integrate Framework: Application to Liver Tumor and Vessel 3D Reconstruction under embedded microprocessor

Xiangyu Meng, Xudong Zhang, Gan Wang, Ying Zhang, Xin Shi, Huanhuan Dai, Zixuan Wang, Xun Wang

专题命中视觉空间推理：reasoning(abstract)；分类 cs.LG

Comments 11 pages, 6 Figures

2202.09646 2022-02-22 cs.AI cs.RO cs.SY eess.SY 57%

Navigating Conceptual Space; A new take on Artificial General Intelligence

Per R. Leikanger

专题命中视觉空间推理：reasoning(abstract)；分类 cs.AI

Comments Featured in the conference of Artificial General Intelligence 2021. Part of the Lecture Notes in Computer Science book series (LNCS, volume 13154) and Lecture Notes in Artificial Intelligence book sub series (LNAI, volume 13154)

Journal ref Electronic ISSN 1611-3349 Lecture Notes in Computer Science 2021

2201.12899 2022-02-08 cs.NI cs.LG 57%

Interpretable AI-based Large-scale 3D Pathloss Prediction Model for enabling Emerging Self-Driving Networks

Usama Masood, Hasan Farooq, Ali Imran, Adnan Abu-Dayya

专题命中视觉空间推理：planning(abstract)；分类 cs.LG

Comments Accepted at IEEE Transactions on Mobile Computing

2112.07596 2021-12-15 cs.AI cs.LO 57%

Rushing and Strolling among Answer Sets -- Navigation Made Easy

Johannes K. Fichte, Sarah Alice Gaggl, Dominik Rusovac

专题命中视觉空间推理：reasoning(abstract)；分类 cs.AI

2111.15144 2021-12-01 stat.ML cs.LG q-bio.BM q-bio.QM 57%

Decoding the Protein-ligand Interactions Using Parallel Graph Neural Networks

Carter Knutson, Mridula Bontha, Jenna A. Bilbrey, Neeraj Kumar

专题命中视觉空间推理：reasoning(abstract)；分类 cs.LG

2107.03438 2021-11-08 cs.RO cs.CL cs.CV 57%

LanguageRefer: Spatial-Language Model for 3D Visual Grounding

Junha Roh, Karthik Desingh, Ali Farhadi, Dieter Fox

专题命中视觉空间推理：reasoning(abstract)；分类 cs.CL

Comments 11 pages, 3 figures

2111.01364 2021-11-03 cs.AI 57%

Learning to Explore by Reinforcement over High-Level Options

Liu Juncheng, McCane Brendan, Mills Steven

专题命中视觉空间推理：planning(abstract)；分类 cs.AI

2102.04760 2021-10-11 cs.CV cs.AI 57%

Improving Scene Graph Classification by Exploiting Knowledge from Texts

Sahand Sharifzadeh, Sina Moayed Baharlou, Martin Schmitt, Hinrich Schütze, Volker Tresp

专题命中视觉空间推理：reasoning(abstract)；分类 cs.AI

2109.11288 2021-09-24 cs.RO cs.LG 57%

Enhancing Navigational Safety in Crowded Environments using Semantic-Deep-Reinforcement-Learning-based Navigation

Linh Kästner, Junhui Li, Zhengcheng Shen, Jens Lambrecht

专题命中视觉空间推理：planning(abstract)；分类 cs.LG

Comments 7 pages, 5 figures, 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

2105.08756 2021-08-18 cs.CV cs.LG 57%

Pathdreamer: A World Model for Indoor Navigation

Jing Yu Koh, Honglak Lee, Yinfei Yang, Jason Baldridge, Peter Anderson

专题命中视觉空间推理：planning(abstract)；分类 cs.LG

Comments In ICCV 2021

2108.06180 2021-08-16 cs.AI cs.CV 57%

SPACE: A Simulator for Physical Interactions and Causal Learning in 3D Environments

Jiafei Duan, Samson Yu Bai Jian, Cheston Tan

专题命中视觉空间推理：reasoning(abstract)；分类 cs.AI

Comments Accepted to ICCV 21, Simulation Technology for Embodied AI (SEAI) Workshop

2107.01151 2021-07-21 cs.CV cs.AI cs.RO 57%

Collaborative Visual Navigation

Haiyang Wang, Wenguan Wang, Xizhou Zhu, Jifeng Dai, Liwei Wang

专题命中视觉空间推理：planning(abstract)；分类 cs.AI

2107.00541 2021-07-02 cs.LG cs.RO 57%

Goal-Conditioned Reinforcement Learning with Imagined Subgoals

Elliot Chane-Sane, Cordelia Schmid, Ivan Laptev

专题命中视觉空间推理：reasoning(abstract)；分类 cs.LG

Comments ICML 2021. See the project webpage at https://www.di.ens.fr/willow/research/ris/

2009.07526 2021-06-09 cs.CV cs.CL cs.MM 57%

CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation

Jing Yu, Yuan Chai, Yujing Wang, Yue Hu, Qi Wu

专题命中视觉空间推理：reasoning(abstract)；分类 cs.CL

Comments Accepted by IJCAI 2021. SOLE copyright holder is IJCAI (International Joint Conferences on Artificial Intelligence)

2104.14040 2021-05-04 cs.CV cs.AI cs.RO 57%

Pushing it out of the Way: Interactive Visual Navigation

Kuo-Hao Zeng, Luca Weihs, Ali Farhadi, Roozbeh Mottaghi

专题命中视觉空间推理：planning(abstract)；分类 cs.AI

Comments 14 pages, 13 figures, CVPR 2021, https://prior.allenai.org/projects/interactive-visual-navigation, https://youtu.be/GvTI5XCMvPw

2103.16095 2021-03-31 cs.RO cs.AI cs.CV 57%

Reconstructing Interactive 3D Scenes by Panoptic Mapping and CAD Model Alignments

Muzhi Han, Zeyu Zhang, Ziyuan Jiao, Xu Xie, Yixin Zhu, Song-Chun Zhu, Hangxin Liu

专题命中视觉空间推理：reasoning(abstract)；分类 cs.AI

Comments ICRA 2021 paper. Project: https://sites.google.com/view/icra2021-reconstruction

2010.08473 2020-10-19 cs.RO cs.AI 57%

SMAC: Symbiotic Multi-Agent Construction

Caleb Wagner, Neel Dhanaraj, Trevor Rizzo, Josue Contreras, Hannan Liang, Gregory Lewin, Carlo Pinciroli

专题命中视觉空间推理：planning(abstract)；分类 cs.AI

Comments 8 pages, submitted to RAL-IROS2021

2010.04551 2020-10-12 cs.AI cs.NE 57%

AI Centered on Scene Fitting and Dynamic Cognitive Network

Feng Chen

专题命中视觉空间推理：reasoning(abstract)；分类 cs.AI

2008.01227 2020-08-05 cs.MA cs.AI 57%

A Combination of Theta*, ORCA and Push and Rotate for Multi-agent Navigation

Stepan Dergachev, Konstantin Yakovlev, Ryhor Prakapovich

专题命中视觉空间推理：planning(abstract)；分类 cs.AI

Comments This is a preprint of the paper accepted to ICR'20. It contains 12 pages and 7 figures

2008.00456 2020-08-04 cs.RO cs.CV cs.LG 57%

Hindsight for Foresight: Unsupervised Structured Dynamics Models from Physical Interaction

Iman Nematollahi, Oier Mees, Lukas Hermann, Wolfram Burgard

专题命中视觉空间推理：planning(abstract)；分类 cs.LG

Comments Accepted at the 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

2007.00643 2020-07-03 cs.CV cs.LG cs.RO 57%

Object Goal Navigation using Goal-Oriented Semantic Exploration

Devendra Singh Chaplot, Dhiraj Gandhi, Abhinav Gupta, Ruslan Salakhutdinov

专题命中视觉空间推理：planning(abstract)；分类 cs.LG

Comments Winner of the CVPR 2020 AI-Habitat Object Goal Navigation Challenge. See the project webpage at https://devendrachaplot.github.io/projects/semantic-exploration.html

2005.02153 2020-05-06 cs.CV cs.LG stat.ML 57%

Improving Target-driven Visual Navigation with Attention on 3D Spatial Relationships

Yunlian Lv, Ning Xie, Yimin Shi, Zijiao Wang, Heng Tao Shen

专题命中视觉空间推理：reasoning(abstract)；分类 cs.LG

Comments 12 pages, 9 figures

1911.06258 2020-03-26 cs.CV cs.CL 57%

Iterative Answer Prediction with Pointer-Augmented Multimodal Transformers for TextVQA

Ronghang Hu, Amanpreet Singh, Trevor Darrell, Marcus Rohrbach

专题命中视觉空间推理：reasoning(abstract)；分类 cs.CL

Comments CVPR 2020

2003.06745 2020-03-17 cs.CV cs.CL 57%

Vision-Dialog Navigation by Exploring Cross-modal Memory

Yi Zhu, Fengda Zhu, Zhaohuan Zhan, Bingqian Lin, Jianbin Jiao, Xiaojun Chang, Xiaodan Liang

专题命中视觉空间推理：reasoning(abstract)；分类 cs.CL

Comments CVPR2020

1. 视觉空间推理 3363 篇

What do navigation agents learn about their environment?

Towards Generalisable Audio Representations for Audio-Visual Navigation

Co-VQA : Answering by Interactive Sub Question Sequence

AI-enabled Automatic Multimodal Fusion of Cone-Beam CT and Intraoral Scans for Intelligent 3D Tooth-Bone Reconstruction and Clinical Applications

Scene Transformer: A unified architecture for predicting multiple agent trajectories

Heterogeneous-Agent Trajectory Forecasting Incorporating Class Uncertainty

Exploiting full Resolution Feature Context for Liver Tumor and Vessel Segmentation via Integrate Framework: Application to Liver Tumor and Vessel 3D Reconstruction under embedded microprocessor

Navigating Conceptual Space; A new take on Artificial General Intelligence

Interpretable AI-based Large-scale 3D Pathloss Prediction Model for enabling Emerging Self-Driving Networks

Rushing and Strolling among Answer Sets -- Navigation Made Easy

Decoding the Protein-ligand Interactions Using Parallel Graph Neural Networks

LanguageRefer: Spatial-Language Model for 3D Visual Grounding

Learning to Explore by Reinforcement over High-Level Options

Improving Scene Graph Classification by Exploiting Knowledge from Texts

Enhancing Navigational Safety in Crowded Environments using Semantic-Deep-Reinforcement-Learning-based Navigation

Pathdreamer: A World Model for Indoor Navigation

SPACE: A Simulator for Physical Interactions and Causal Learning in 3D Environments

Collaborative Visual Navigation

Goal-Conditioned Reinforcement Learning with Imagined Subgoals

CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation

Pushing it out of the Way: Interactive Visual Navigation

Reconstructing Interactive 3D Scenes by Panoptic Mapping and CAD Model Alignments

SMAC: Symbiotic Multi-Agent Construction

AI Centered on Scene Fitting and Dynamic Cognitive Network

A Combination of Theta*, ORCA and Push and Rotate for Multi-agent Navigation

Hindsight for Foresight: Unsupervised Structured Dynamics Models from Physical Interaction

Object Goal Navigation using Goal-Oriented Semantic Exploration

Improving Target-driven Visual Navigation with Attention on 3D Spatial Relationships

Iterative Answer Prediction with Pointer-Augmented Multimodal Transformers for TextVQA

Vision-Dialog Navigation by Exploring Cross-modal Memory