大模型推理能力 - arXivDaily 专题

2104.02818 2021-11-02 cs.HC 50%

Why? Why not? When? Visual Explanations of Agent Behavior in Reinforcement Learning

Aditi Mishra, Utkarsh Soni, Jinbin Huang, Chris Bryan

专题命中视觉空间推理：reasoning(abstract)

2110.08571 2021-10-19 cs.CV 50%

Explore before Moving: A Feasible Path Estimation and Memory Recalling Framework for Embodied Navigation

Yang Wu, Shirui Feng, Guanbin Li, Liang Lin

专题命中视觉空间推理：planning(abstract)

2104.11746 2021-10-19 cs.CV 50%

VidTr: Video Transformer Without Convolutions

Yanyi Zhang, Xinyu Li, Chunhui Liu, Bing Shuai, Yi Zhu, Biagio Brattoli, Hao Chen, Ivan Marsic, Joseph Tighe

专题命中视觉空间推理：reasoning(abstract)

Comments ICCV 2021 Accepted

2109.07872 2021-09-17 cs.RO 50%

Knowledge-based Embodied Question Answering

Sinan Tan, Mengmeng Ge, Di Guo, Huaping Liu, Fuchun Sun

专题命中视觉空间推理：reasoning(abstract)

2006.07034 2021-08-18 cs.CV 50%

Benchmarking Unsupervised Object Representations for Video Sequences

Marissa A. Weis, Kashyap Chitta, Yash Sharma, Wieland Brendel, Matthias Bethge, Andreas Geiger, Alexander S. Ecker

专题命中视觉空间推理：reasoning(abstract)

Journal ref Journal of Machine Learning Research 22 (183): 1-61, 2021

2108.03866 2021-08-10 cs.RO 50%

Mapless Humanoid Navigation Using Learned Latent Dynamics

Andre Brandenburger, Diego Rodriguez, Sven Behnke

专题命中视觉空间推理：planning(abstract)

Comments Accepted for IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

2106.03089 2021-07-15 cs.CV 50%

Referring Transformer: A One-step Approach to Multi-task Visual Grounding

Muchen Li, Leonid Sigal

专题命中视觉空间推理：reasoning(abstract)

2106.13667 2021-06-28 cs.RO 50%

Move Beyond Trajectories: Distribution Space Coupling for Crowd Navigation

Muchen Sun, Francesca Baldini, Peter Trautman, Todd Murphey

专题命中视觉空间推理：planning(abstract)

Comments 12 pages

Journal ref Robotics: Science and Systems, 2021

2106.11379 2021-06-23 cs.CV cs.RO 50%

BEyond observation: an approach for ObjectNav

Daniel V. Ruiz, Eduardo Todt

专题命中视觉空间推理：planning(abstract)

Comments Presented at the 2th Embodied AI Workshop at CVPR 2021

2106.05266 2021-06-10 cs.CV 50%

Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time

Shaowei Liu, Hanwen Jiang, Jiarui Xu, Sifei Liu, Xiaolong Wang

专题命中视觉空间推理：reasoning(abstract)

Comments CVPR 2021, Project page: https://stevenlsw.github.io/Semi-Hand-Object

2005.13229 2021-05-12 cs.RO 50%

3D-OGSE: Online Safe and Smooth Trajectory Generation using Generalized Shape Expansion in Unknown 3-D Environments

Vrushabh Zinage, Senthil Hariharan Arul, Dinesh Manocha, Satadal Ghosh

专题命中视觉空间推理：planning(abstract)

Comments 9 pages

2105.02061 2021-05-06 cs.CV 50%

Proposal-free One-stage Referring Expression via Grid-Word Cross-Attention

Wei Suo, Mengyang Sun, Peng Wang, Qi Wu

专题命中视觉空间推理：reasoning(abstract)

Comments To be published in the 30th International Joint Conference on Artificial Intelligence (IJCAI-2021)

2104.14741 2021-05-03 cs.CV 50%

Chop Chop BERT: Visual Question Answering by Chopping VisualBERT's Heads

Chenyu Gao, Qi Zhu, Peng Wang, Qi Wu

专题命中视觉空间推理：reasoning(abstract)

Comments 14 pages

2104.10674 2021-04-22 cs.RO 50%

Hierarchical Cross-Modal Agent for Robotics Vision-and-Language Navigation

Muhammad Zubair Irshad, Chih-Yao Ma, Zsolt Kira

专题命中视觉空间推理：reasoning(abstract)

Comments Accepted to ICRA 2021; Code and Dataset are available at https://github.com/GT-RIPL/robo-vln

2104.06132 2021-04-14 cs.SE 50%

An Agent-based Architecture for AI-Enhanced Automated Testing for XR Systems, a Short Paper

I. S. W. B. Prasetya, Samira Shirzadehhajimahmood, Saba Gholizadeh Ansari, Pedro Fernandes, Rui Prada

专题命中视觉空间推理：reasoning(abstract)

Journal ref 2021 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW)

2012.04512 2021-03-23 cs.CV cs.RO 50%

SSCNav: Confidence-Aware Semantic Scene Completion for Visual Semantic Navigation

Yiqing Liang, Boyuan Chen, Shuran Song

专题命中视觉空间推理：planning(abstract)

2007.12146 2020-12-24 cs.CV 50%

Spatially Aware Multimodal Transformers for TextVQA

Yash Kant, Dhruv Batra, Peter Anderson, Alex Schwing, Devi Parikh, Jiasen Lu, Harsh Agrawal

专题命中视觉空间推理：reasoning(abstract)

Comments Accepted at European Conference on Computer Vision, 2020

2011.05288 2020-11-11 cs.RO 50%

Frontier-based Automatic-differentiable Information Gain Measure for Robotic Exploration of Unknown 3D Environments

Di Deng, Zhefan Xu, Wenbo Zhao, Kenji Shimada

专题命中视觉空间推理：planning(abstract)

2010.16361 2020-11-06 cs.RO 50%

Towards Preference Learning for Autonomous Ground Robot Navigation Tasks

Cory Hayes, Matthew Marge

专题命中视觉空间推理：planning(abstract)

Comments Accepted for publication at AI-HRI 2020 (arXiv:2010.13830)

2002.04354 2020-05-07 cs.RO cs.SY eess.SY 50%

Inference-Based Strategy Alignment for General-Sum Differential Games

Lasse Peters, David Fridovich-Keil, Claire J. Tomlin, Zachary N. Sunberg

专题命中视觉空间推理：reasoning(abstract)

1810.11556 2020-02-25 cs.RO 50%

Efficient and Trustworthy Social Navigation Via Explicit and Implicit Robot-Human Communication

Yuhang Che, Allison M. Okamura, Dorsa Sadigh

专题命中视觉空间推理：planning(abstract)

Journal ref IEEETransactionsonRobotics,pp(99):1-16,2020

2001.05673 2020-01-17 cs.CV cs.RO 50%

Probabilistic 3D Multi-Object Tracking for Autonomous Driving

Hsu-kuang Chiu, Antonio Prioletti, Jie Li, Jeannette Bohg

专题命中视觉空间推理：planning(abstract)

1912.03865 2019-12-10 cs.CV 50%

Learning a Layout Transfer Network for Context Aware Object Detection

Tao Wang, Xuming He, Yuanzheng Cai, Guobao Xiao

专题命中视觉空间推理：reasoning(abstract)

Comments Paper accepted by the IEEE Transactions on Intelligent Transportation Systems

1811.10742 2019-09-13 cs.CV 50%

Joint Monocular 3D Vehicle Detection and Tracking

Hou-Ning Hu, Qi-Zhi Cai, Dequan Wang, Ji Lin, Min Sun, Philipp Krähenbühl, Trevor Darrell, Fisher Yu

专题命中视觉空间推理：planning(abstract)

Comments 18 pages, 12 figures. Add supplementary material. Accepted by ICCV 2019. Website: https://eborboihuc.github.io/Mono-3DT Code: https://github.com/ucbdrive/3d-vehicle-tracking Video: https://youtu.be/EJAtOCKI31g

1907.06794 2019-08-20 cs.CV 50%

2nd Place Solution to the GQA Challenge 2019

Shijie Geng, Ji Zhang, Hang Zhang, Ahmed Elgammal, Dimitris N. Metaxas

专题命中视觉空间推理：reasoning(abstract)

1812.02347 2019-08-12 cs.CV 50%

Counterfactual Critic Multi-Agent Training for Scene Graph Generation

Long Chen, Hanwang Zhang, Jun Xiao, Xiangnan He, Shiliang Pu, Shih-Fu Chang

专题命中视觉空间推理：reasoning(abstract)

Comments International Conference on Computer Vision (ICCV), 2019 (oral)

1904.04686 2019-04-10 cs.CV 50%

Multi-Target Embodied Question Answering

Licheng Yu, Xinlei Chen, Georgia Gkioxari, Mohit Bansal, Tamara L. Berg, Dhruv Batra

专题命中视觉空间推理：reasoning(abstract)

Comments 10 pages, 6 figures

1807.06775 2018-07-19 cs.CV cs.RO 50%

Visual Affordance and Function Understanding: A Survey

Mohammed Hassanin, Salman Khan, Murat Tahtali

专题命中视觉空间推理：reasoning(abstract)

Comments 26 pages, 22 images

1712.07576 2018-06-18 cs.CV 50%

Learning to Act Properly: Predicting and Explaining Affordances from Images

Ching-Yao Chuang, Jiaman Li, Antonio Torralba, Sanja Fidler

专题命中视觉空间推理：reasoning(abstract)

1802.07218 2018-03-01 cs.GT cs.RO 50%

A 3D Game Theoretical Framework for the Evaluation of Unmanned Aircraft Systems Airspace Integration Concepts

Negin Musavi, Ayman Manzoor, Yildiray Yildiz

专题命中视觉空间推理：reasoning(abstract)

Comments Added 'Acknowledgement' Section

1. 视觉空间推理 3363 篇

Why? Why not? When? Visual Explanations of Agent Behavior in Reinforcement Learning

Explore before Moving: A Feasible Path Estimation and Memory Recalling Framework for Embodied Navigation

VidTr: Video Transformer Without Convolutions

Knowledge-based Embodied Question Answering

Benchmarking Unsupervised Object Representations for Video Sequences

Mapless Humanoid Navigation Using Learned Latent Dynamics

Referring Transformer: A One-step Approach to Multi-task Visual Grounding

Move Beyond Trajectories: Distribution Space Coupling for Crowd Navigation

BEyond observation: an approach for ObjectNav

Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time

3D-OGSE: Online Safe and Smooth Trajectory Generation using Generalized Shape Expansion in Unknown 3-D Environments

Proposal-free One-stage Referring Expression via Grid-Word Cross-Attention

Chop Chop BERT: Visual Question Answering by Chopping VisualBERT's Heads

Hierarchical Cross-Modal Agent for Robotics Vision-and-Language Navigation

An Agent-based Architecture for AI-Enhanced Automated Testing for XR Systems, a Short Paper

SSCNav: Confidence-Aware Semantic Scene Completion for Visual Semantic Navigation

Spatially Aware Multimodal Transformers for TextVQA

Frontier-based Automatic-differentiable Information Gain Measure for Robotic Exploration of Unknown 3D Environments

Towards Preference Learning for Autonomous Ground Robot Navigation Tasks

Inference-Based Strategy Alignment for General-Sum Differential Games

Efficient and Trustworthy Social Navigation Via Explicit and Implicit Robot-Human Communication

Probabilistic 3D Multi-Object Tracking for Autonomous Driving

Learning a Layout Transfer Network for Context Aware Object Detection

Joint Monocular 3D Vehicle Detection and Tracking

2nd Place Solution to the GQA Challenge 2019

Counterfactual Critic Multi-Agent Training for Scene Graph Generation

Multi-Target Embodied Question Answering

Visual Affordance and Function Understanding: A Survey

Learning to Act Properly: Predicting and Explaining Affordances from Images

A 3D Game Theoretical Framework for the Evaluation of Unmanned Aircraft Systems Airspace Integration Concepts