大模型推理能力 - arXivDaily 专题

2310.07781 2023-10-13 cs.CV 50%

3D TransUNet: Advancing Medical Image Segmentation through Vision Transformers

Jieneng Chen, Jieru Mei, Xianhang Li, Yongyi Lu, Qihang Yu, Qingyue Wei, Xiangde Luo, Yutong Xie, Ehsan Adeli, Yan Wang, Matthew Lungren, Lei Xing, Le Lu, Alan Yuille, Yuyin Zhou

专题命中视觉空间推理：planning(abstract)

Comments Code and models are available at https://github.com/Beckschen/3D-TransUNet

2310.01356 2023-10-03 cs.CV 50%

Less is More: Toward Zero-Shot Local Scene Graph Generation via Foundation Models

Shu Zhao, Huijuan Xu

专题命中视觉空间推理：reasoning(abstract)

2309.16838 2023-10-02 cs.RO cs.MA 50%

Social Navigation in Crowded Environments with Model Predictive Control and Deep Learning-Based Human Trajectory Prediction

Viet-Anh Le, Behdad Chalaki, Vaishnav Tadiparthi, Hossein Nourkhiz Mahjoub, Jovin D'sa, Ehsan Moradi-Pari

专题命中视觉空间推理：planning(abstract)

Comments 7 pages, 3 figures, 6 tables

2306.03857 2023-10-02 cs.RO cs.CV 50%

Learning with a Mole: Transferable latent spatial representations for navigation without reconstruction

Guillaume Bono, Leonid Antsfeld, Assem Sadek, Gianluca Monaci, Christian Wolf

专题命中视觉空间推理：planning(abstract)

2309.16164 2023-09-29 cs.RO cs.CV 50%

Learning to Terminate in Object Navigation

Yuhang Song, Anh Nguyen, Chun-Yi Lee

专题命中视觉空间推理：planning(abstract)

Comments 16 pages

2306.03253 2023-09-28 cs.CV 50%

Zero-Shot 3D Shape Correspondence

Ahmed Abdelreheem, Abdelrahman Eldesokey, Maks Ovsjanikov, Peter Wonka

专题命中视觉空间推理：reasoning(abstract)

Comments Project webpage: https://samir55.github.io/3dshapematch/

2309.10309 2023-09-22 cs.RO 50%

Bridging Zero-shot Object Navigation and Foundation Models through Pixel-Guided Navigation Skill

Wenzhe Cai, Siyuan Huang, Guangran Cheng, Yuxing Long, Peng Gao, Changyin Sun, Hao Dong

专题命中视觉空间推理：planning(abstract)

Comments 8 pages, 5 figures

2308.09033 2023-09-20 cs.CV 50%

Uni-NLX: Unifying Textual Explanations for Vision and Vision-Language Tasks

Fawaz Sammani, Nikos Deligiannis

专题命中视觉空间推理：reasoning(abstract)

Comments Accepted to ICCVW 2023

2309.05036 2023-09-12 cs.RO cs.CV 50%

What Is Near?: Room Locality Learning for Enhanced Robot Vision-Language-Navigation in Indoor Living Environments

Muraleekrishna Gopinathan, Jumana Abu-Khalaf, David Suter, Sidike Paheding, Nathir A. Rawashdeh

专题命中视觉空间推理：planning(abstract)

2203.12929 2023-09-06 cs.CV cs.MM 50%

Towards Escaping from Language Bias and OCR Error: Semantics-Centered Text Visual Question Answering

Chengyang Fang, Gangyan Zeng, Yu Zhou, Daiqing Wu, Can Ma, Dayong Hu, Weiping Wang

专题命中视觉空间推理：reasoning(abstract)

2303.12077 2023-08-25 cs.RO cs.CV 50%

VAD: Vectorized Scene Representation for Efficient Autonomous Driving

Bo Jiang, Shaoyu Chen, Qing Xu, Bencheng Liao, Jiajie Chen, Helong Zhou, Qian Zhang, Wenyu Liu, Chang Huang, Xinggang Wang

专题命中视觉空间推理：planning(abstract)

Comments Accepted to ICCV 2023. Code&Demos: https://github.com/hustvl/VAD

2308.10141 2023-08-22 cs.CV 50%

March in Chat: Interactive Prompting for Remote Embodied Referring Expression

Yanyuan Qiao, Yuankai Qi, Zheng Yu, Jing Liu, Qi Wu

专题命中视觉空间推理：planning(abstract)

Comments Accepted by ICCV 2023

2211.10408 2023-08-21 cs.CV 50%

CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow

Philippe Weinzaepfel, Thomas Lucas, Vincent Leroy, Yohann Cabon, Vaibhav Arora, Romain Brégier, Gabriela Csurka, Leonid Antsfeld, Boris Chidlovskii, Jérôme Revaud

专题命中视觉空间推理：reasoning(abstract)

Comments ICCV 2023

2308.08769 2023-08-21 cs.CV 50%

Chat-3D: Data-efficiently Tuning Large Language Model for Universal Dialogue of 3D Scenes

Zehan Wang, Haifeng Huang, Yang Zhao, Ziang Zhang, Zhou Zhao

专题命中视觉空间推理：reasoning(abstract)

Comments The project page is \url{https://chat-3d.github.io/}

2308.07997 2023-08-17 cs.CV cs.RO 50%

$A^2$Nav: Action-Aware Zero-Shot Robot Navigation by Exploiting Vision-and-Language Ability of Foundation Models

Peihao Chen, Xinyu Sun, Hongyan Zhi, Runhao Zeng, Thomas H. Li, Gaowen Liu, Mingkui Tan, Chuang Gan

专题命中视觉空间推理：reasoning(abstract)

2308.06635 2023-08-15 cs.CV 50%

3DMOTFormer: Graph Transformer for Online 3D Multi-Object Tracking

Shuxiao Ding, Eike Rehder, Lukas Schneider, Marius Cordts, Juergen Gall

专题命中视觉空间推理：planning(abstract)

Comments 17 pages, 8 figures, accepted by ICCV2023

2308.05602 2023-08-11 cs.CV cs.RO 50%

Object Goal Navigation with Recursive Implicit Maps

Shizhe Chen, Thomas Chabal, Ivan Laptev, Cordelia Schmid

专题命中视觉空间推理：reasoning(abstract)

Comments Accepted to IROS 2023

2303.12188 2023-08-03 cond-mat.mtrl-sci physics.comp-ph 50%

Toward Accurate Interpretable Predictions of Materials Properties within Transformer Language Models

Vadim Korolev, Pavel Protsenko

专题命中视觉空间推理：reasoning(abstract)

Comments 17 pages, 5 figures, 1 table

2210.01683 2023-08-01 cs.RO 50%

Learning Depth Vision-Based Personalized Robot Navigation From Dynamic Demonstrations in Virtual Reality

Jorge de Heuvel, Nathan Corral, Benedikt Kreis, Jacobus Conradi, Anne Driemel, Maren Bennewitz

专题命中视觉空间推理：reasoning(abstract)

2307.07938 2023-07-18 cs.CV 50%

CVSformer: Cross-View Synthesis Transformer for Semantic Scene Completion

Haotian Dong, Enhui Ma, Lubo Wang, Miaohui Wang, Wuyuan Xie, Qing Guo, Ping Li, Lingyu Liang, Kairui Yang, Di Lin

专题命中视觉空间推理：reasoning(abstract)

Comments 10 pages, 6 figures

2306.05696 2023-06-12 cs.RO 50%

Embodied Executable Policy Learning with Language-based Scene Summarization

Jielin Qiu, Mengdi Xu, William Han, Seungwhan Moon, Ding Zhao

专题命中视觉空间推理：planning(abstract)

Comments 15 pages. arXiv admin note: text overlap with arXiv:2107.06912 by other authors

2305.19467 2023-06-01 eess.IV cs.CV 50%

Synthetic CT Generation from MRI using 3D Transformer-based Denoising Diffusion Model

Shaoyan Pan, Elham Abouei, Jacob Wynne, Tonghe Wang, Richard L. J. Qiu, Yuheng Li, Chih-Wei Chang, Junbo Peng, Justin Roper, Pretesh Patel, David S. Yu, Hui Mao, Xiaofeng Yang

专题命中视觉空间推理：planning(abstract)

2305.15808 2023-05-26 cs.CV 50%

Towards Language-guided Interactive 3D Generation: LLMs as Layout Interpreter with Generative Feedback

Yiqi Lin, Hao Wu, Ruichen Wang, Haonan Lu, Xiaodong Lin, Hui Xiong, Lin Wang

专题命中视觉空间推理：reasoning(abstract)

Comments Preprint. Work in Progres

2305.08522 2023-05-16 cs.CV 50%

Cross-Modality Time-Variant Relation Learning for Generating Dynamic Scene Graphs

Jingyi Wang, Jinfa Huang, Can Zhang, Zhidong Deng

专题命中视觉空间推理：planning(abstract)

Comments Preprint. Accepted by ICRA 2023

2305.05583 2023-05-10 cs.CV 50%

Group Activity Recognition via Dynamic Composition and Interaction

Youliang Zhang, Zhuo Zhou, Wenxuan Liu, Danni Xu, Zheng Wang

专题命中视觉空间推理：reasoning(abstract)

Comments 13 pages, 6 figures

2208.08041 2023-05-09 cs.CV 50%

InterTrack: Interaction Transformer for 3D Multi-Object Tracking

John Willes, Cody Reading, Steven L. Waslander

专题命中视觉空间推理：planning(abstract)

Comments Accepted to CRV 2023

2304.01192 2023-04-04 cs.CV cs.RO 50%

Navigating to Objects Specified by Images

Jacob Krantz, Theophile Gervet, Karmesh Yadav, Austin Wang, Chris Paxton, Roozbeh Mottaghi, Dhruv Batra, Jitendra Malik, Stefan Lee, Devendra Singh Chaplot

专题命中视觉空间推理：reasoning(abstract)

2303.14278 2023-03-28 cs.RO cs.SY eess.SY 50%

Safe Hierarchical Navigation in Crowded Dynamic Uncertain Environments

Hongyi Chen, Shiyu Feng, Ye Zhao, Changliu Liu, Patricio A. Vela

专题命中视觉空间推理：planning(abstract)

2212.09522 2022-12-20 cs.CV 50%

MIST: Multi-modal Iterative Spatial-Temporal Transformer for Long-form Video Question Answering

Difei Gao, Luowei Zhou, Lei Ji, Linchao Zhu, Yi Yang, Mike Zheng Shou

专题命中视觉空间推理：reasoning(abstract)

2207.11514 2022-12-07 cs.CV cs.RO 50%

Semantic Abstraction: Open-World 3D Scene Understanding from 2D Vision-Language Models

Huy Ha, Shuran Song

专题命中视觉空间推理：reasoning(abstract)

Comments 16 pages, 9 figures, project website at https://semantic-abstraction.cs.columbia.edu/

1. 视觉空间推理 3363 篇

3D TransUNet: Advancing Medical Image Segmentation through Vision Transformers

Less is More: Toward Zero-Shot Local Scene Graph Generation via Foundation Models

Social Navigation in Crowded Environments with Model Predictive Control and Deep Learning-Based Human Trajectory Prediction

Learning with a Mole: Transferable latent spatial representations for navigation without reconstruction

Learning to Terminate in Object Navigation

Zero-Shot 3D Shape Correspondence

Bridging Zero-shot Object Navigation and Foundation Models through Pixel-Guided Navigation Skill

Uni-NLX: Unifying Textual Explanations for Vision and Vision-Language Tasks

What Is Near?: Room Locality Learning for Enhanced Robot Vision-Language-Navigation in Indoor Living Environments

Towards Escaping from Language Bias and OCR Error: Semantics-Centered Text Visual Question Answering

VAD: Vectorized Scene Representation for Efficient Autonomous Driving

March in Chat: Interactive Prompting for Remote Embodied Referring Expression

CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow

Chat-3D: Data-efficiently Tuning Large Language Model for Universal Dialogue of 3D Scenes

$A^2$Nav: Action-Aware Zero-Shot Robot Navigation by Exploiting Vision-and-Language Ability of Foundation Models

3DMOTFormer: Graph Transformer for Online 3D Multi-Object Tracking

Object Goal Navigation with Recursive Implicit Maps

Toward Accurate Interpretable Predictions of Materials Properties within Transformer Language Models

Learning Depth Vision-Based Personalized Robot Navigation From Dynamic Demonstrations in Virtual Reality

CVSformer: Cross-View Synthesis Transformer for Semantic Scene Completion

Embodied Executable Policy Learning with Language-based Scene Summarization

Synthetic CT Generation from MRI using 3D Transformer-based Denoising Diffusion Model

Towards Language-guided Interactive 3D Generation: LLMs as Layout Interpreter with Generative Feedback

Cross-Modality Time-Variant Relation Learning for Generating Dynamic Scene Graphs

Group Activity Recognition via Dynamic Composition and Interaction

InterTrack: Interaction Transformer for 3D Multi-Object Tracking

Navigating to Objects Specified by Images

Safe Hierarchical Navigation in Crowded Dynamic Uncertain Environments

MIST: Multi-modal Iterative Spatial-Temporal Transformer for Long-form Video Question Answering

Semantic Abstraction: Open-World 3D Scene Understanding from 2D Vision-Language Models