大模型推理能力 - arXivDaily 专题

2211.05243 2022-11-11 cs.RO 50%

Vision-based navigation and obstacle avoidance via deep reinforcement learning

Paul Blum, Peter Crowley, George Lykotrafitis

专题命中视觉空间推理：planning(abstract)

2203.07997 2022-11-08 cs.CV 50%

InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene Understanding

Hanrong Ye, Dan Xu

专题命中视觉空间推理：reasoning(abstract)

Comments Published in ECCV 2022 Conference. Code is available at https://github.com/prismformore/InvPT

Journal ref ECCV 2022

2210.15908 2022-10-31 cs.CV cs.RO 50%

Long-HOT: A Modular Hierarchical Approach for Long-Horizon Object Transport

Sriram Narayanan, Dinesh Jayaraman, Manmohan Chandraker

专题命中视觉空间推理：planning(abstract)

2210.14601 2022-10-27 cs.CV 50%

End-to-end Tracking with a Multi-query Transformer

Bruno Korbar, Andrew Zisserman

专题命中视觉空间推理：reasoning(abstract)

2209.08663 2022-09-20 cs.RO 50%

Multiple Waypoint Navigation in Unknown Indoor Environments

Shivam Sood, Jaskaran Singh Sodhi, Parv Maheshwari, Karan Uppal, Debashish Chakravarty

专题命中视觉空间推理：planning(abstract)

Comments Accepted at ICCR 2022

2004.07031 2022-09-05 cs.HC eess.IV 50%

SenseCare: A Research Platform for Medical Image Informatics and Interactive 3D Visualization

Qi Duan, Guotai Wang, Rui Wang, Chao Fu, Xinjun Li, Na Wang, Yechong Huang, Xiaodi Huang, Tao Song, Liang Zhao, Xinglong Liu, Qing Xia, Zhiqiang Hu, Yinan Chen, Shaoting Zhang

专题命中视觉空间推理：planning(abstract)

Comments 15 pages, 16 figures

2208.12602 2022-08-29 cs.RO 50%

The Foreseeable Future: Self-Supervised Learning to Predict Dynamic Scenes for Indoor Navigation

Hugues Thomas, Jian Zhang, Timothy D. Barfoot

专题命中视觉空间推理：planning(abstract)

2208.04307 2022-08-09 cs.CV 50%

PlaneFormers: From Sparse View Planes to 3D Reconstruction

Samir Agarwala, Linyi Jin, Chris Rockwell, David F. Fouhey

专题命中视觉空间推理：reasoning(abstract)

Comments Accepted to ECCV 2022

2207.13440 2022-07-28 cs.CV 50%

Iterative Scene Graph Generation

Siddhesh Khandelwal, Leonid Sigal

专题命中视觉空间推理：reasoning(abstract)

Comments 25 pages, 10 images, 9 tables

2203.07553 2022-07-19 cs.CV 50%

VPFusion: Joint 3D Volume and Pixel-Aligned Feature Fusion for Single and Multi-view 3D Reconstruction

Jisan Mahmud, Jan-Michael Frahm

专题命中视觉空间推理：reasoning(abstract)

2108.09717 2022-07-18 cs.CV cs.MM 50%

EKTVQA: Generalized use of External Knowledge to empower Scene Text in Text-VQA

Arka Ujjal Dey, Ernest Valveny, Gaurav Harit

专题命中视觉空间推理：reasoning(abstract)

Comments Accepted at IEEE Access

Journal ref IEEE.ACCESS 10 (2022) 72092-72106

2206.05728 2022-07-14 cs.RO cs.SY eess.SY 50%

Arena-Bench: A Benchmarking Suite for Obstacle Avoidance Approaches in Highly Dynamic Environments

Linh Kästner, Teham Bhuiyan, Tuan Anh Le, Elias Treis, Johannes Cox, Boris Meinardus, Jacek Kmiecik, Reyk Carstens, Duc Pichel, Bassel Fatloun, Niloufar Khorsandi, Jens Lambrecht

专题命中视觉空间推理：planning(abstract)

Comments Robotics and Automation Letters (RA-L), 2022, 8 pages, 6 figures

2207.01779 2022-07-07 cs.RO cs.CV 50%

3D Part Assembly Generation with Instance Encoded Transformer

Rufeng Zhang, Tao Kong, Weihao Wang, Xuan Han, Mingyu You

专题命中视觉空间推理：reasoning(abstract)

Comments 8 pages, 7 figures

Journal ref IROS 2022 and IEEE Robotics and Automation Letters (RA-L), 2022

2207.02201 2022-07-06 cs.CV cs.RO 50%

Efficient Spatial-Temporal Information Fusion for LiDAR-Based 3D Moving Object Segmentation

Jiadai Sun, Yuchao Dai, Xianjing Zhang, Jintao Xu, Rui Ai, Weihao Gu, Xieyuanli Chen

专题命中视觉空间推理：planning(abstract)

Comments Accepted by IROS2022. Code: https://github.com/haomo-ai/MotionSeg3D

2206.09553 2022-06-22 cs.CV 50%

Capturing and Inferring Dense Full-Body Human-Scene Contact

Chun-Hao P. Huang, Hongwei Yi, Markus Höschle, Matvey Safroshkin, Tsvetelina Alexiadis, Senya Polikovsky, Daniel Scharstein, Michael J. Black

专题命中视觉空间推理：reasoning(abstract)

Comments CVPR 2022

2206.08423 2022-06-20 cs.CV 50%

IRISformer: Dense Vision Transformers for Single-Image Inverse Rendering in Indoor Scenes

Rui Zhu, Zhengqin Li, Janarbek Matai, Fatih Porikli, Manmohan Chandraker

专题命中视觉空间推理：reasoning(abstract)

Comments CVPR 22 camera ready version with supplementary

2106.12413 2022-06-06 cs.CV 50%

Transformer Meets Convolution: A Bilateral Awareness Network for Semantic Segmentation of Very Fine Resolution Urban Scene Images

Libo Wang, Rui Li, Dongzhi Wang, Chenxi Duan, Teng Wang, Xiaoliang Meng

专题命中视觉空间推理：planning(abstract)

Comments Accepted by Remote Sensing, see https://www.mdpi.com/2072-4292/13/16/3065

2204.04913 2022-06-01 cs.CV 50%

Permutation-Invariant Relational Network for Multi-person 3D Pose Estimation

Nicolas Ugrinovic, Adria Ruiz, Antonio Agudo, Alberto Sanfeliu, Francesc Moreno-Noguer

专题命中视觉空间推理：reasoning(abstract)

2205.12616 2022-05-26 cs.CV 50%

Guiding Visual Question Answering with Attention Priors

Thao Minh Le, Vuong Le, Sunil Gupta, Svetha Venkatesh, Truyen Tran

专题命中视觉空间推理：reasoning(abstract)

Comments Preprint, 10 pages

2203.10202 2022-03-22 cs.CV 50%

Relationformer: A Unified Framework for Image-to-Graph Generation

Suprosanna Shit, Rajat Koner, Bastian Wittmann, Johannes Paetzold, Ivan Ezhov, Hongwei Li, Jiazhen Pan, Sahand Sharifzadeh, Georgios Kaissis, Volker Tresp, Bjoern Menze

专题命中视觉空间推理：reasoning(abstract)

2111.13539 2022-03-22 cs.CV 50%

GeoNeRF: Generalizing NeRF with Geometry Priors

Mohammad Mahdi Johari, Yann Lepoittevin, François Fleuret

专题命中视觉空间推理：reasoning(abstract)

Comments CVPR2022

2112.10196 2022-03-10 cs.CV 50%

End-to-End Learning of Multi-category 3D Pose and Shape Estimation

Yigit Baran Can, Alexander Liniger, Danda Pani Paudel, Luc Van Gool

专题命中视觉空间推理：reasoning(abstract)

2202.11334 2022-02-24 cs.RO 50%

Dense Multi-Agent Navigation Using Voronoi Cells and Congestion Metric-based Replanning

Senthil Hariharan Arul, Dinesh Manocha

专题命中视觉空间推理：planning(abstract)

2108.06105 2022-02-23 cs.RO 50%

Image-Goal Navigation in Complex Environments via Modular Learning

Qiaoyun Wu, Jun Wang, Jing Liang, Xiaoxi Gong, Dinesh Manocha

专题命中视觉空间推理：planning(abstract)

Comments 9 pages

2112.04863 2021-12-20 eess.IV cs.CV 50%

3D Medical Point Transformer: Introducing Convolution to Attention Networks for Medical Point Cloud Analysis

Jianhui Yu, Chaoyi Zhang, Heng Wang, Dingxin Zhang, Yang Song, Tiange Xiang, Dongnan Liu, Weidong Cai

专题命中视觉空间推理：reasoning(abstract)

Comments Technical Report

2111.03368 2021-11-23 eess.IV cs.CV 50%

Hepatic vessel segmentation based on 3D swin-transformer with inductive biased multi-head self-attention

Mian Wu, Yinling Qian, Xiangyun Liao, Qiong Wang, Pheng-Ann Heng

专题命中视觉空间推理：planning(abstract)

Comments 20 pages, 6 figures

2111.07975 2021-11-16 cs.RO cs.CV 50%

Semantically Grounded Object Matching for Robust Robotic Scene Rearrangement

Walter Goodwin, Sagar Vaze, Ioannis Havoutis, Ingmar Posner

专题命中视觉空间推理：planning(abstract)

Comments 8 pages, 5 figures

2111.06075 2021-11-12 cs.CV 50%

Graph Relation Transformer: Incorporating pairwise object features into the Transformer architecture

Michael Yang, Aditya Anantharaman, Zachary Kitowski, Derik Clive Robert

专题命中视觉空间推理：reasoning(abstract)

Comments Presented as poster in CVPR 2021 Visual Question Answering Workshop

2107.11043 2021-11-10 cs.CV 50%

Integrating Deep Learning and Augmented Reality to Enhance Situational Awareness in Firefighting Environments

Manish Bhattarai

专题命中视觉空间推理：planning(abstract)

Comments PhD Dissertation

2106.13488 2021-11-10 cs.CV 50%

Probing Inter-modality: Visual Parsing with Self-Attention for Vision-Language Pre-training

Hongwei Xue, Yupan Huang, Bei Liu, Houwen Peng, Jianlong Fu, Houqiang Li, Jiebo Luo

专题命中视觉空间推理：reasoning(abstract)

Comments Accepted by NeurIPS 2021

1. 视觉空间推理 3363 篇

Vision-based navigation and obstacle avoidance via deep reinforcement learning

InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene Understanding

Long-HOT: A Modular Hierarchical Approach for Long-Horizon Object Transport

End-to-end Tracking with a Multi-query Transformer

Multiple Waypoint Navigation in Unknown Indoor Environments

SenseCare: A Research Platform for Medical Image Informatics and Interactive 3D Visualization

The Foreseeable Future: Self-Supervised Learning to Predict Dynamic Scenes for Indoor Navigation

PlaneFormers: From Sparse View Planes to 3D Reconstruction

Iterative Scene Graph Generation

VPFusion: Joint 3D Volume and Pixel-Aligned Feature Fusion for Single and Multi-view 3D Reconstruction

EKTVQA: Generalized use of External Knowledge to empower Scene Text in Text-VQA

Arena-Bench: A Benchmarking Suite for Obstacle Avoidance Approaches in Highly Dynamic Environments

3D Part Assembly Generation with Instance Encoded Transformer

Efficient Spatial-Temporal Information Fusion for LiDAR-Based 3D Moving Object Segmentation

Capturing and Inferring Dense Full-Body Human-Scene Contact

IRISformer: Dense Vision Transformers for Single-Image Inverse Rendering in Indoor Scenes

Transformer Meets Convolution: A Bilateral Awareness Network for Semantic Segmentation of Very Fine Resolution Urban Scene Images

Permutation-Invariant Relational Network for Multi-person 3D Pose Estimation

Guiding Visual Question Answering with Attention Priors

Relationformer: A Unified Framework for Image-to-Graph Generation

GeoNeRF: Generalizing NeRF with Geometry Priors

End-to-End Learning of Multi-category 3D Pose and Shape Estimation

Dense Multi-Agent Navigation Using Voronoi Cells and Congestion Metric-based Replanning

Image-Goal Navigation in Complex Environments via Modular Learning

3D Medical Point Transformer: Introducing Convolution to Attention Networks for Medical Point Cloud Analysis

Hepatic vessel segmentation based on 3D swin-transformer with inductive biased multi-head self-attention

Semantically Grounded Object Matching for Robust Robotic Scene Rearrangement

Graph Relation Transformer: Incorporating pairwise object features into the Transformer architecture

Integrating Deep Learning and Augmented Reality to Enhance Situational Awareness in Firefighting Environments

Probing Inter-modality: Visual Parsing with Self-Attention for Vision-Language Pre-training