多模态大模型 - arXivDaily 专题

2308.04352 2023-08-09 cs.CV 57%

3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment

Ziyu Zhu, Xiaojian Ma, Yixin Chen, Zhidong Deng, Siyuan Huang, Qing Li

专题命中多模态训练与对齐：multi-modal(abstract)；分类 cs.CV

2305.11427 2023-08-08 cs.CV 57%

RGB-D And Thermal Sensor Fusion: A Systematic Literature Review

Martin Brenner, Napoleon H. Reyes, Teo Susnjak, Andre L. C. Barczak

专题命中多模态训练与对齐：multimodal(abstract)；分类 cs.CV

Comments 34 pages, 21 figures

2307.16142 2023-08-01 eess.IV cs.CV 57%

Implicit Neural Representation in Medical Imaging: A Comparative Survey

Amirali Molaei, Amirhossein Aminimehr, Armin Tavakoli, Amirhossein Kazerouni, Bobby Azad, Reza Azad, Dorit Merhof

专题命中多模态训练与对齐：multi-modal(abstract)；分类 cs.CV

2307.09749 2023-08-01 cs.CV 57%

Towards Robust Scene Text Image Super-resolution via Explicit Location Enhancement

Hang Guo, Tao Dai, Guanghao Meng, Shu-Tao Xia

专题命中多模态训练与对齐：multi-modal(abstract)；分类 cs.CV

Comments Accepted as IJCAI2023 paper

2307.13323 2023-07-26 cs.RO cs.AI 57%

Learning Autonomous Ultrasound via Latent Task Representation and Robotic Skills Adaptation

Xutian Deng, Junnan Jiang, Wen Cheng, Miao Li

专题命中多模态训练与对齐：multimodal(abstract)；分类 cs.AI

2206.09731 2023-07-19 cs.CV eess.IV 57%

Semantic Labeling of High Resolution Images Using EfficientUNets and Transformers

Hasan AlMarzouqi, Lyes Saad Saoud

专题命中多模态训练与对齐：multi-modal(abstract)；分类 cs.CV

2208.14365 2023-07-17 cs.CV 57%

Image-Specific Information Suppression and Implicit Local Alignment for Text-based Person Search

Shuanglin Yan, Hao Tang, Liyan Zhang, Jinhui Tang

专题命中多模态训练与对齐：cross-modal(abstract)；分类 cs.CV

2307.06771 2023-07-14 eess.IV cs.CV cs.LG 57%

Generalizing Supervised Deep Learning MRI Reconstruction to Multiple and Unseen Contrasts using Meta-Learning Hypernetworks

Sriprabha Ramanarayanan, Arun Palla, Keerthi Ram, Mohanasankar Sivaprakasam

专题命中多模态训练与对齐：multimodal(abstract)；分类 cs.CV

Comments Accepted for publication in Elsevier Applied Soft Computing Journal, 36 pages, 18 figures

2306.05437 2023-06-28 cs.LG cs.AI 57%

One-step Multi-view Clustering with Diverse Representation

Xinhang Wan, Jiyuan Liu, Xinwang Liu, Siwei Wang, Yi Wen, Tianjiao Wan, Li Shen, En Zhu

专题命中多模态训练与对齐：multimodal(abstract)；分类 cs.AI

2306.13380 2023-06-26 cs.CV 57%

First Place Solution to the CVPR'2023 AQTC Challenge: A Function-Interaction Centric Approach with Spatiotemporal Visual-Language Alignment

Tom Tongjia Chen, Hongshan Yu, Zhengeng Yang, Ming Li, Zechuan Li, Jingwen Wang, Wei Miao, Wei Sun, Chen Chen

专题命中多模态训练与对齐：multimodal(abstract)；分类 cs.CV

Comments Winner of CVPR2023 Long-form Video Understanding and Generation Challenge (Track 3)

2305.10764 2023-06-21 cs.CV 57%

OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding

Minghua Liu, Ruoxi Shi, Kaiming Kuang, Yinhao Zhu, Xuanlin Li, Shizhong Han, Hong Cai, Fatih Porikli, Hao Su

专题命中多模态训练与对齐：multi-modal(abstract)；分类 cs.CV

Comments Project Website: https://colin97.github.io/OpenShape/

2212.01108 2023-06-21 eess.IV cs.CV 57%

Multi-scale Transformer Network with Edge-aware Pre-training for Cross-Modality MR Image Synthesis

Yonghao Li, Tao Zhou, Kelei He, Yi Zhou, Dinggang Shen

专题命中多模态训练与对齐：multi-modal(abstract)；分类 cs.CV

Comments 13 pages, 16 figures. This paper has been accepted by IEEE TMI

2211.16697 2023-06-19 cs.CV cs.HC 57%

SGDraw: Scene Graph Drawing Interface Using Object-Oriented Representation

Tianyu Zhang, Xusheng Du, Chia-Ming Chang, Xi Yang, Haoran Xie

专题命中多模态训练与对齐：multi-modal(abstract)；分类 cs.CV

Comments 16 pages, 9 figures, video is https://youtu.be/acy0SNLfahg, accepted in HCI International 2023

2305.06500 2023-06-16 cs.CV cs.LG 57%

InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning

Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, Steven Hoi

专题命中多模态训练与对齐：multimodal(abstract)；分类 cs.CV

Comments preprint

2306.07344 2023-06-14 cs.RO cs.CV 57%

Towards a Robust Sensor Fusion Step for 3D Object Detection on Corrupted Data

Maciej K. Wozniak, Viktor Karefjards, Marko Thiel, Patric Jensfelt

专题命中多模态训练与对齐：multimodal(abstract)；分类 cs.CV

1806.05104 2023-06-06 cs.CV 57%

Improving Cytoarchitectonic Segmentation of Human Brain Areas with Self-supervised Siamese Networks

Hannah Spitzer, Kai Kiwitz, Katrin Amunts, Stefan Harmeling, Timo Dickscheid

专题命中多模态训练与对齐：multimodal(abstract)；分类 cs.CV

Comments Accepted at MICCAI 2018

2305.19924 2023-06-02 cs.CV 57%

Joint Adaptive Representations for Image-Language Learning

AJ Piergiovanni, Anelia Angelova

专题命中多模态训练与对齐：multi-modal(abstract)；分类 cs.CV

Comments T4V Workshop

2304.00932 2023-05-26 cs.CV 57%

HypLiLoc: Towards Effective LiDAR Pose Regression with Hyperbolic Fusion

Sijie Wang, Qiyu Kang, Rui She, Wei Wang, Kai Zhao, Yang Song, Wee Peng Tay

专题命中多模态训练与对齐：multi-modal(abstract)；分类 cs.CV

Comments Accepted by CVPR 2023

2305.14969 2023-05-25 cs.CV 57%

MMNet: Multi-Mask Network for Referring Image Segmentation

Yichen Yan, Xingjian He, Wenxuan Wan, Jing Liu

专题命中多模态训练与对齐：cross-modal(abstract)；分类 cs.CV

Comments 10 pages, 5 figures

2305.13220 2023-05-23 cs.CV 57%

Fast Monocular Scene Reconstruction with Global-Sparse Local-Dense Grids

Wei Dong, Chris Choy, Charles Loop, Or Litany, Yuke Zhu, Anima Anandkumar

专题命中多模态训练与对齐：multi-modal(abstract)；分类 cs.CV

Comments CVPR 2023

2302.02318 2023-05-23 cs.CV 57%

Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining

Zekun Qi, Runpei Dong, Guofan Fan, Zheng Ge, Xiangyu Zhang, Kaisheng Ma, Li Yi

专题命中多模态训练与对齐：cross-modal(abstract)；分类 cs.CV

Comments Accepted at ICML 2023

2211.08691 2023-05-23 cs.CV cs.RO 57%

Towards Long-Tailed 3D Detection

Neehar Peri, Achal Dave, Deva Ramanan, Shu Kong

专题命中多模态训练与对齐：multimodal(abstract)；分类 cs.CV

Comments This work has been accepted to the Conference on Robot Learning (CoRL) 2022

2305.09999 2023-05-18 cs.CV 57%

An Interactively Reinforced Paradigm for Joint Infrared-Visible Image Fusion and Saliency Object Detection

Di Wang, Jinyuan Liu, Risheng Liu, Xin Fan

专题命中多模态训练与对齐：multimodal(abstract)；分类 cs.CV

2305.09641 2023-05-17 cs.CV cs.GR cs.LG 57%

FitMe: Deep Photorealistic 3D Morphable Model Avatars

Alexandros Lattas, Stylianos Moschoglou, Stylianos Ploumpis, Baris Gecer, Jiankang Deng, Stefanos Zafeiriou

专题命中多模态训练与对齐：multi-modal(abstract)；分类 cs.CV

Comments Accepted at CVPR 2023, project page at https://lattas.github.io/fitme , 17 pages including supplementary material

2304.14323 2023-05-12 cs.AI 57%

Pushing the Boundaries of Tractable Multiperspective Reasoning: A Deduction Calculus for Standpoint EL+

Lucía Gómez Álvarez, Sebastian Rudolph, Hannes Strass

专题命中多模态训练与对齐：multi-modal(abstract)；分类 cs.AI

2112.07133 2023-05-12 cs.CV 57%

CLIP-Lite: Information Efficient Visual Representation Learning with Language Supervision

Aman Shrivastava, Ramprasaath R. Selvaraju, Nikhil Naik, Vicente Ordonez

专题命中多模态训练与对齐：image-text(abstract)；分类 cs.CV

2305.05166 2023-05-11 cs.CL 57%

E2TIMT: Efficient and Effective Modal Adapter for Text Image Machine Translation

Cong Ma, Yaping Zhang, Mei Tu, Yang Zhao, Yu Zhou, Chengqing Zong

专题命中多模态训练与对齐：cross-modal(abstract)；分类 cs.CL

Comments Accepted at The 17th International Conference on Document Analysis and Recognition (ICDAR 2023)

2302.13187 2023-05-11 cs.AI 57%

Tractable Diversity: Scalable Multiperspective Ontology Management via Standpoint EL

Lucía Gómez Álvarez, Sebastian Rudolph, Hannes Strass

专题命中多模态训练与对齐：multi-modal(abstract)；分类 cs.AI

Journal ref 32nd International Joint Conference on Artificial Intelligence, IJCAI 2023

2112.03041 2023-05-11 cs.LG cs.AI q-bio.QM 57%

Keeping it Simple: Language Models can learn Complex Molecular Distributions

Daniel Flam-Shepherd, Kevin Zhu, Alán Aspuru-Guzik

专题命中多模态训练与对齐：multi-modal(abstract)；分类 cs.AI

Journal ref Nat Commun 13, 3293 (2022)

2305.03314 2023-05-08 cs.CL 57%

Block the Label and Noise: An N-Gram Masked Speller for Chinese Spell Checking

Haiyun Yang

专题命中多模态训练与对齐：multi-modal(abstract)；分类 cs.CL

1. 多模态训练与对齐 6929 篇

3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment

RGB-D And Thermal Sensor Fusion: A Systematic Literature Review

Implicit Neural Representation in Medical Imaging: A Comparative Survey

Towards Robust Scene Text Image Super-resolution via Explicit Location Enhancement

Learning Autonomous Ultrasound via Latent Task Representation and Robotic Skills Adaptation

Semantic Labeling of High Resolution Images Using EfficientUNets and Transformers

Image-Specific Information Suppression and Implicit Local Alignment for Text-based Person Search

Generalizing Supervised Deep Learning MRI Reconstruction to Multiple and Unseen Contrasts using Meta-Learning Hypernetworks

One-step Multi-view Clustering with Diverse Representation

First Place Solution to the CVPR'2023 AQTC Challenge: A Function-Interaction Centric Approach with Spatiotemporal Visual-Language Alignment

OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding

Multi-scale Transformer Network with Edge-aware Pre-training for Cross-Modality MR Image Synthesis

SGDraw: Scene Graph Drawing Interface Using Object-Oriented Representation

InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning

Towards a Robust Sensor Fusion Step for 3D Object Detection on Corrupted Data

Improving Cytoarchitectonic Segmentation of Human Brain Areas with Self-supervised Siamese Networks

Joint Adaptive Representations for Image-Language Learning

HypLiLoc: Towards Effective LiDAR Pose Regression with Hyperbolic Fusion

MMNet: Multi-Mask Network for Referring Image Segmentation

Fast Monocular Scene Reconstruction with Global-Sparse Local-Dense Grids

Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining

Towards Long-Tailed 3D Detection

An Interactively Reinforced Paradigm for Joint Infrared-Visible Image Fusion and Saliency Object Detection

FitMe: Deep Photorealistic 3D Morphable Model Avatars

Pushing the Boundaries of Tractable Multiperspective Reasoning: A Deduction Calculus for Standpoint EL+

CLIP-Lite: Information Efficient Visual Representation Learning with Language Supervision

E2TIMT: Efficient and Effective Modal Adapter for Text Image Machine Translation

Tractable Diversity: Scalable Multiperspective Ontology Management via Standpoint EL

Keeping it Simple: Language Models can learn Complex Molecular Distributions

Block the Label and Noise: An N-Gram Masked Speller for Chinese Spell Checking