语言大模型 / LLM - arXivDaily 专题

2406.07537 2024-06-12 cs.CV 78%

Autoregressive Pretraining with Mamba in Vision

Sucheng Ren, Xianhang Li, Haoqin Tu, Feng Wang, Fangxun Shu, Lei Zhang, Jieru Mei, Linjie Yang, Peng Wang, Heng Wang, Alan Yuille, Cihang Xie

专题命中预训练与数据：pretraining(title,abstract)

2402.16164 2024-06-11 cs.CV 78%

Task Specific Pretraining with Noisy Labels for Remote Sensing Image Segmentation

Chenying Liu, Conrad M Albrecht, Yi Wang, Xiao Xiang Zhu

专题命中预训练与数据：pretraining(title,abstract)

Comments To appear as a conference paper at IEEE IGARSS 2024

2401.07527 2024-05-29 cs.CV 78%

One for All: Toward Unified Foundation Models for Earth Vision

Zhitong Xiong, Yi Wang, Fahong Zhang, Xiao Xiang Zhu

专题命中预训练与数据：foundation model(title,abstract)

Comments 5 pages

2403.00206 2024-05-24 cs.CV 78%

MaskLRF: Self-supervised Pretraining via Masked Autoencoding of Local Reference Frames for Rotation-invariant 3D Point Set Analysis

Takahiko Furuya

专题命中预训练与数据：pretraining(title,abstract)

Comments Accepted to the IEEE Access journal

2307.12018 2024-05-22 cs.CV 78%

GEM: Boost Simple Network for Glass Surface Segmentation via Vision Foundation Models

Jing Hao, Moyun Liu, Jinrong Yang, Kuo Feng Hung

专题命中预训练与数据：foundation model(title,abstract)

Comments 12 pages, 8 figures, 8 tables

2405.12018 2024-05-21 cs.CV 78%

Continuous Sign Language Recognition with Adapted Conformer via Unsupervised Pretraining

Neena Aloysius, Geetha M, Prema Nedungadi

专题命中预训练与数据：pretraining(title,abstract)

2304.06911 2024-04-30 cs.CV 78%

3D Feature Prediction for Masked-AutoEncoder-Based Point Cloud Pretraining

Siming Yan, Yuqi Yang, Yuxiao Guo, Hao Pan, Peng-shuai Wang, Xin Tong, Yang Liu, Qixing Huang

专题命中预训练与数据：pretraining(title,abstract)

Comments Published in ICLR 2024

2404.09732 2024-04-16 cs.CV 78%

Photo-Realistic Image Restoration in the Wild with Controlled Vision-Language Models

Ziwei Luo, Fredrik K. Gustafsson, Zheng Zhao, Jens Sjölund, Thomas B. Schön

专题命中预训练与数据：language model(title,abstract)

Comments CVPRW 2024; Code: https://github.com/Algolzw/daclip-uir

2211.06687 2024-03-25 cs.SD eess.AS 78%

Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation

Yusong Wu, Ke Chen, Tianyu Zhang, Yuchen Hui, Marianna Nezhurina, Taylor Berg-Kirkpatrick, Shlomo Dubnov

专题命中预训练与数据：pretraining(title,abstract)

2403.11450 2024-03-19 cs.CV 78%

Zero-shot Compound Expression Recognition with Visual Language Model at the 6th ABAW Challenge

Jiahe Wang, Jiale Huang, Bingzhao Cai, Yifan Cao, Xin Yun, Shangfei Wang

专题命中预训练与数据：language model(title,abstract)

Comments USTC-AC's paper for Compound Expression (CE) Recognition Challenge in 6th Workshop and Competition on Affective Behavior Analysis in-the-wild (ABAW)

2403.10191 2024-03-18 cs.CV 78%

Generative Region-Language Pretraining for Open-Ended Object Detection

Chuang Lin, Yi Jiang, Lizhen Qu, Zehuan Yuan, Jianfei Cai

专题命中预训练与数据：pretraining(title)；language model(abstract)

Comments CVPR 2024

2403.09493 2024-03-15 cs.CV 78%

Anomaly Detection by Adapting a pre-trained Vision Language Model

Yuxuan Cai, Xinwei He, Dingkang Liang, Ao Tong, Xiang Bai

专题命中预训练与数据：language model(title,abstract)

2403.06453 2024-03-12 cs.CV cs.GR 78%

FontCLIP: A Semantic Typography Visual-Language Model for Multilingual Font Applications

Yuki Tatsukawa, I-Chao Shen, Anran Qi, Yuki Koyama, Takeo Igarashi, Ariel Shamir

专题命中预训练与数据：language model(title,abstract)

Comments 11 pages. Eurographics 2024. https://yukistavailable.github.io/fontclip.github.io/

2402.18476 2024-02-29 cs.CV 78%

IBD: Alleviating Hallucinations in Large Vision-Language Models via Image-Biased Decoding

Lanyun Zhu, Deyi Ji, Tianrun Chen, Peng Xu, Jieping Ye, Jun Liu

专题命中预训练与数据：language model(title,abstract)

2402.14215 2024-02-23 cs.CV 78%

Swin3D++: Effective Multi-Source Pretraining for 3D Indoor Scene Understanding

Yu-Qi Yang, Yu-Xiao Guo, Yang Liu

专题命中预训练与数据：pretraining(title,abstract)

Comments technical report

2306.12106 2024-02-20 cs.CV 78%

ViTEraser: Harnessing the Power of Vision Transformers for Scene Text Removal with SegMIM Pretraining

Dezhi Peng, Chongyu Liu, Yuliang Liu, Lianwen Jin

专题命中预训练与数据：pretraining(title,abstract)

Comments AAAI 2024; Full Version

2402.06198 2024-02-14 cs.CV 78%

GS-CLIP: Gaussian Splatting for Contrastive Language-Image-3D Pretraining from Real-World Data

Haoyuan Li, Yanpeng Zhou, Yihan Zeng, Hang Xu, Xiaodan Liang

专题命中预训练与数据：pretraining(title)；language model(abstract)

Comments The content of the technical report needs to be updated and retracted to avoid other impacts

2402.03823 2024-02-07 q-bio.QM 78%

Learning immune receptor representations with protein language models

Andreas Dounas, Tudor-Stefan Cotet, Alexander Yermanos

专题命中预训练与数据：language model(title,abstract)

2301.11915 2024-01-24 cs.CV 78%

Understanding Self-Supervised Pretraining with Part-Aware Representation Learning

Jie Zhu, Jiyang Qi, Mingyu Ding, Xiaokang Chen, Ping Luo, Xinggang Wang, Wenyu Liu, Leye Wang, Jingdong Wang

专题命中预训练与数据：pretraining(title,abstract)

Comments Accepted by TMLR

2401.09038 2024-01-18 cs.RO 78%

Visual Robotic Manipulation with Depth-Aware Pretraining

Wanying Wang, Jinming Li, Yichen Zhu, Zhiyuan Xu, Zhengping Che, Yaxin Peng, Chaomin Shen, Dong Liu, Feifei Feng, Jian Tang

专题命中预训练与数据：pretraining(title,abstract)

Comments submitted to ICRA2024

2401.08045 2024-01-17 cs.CV 78%

Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and Opportunities

Xu Yan, Haiming Zhang, Yingjie Cai, Jingming Guo, Weichao Qiu, Bin Gao, Kaiqiang Zhou, Yue Zhao, Huan Jin, Jiantao Gao, Zhen Li, Lihui Jiang, Wei Zhang, Hongbo Zhang, Dengxin Dai, Bingbing Liu

专题命中预训练与数据：foundation model(title,abstract)

Comments Github Repo: https://github.com/zhanghm1995/Forge_VFM4AD

2306.16741 2024-01-10 cs.CV 78%

Foundation Model for Endoscopy Video Analysis via Large-scale Self-supervised Pre-train

Zhao Wang, Chang Liu, Shaoting Zhang, Qi Dou

专题命中预训练与数据：foundation model(title,abstract)

Comments MICCAI 2023 camera-ready version

2310.17974 2024-01-10 cs.CV eess.IV 78%

FaultSeg Swin-UNETR: Transformer-Based Self-Supervised Pretraining Model for Fault Recognition

Zeren Zhang, Ran Chen, Jinwen Ma

专题命中预训练与数据：pretraining(title,abstract)

Comments The logical flow and background of the article need significant revisions

2312.09747 2024-01-09 eess.AS eess.SP 78%

SELM: Speech Enhancement Using Discrete Tokens and Language Models

Ziqian Wang, Xinfa Zhu, Zihan Zhang, YuanJun Lv, Ning Jiang, Guoqing Zhao, Lei Xie

专题命中预训练与数据：language model(title,abstract)

Comments Accepted by ICASSP 2024

2212.10368 2023-12-27 cs.CV 78%

Masked Event Modeling: Self-Supervised Pretraining for Event Cameras

Simon Klenk, David Bonello, Lukas Koestler, Nikita Araslanov, Daniel Cremers

专题命中预训练与数据：pretraining(title,abstract)

Comments To appear at WACV 2024. Code: https://github.com/tum-vision/mem

2312.12661 2023-12-21 cs.CV 78%

Misalign, Contrast then Distill: Rethinking Misalignments in Language-Image Pretraining

Bumsoo Kim, Yeonsik Jo, Jinhyung Kim, Seung Hwan Kim

专题命中预训练与数据：pretraining(title,abstract)

Comments ICCV 2023

2304.06385 2023-12-21 cs.CV 78%

TransHP: Image Classification with Hierarchical Prompting

Wenhao Wang, Yifan Sun, Wei Li, Yi Yang

专题命中预训练与数据：prompting(title,abstract)

Comments Accepted to NeurIPS 2023; Released code

2309.02791 2023-12-18 physics.geo-ph 78%

Seismic Foundation Model (SFM): a new generation deep learning model in geophysics

Hanlin Sheng, Xinming Wu, Xu Si, Jintao Li, Sibo Zhang, Xudong Duan

专题命中预训练与数据：foundation model(title,abstract)

Comments 27 pages, 9 figures, and 4 tables

2312.09249 2023-12-15 cs.CV cs.GR 78%

ZeroRF: Fast Sparse View 360° Reconstruction with Zero Pretraining

Ruoxi Shi, Xinyue Wei, Cheng Wang, Hao Su

专题命中预训练与数据：pretraining(title,abstract)

Comments Project page: https://sarahweiii.github.io/zerorf/

2305.12530 2023-12-12 eess.AS cs.SD 78%

Towards Robust Family-Infant Audio Analysis Based on Unsupervised Pretraining of Wav2vec 2.0 on Large-Scale Unlabeled Family Audio

Jialu Li, Mark Hasegawa-Johnson, Nancy L. McElwain

专题命中预训练与数据：pretraining(title,abstract)

Comments Proceedings of Interspeech 2023; v4 version updates: correction of W2V2-base pretrained on 960-hour of LibriSpeech and number of families participated for LENA home recordings

1. 预训练与数据 12393 篇

Autoregressive Pretraining with Mamba in Vision

Task Specific Pretraining with Noisy Labels for Remote Sensing Image Segmentation

One for All: Toward Unified Foundation Models for Earth Vision

MaskLRF: Self-supervised Pretraining via Masked Autoencoding of Local Reference Frames for Rotation-invariant 3D Point Set Analysis

GEM: Boost Simple Network for Glass Surface Segmentation via Vision Foundation Models

Continuous Sign Language Recognition with Adapted Conformer via Unsupervised Pretraining

3D Feature Prediction for Masked-AutoEncoder-Based Point Cloud Pretraining

Photo-Realistic Image Restoration in the Wild with Controlled Vision-Language Models

Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation

Zero-shot Compound Expression Recognition with Visual Language Model at the 6th ABAW Challenge

Generative Region-Language Pretraining for Open-Ended Object Detection

Anomaly Detection by Adapting a pre-trained Vision Language Model

FontCLIP: A Semantic Typography Visual-Language Model for Multilingual Font Applications

IBD: Alleviating Hallucinations in Large Vision-Language Models via Image-Biased Decoding

Swin3D++: Effective Multi-Source Pretraining for 3D Indoor Scene Understanding

ViTEraser: Harnessing the Power of Vision Transformers for Scene Text Removal with SegMIM Pretraining

GS-CLIP: Gaussian Splatting for Contrastive Language-Image-3D Pretraining from Real-World Data

Learning immune receptor representations with protein language models

Understanding Self-Supervised Pretraining with Part-Aware Representation Learning

Visual Robotic Manipulation with Depth-Aware Pretraining

Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and Opportunities

Foundation Model for Endoscopy Video Analysis via Large-scale Self-supervised Pre-train

FaultSeg Swin-UNETR: Transformer-Based Self-Supervised Pretraining Model for Fault Recognition

SELM: Speech Enhancement Using Discrete Tokens and Language Models

Masked Event Modeling: Self-Supervised Pretraining for Event Cameras

Misalign, Contrast then Distill: Rethinking Misalignments in Language-Image Pretraining

TransHP: Image Classification with Hierarchical Prompting

Seismic Foundation Model (SFM): a new generation deep learning model in geophysics

ZeroRF: Fast Sparse View 360° Reconstruction with Zero Pretraining

Towards Robust Family-Infant Audio Analysis Based on Unsupervised Pretraining of Wav2vec 2.0 on Large-Scale Unlabeled Family Audio