语言大模型 / LLM - arXivDaily 专题

2311.02536 2023-11-07 cs.CV 78%

Augment the Pairs: Semantics-Preserving Image-Caption Pair Augmentation for Grounding-Based Vision and Language Models

Jingru Yi, Burak Uzkent, Oana Ignat, Zili Li, Amanmeet Garg, Xiang Yu, Linda Liu

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

Comments Accepted to WACV2024

2310.15019 2023-10-25 cs.LG cs.AI cs.CL 78%

Meta learning with language models: Challenges and opportunities in the classification of imbalanced text

Apostol Vassilev, Honglan Jin, Munawar Hasan

专题命中预训练与数据：language model(title)；分类 cs.CL、cs.AI、cs.LG

Comments 22 pages, including 5 figures, 12 tables, 1 appendix

2206.00311 2023-10-11 cs.CV 78%

MaskOCR: Text Recognition with Masked Encoder-Decoder Pretraining

Pengyuan Lyu, Chengquan Zhang, Shanshan Liu, Meina Qiao, Yangliu Xu, Liang Wu, Kun Yao, Junyu Han, Errui Ding, Jingdong Wang

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

2309.11730 2023-09-28 eess.AS cs.SD 78%

Leveraging In-the-Wild Data for Effective Self-Supervised Pretraining in Speaker Recognition

Shuai Wang, Qibing Bai, Qi Liu, Jianwei Yu, Zhengyang Chen, Bing Han, Yanmin Qian, Haizhou Li

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

Comments submitted to ICASSP 2024

2309.07394 2023-09-22 cs.CV 78%

Nucleus-aware Self-supervised Pretraining Using Unpaired Image-to-image Translation for Histopathology Images

Zhiyun Song, Penghui Du, Junpeng Yan, Kailu Li, Jianzhong Shou, Maode Lai, Yubo Fan, Yan Xu

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

2309.09421 2023-09-19 cs.MM 78%

Unified Pretraining Target Based Video-music Retrieval With Music Rhythm And Video Optical Flow Information

Tianjun Mao, Shansong Liu, Yunxuan Zhang, Dian Li, Ying Shan

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

2307.03275 2023-08-23 cs.CV 78%

To pretrain or not to pretrain? A case study of domain-specific pretraining for semantic segmentation in histopathology

Tushar Kataria, Beatrice Knudsen, Shireen Elhabian

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

2308.09775 2023-08-22 cs.CV 78%

Long-range Multimodal Pretraining for Movie Understanding

Dawit Mureja Argaw, Joon-Young Lee, Markus Woodson, In So Kweon, Fabian Caba Heilbron

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

Comments Accepted to ICCV 2023

2308.08414 2023-08-17 cs.CV 78%

Tem-adapter: Adapting Image-Text Pretraining for Video Question Answer

Guangyi Chen, Xiao Liu, Guangrun Wang, Kun Zhang, Philip H. S. Torr, Xiao-Ping Zhang, Yansong Tang

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

Comments ICCV 2023

2308.05358 2023-08-11 cs.CV 78%

Fine-grained building roof instance segmentation based on domain adapted pretraining and composite dual-backbone

Guozhang Liu, Baochai Peng, Ting Liu, Pan Zhang, Mengke Yuan, Chaoran Lu, Ningning Cao, Sen Zhang, Simin Huang, Tao Wang

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

2209.13042 2023-08-01 cs.RO 78%

Self-Supervised Visuo-Tactile Pretraining to Locate and Follow Garment Features

Justin Kerr, Huang Huang, Albert Wilcox, Ryan Hoque, Jeffrey Ichnowski, Roberto Calandra, Ken Goldberg

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

Comments RSS 2023, site: https://sites.google.com/berkeley.edu/ssvtp

2307.14768 2023-07-28 cs.CV 78%

Gloss-free Sign Language Translation: Improving from Visual-Language Pretraining

Benjia Zhou, Zhigang Chen, Albert Clapés, Jun Wan, Yanyan Liang, Sergio Escalera, Zhen Lei, Du Zhang

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

Comments Accepted to ICCV'23

2307.12854 2023-07-25 cs.CV 78%

Multiscale Video Pretraining for Long-Term Activity Forecasting

Reuben Tan, Matthias De Lange, Michael Iuzzolino, Bryan A. Plummer, Kate Saenko, Karl Ridgeway, Lorenzo Torresani

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

2106.04550 2023-07-21 cs.CV 78%

DETReg: Unsupervised Pretraining with Region Priors for Object Detection

Amir Bar, Xin Wang, Vadim Kantorov, Colorado J Reed, Roei Herzig, Gal Chechik, Anna Rohrbach, Trevor Darrell, Amir Globerson

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

Comments Project page: https://www.amirbar.net/detreg/

2204.02825 2023-07-19 cs.CV 78%

An Empirical Study of Remote Sensing Pretraining

Di Wang, Jing Zhang, Bo Du, Gui-Song Xia, Dacheng Tao

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

Comments Accepted by IEEE TGRS, codes and pretrained models are moved to https://github.com/ViTAE-Transformer/RSP

2306.10146 2023-06-21 cs.CV eess.IV 78%

Multi-task 3D building understanding with multi-modal pretraining

Shicheng Xu

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

Comments 8 pages, 9 figures, 9 tables

2306.07791 2023-06-14 cs.SD eess.AS 78%

Unlocking Foundation Models for Privacy-Enhancing Speech Understanding: An Early Study on Low Resource Speech Training Leveraging Label-guided Synthetic Speech Content

Tiantian Feng, Digbalay Bose, Xuan Shi, Shrikanth Narayanan

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

2306.02867 2023-06-06 cs.IR 78%

Benchmarking Middle-Trained Language Models for Neural Search

Hervé Déjean, Stéphane Clinchant, Carlos Lassance, Simon Lupart, Thibault Formal

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

2208.14754 2023-06-06 cs.IR 78%

LexMAE: Lexicon-Bottlenecked Pretraining for Large-Scale Retrieval

Tao Shen, Xiubo Geng, Chongyang Tao, Can Xu, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang

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

Comments Appeared at ICLR 2023

2302.02318 2023-05-23 cs.CV 78%

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

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

Comments Accepted at ICML 2023

2305.05598 2023-05-10 cs.CV 78%

Region-based Contrastive Pretraining for Medical Image Retrieval with Anatomic Query

Ho Hin Lee, Alberto Santamaria-Pang, Jameson Merkow, Ozan Oktay, Fernando Pérez-García, Javier Alvarez-Valle, Ivan Tarapov

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

2305.03324 2023-05-08 cs.IR 78%

Augmenting Low-Resource Text Classification with Graph-Grounded Pre-training and Prompting

Zhihao Wen, Yuan Fang

专题命中预训练与数据：prompting(title,abstract)

Comments 11 pages, accepted by SIGIR'23

2302.05020 2023-04-18 cs.SE 78%

Impact of Code Language Models on Automated Program Repair

Nan Jiang, Kevin Liu, Thibaud Lutellier, Lin Tan

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

Comments This paper is accepted by 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE)

2211.05778 2023-04-18 cs.CV 78%

InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions

Wenhai Wang, Jifeng Dai, Zhe Chen, Zhenhang Huang, Zhiqi Li, Xizhou Zhu, Xiaowei Hu, Tong Lu, Lewei Lu, Hongsheng Li, Xiaogang Wang, Yu Qiao

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

Comments Accepted to CVPR 2023

2208.12262 2023-04-11 cs.CV 78%

MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining

Xiaoyi Dong, Jianmin Bao, Yinglin Zheng, Ting Zhang, Dongdong Chen, Hao Yang, Ming Zeng, Weiming Zhang, Lu Yuan, Dong Chen, Fang Wen, Nenghai Yu

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

Comments CVPR 2023, code is available at https://github.com/LightDXY/MaskCLIP

2304.03105 2023-04-10 cs.CV 78%

Geometric-aware Pretraining for Vision-centric 3D Object Detection

Linyan Huang, Huijie Wang, Jia Zeng, Shengchuan Zhang, Liujuan Cao, Junchi Yan, Hongyang Li

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

Comments 15 pages, 3 figures

2212.05051 2023-04-06 cs.CV 78%

VindLU: A Recipe for Effective Video-and-Language Pretraining

Feng Cheng, Xizi Wang, Jie Lei, David Crandall, Mohit Bansal, Gedas Bertasius

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

Comments CVPR 2023. Project page: https://klauscc.github.io/vindlu.html

2303.17636 2023-04-03 cs.CV 78%

Whether and When does Endoscopy Domain Pretraining Make Sense?

Dominik Batić, Felix Holm, Ege Özsoy, Tobias Czempiel, Nassir Navab

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

2303.05675 2023-03-13 cs.CV 78%

HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining

Shixiang Tang, Cheng Chen, Qingsong Xie, Meilin Chen, Yizhou Wang, Yuanzheng Ci, Lei Bai, Feng Zhu, Haiyang Yang, Li Yi, Rui Zhao, Wanli Ouyang

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

Comments Accepted to CVPR2023

2303.01237 2023-03-03 cs.CV 78%

FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation

Xiaoyu Shi, Zhaoyang Huang, Dasong Li, Manyuan Zhang, Ka Chun Cheung, Simon See, Hongwei Qin, Jifeng Dai, Hongsheng Li

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

1. 预训练与数据 12429 篇

Augment the Pairs: Semantics-Preserving Image-Caption Pair Augmentation for Grounding-Based Vision and Language Models

Meta learning with language models: Challenges and opportunities in the classification of imbalanced text

MaskOCR: Text Recognition with Masked Encoder-Decoder Pretraining

Leveraging In-the-Wild Data for Effective Self-Supervised Pretraining in Speaker Recognition

Nucleus-aware Self-supervised Pretraining Using Unpaired Image-to-image Translation for Histopathology Images

Unified Pretraining Target Based Video-music Retrieval With Music Rhythm And Video Optical Flow Information

To pretrain or not to pretrain? A case study of domain-specific pretraining for semantic segmentation in histopathology

Long-range Multimodal Pretraining for Movie Understanding

Tem-adapter: Adapting Image-Text Pretraining for Video Question Answer

Fine-grained building roof instance segmentation based on domain adapted pretraining and composite dual-backbone

Self-Supervised Visuo-Tactile Pretraining to Locate and Follow Garment Features

Gloss-free Sign Language Translation: Improving from Visual-Language Pretraining

Multiscale Video Pretraining for Long-Term Activity Forecasting

DETReg: Unsupervised Pretraining with Region Priors for Object Detection

An Empirical Study of Remote Sensing Pretraining

Multi-task 3D building understanding with multi-modal pretraining

Unlocking Foundation Models for Privacy-Enhancing Speech Understanding: An Early Study on Low Resource Speech Training Leveraging Label-guided Synthetic Speech Content

Benchmarking Middle-Trained Language Models for Neural Search

LexMAE: Lexicon-Bottlenecked Pretraining for Large-Scale Retrieval

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

Region-based Contrastive Pretraining for Medical Image Retrieval with Anatomic Query

Augmenting Low-Resource Text Classification with Graph-Grounded Pre-training and Prompting

Impact of Code Language Models on Automated Program Repair

InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions

MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining

Geometric-aware Pretraining for Vision-centric 3D Object Detection

VindLU: A Recipe for Effective Video-and-Language Pretraining

Whether and When does Endoscopy Domain Pretraining Make Sense?

HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining

FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation