Alert button

"Text": models, code, and papers
Alert button

DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting

Nov 19, 2022
Maoyuan Ye, Jing Zhang, Shanshan Zhao, Juhua Liu, Tongliang Liu, Bo Du, Dacheng Tao

Figure 1 for DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting
Figure 2 for DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting
Figure 3 for DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting
Figure 4 for DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting
Viaarxiv icon

Three ways to improve feature alignment for open vocabulary detection

Mar 23, 2023
Relja Arandjelović, Alex Andonian, Arthur Mensch, Olivier J. Hénaff, Jean-Baptiste Alayrac, Andrew Zisserman

Figure 1 for Three ways to improve feature alignment for open vocabulary detection
Figure 2 for Three ways to improve feature alignment for open vocabulary detection
Figure 3 for Three ways to improve feature alignment for open vocabulary detection
Figure 4 for Three ways to improve feature alignment for open vocabulary detection
Viaarxiv icon

Laziness Is a Virtue When It Comes to Compositionality in Neural Semantic Parsing

May 07, 2023
Maxwell Crouse, Pavan Kapanipathi, Subhajit Chaudhury, Tahira Naseem, Ramon Astudillo, Achille Fokoue, Tim Klinger

Figure 1 for Laziness Is a Virtue When It Comes to Compositionality in Neural Semantic Parsing
Figure 2 for Laziness Is a Virtue When It Comes to Compositionality in Neural Semantic Parsing
Figure 3 for Laziness Is a Virtue When It Comes to Compositionality in Neural Semantic Parsing
Figure 4 for Laziness Is a Virtue When It Comes to Compositionality in Neural Semantic Parsing
Viaarxiv icon

MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks

Mar 30, 2023
Weicheng Kuo, AJ Piergiovanni, Dahun Kim, Xiyang Luo, Ben Caine, Wei Li, Abhijit Ogale, Luowei Zhou, Andrew Dai, Zhifeng Chen, Claire Cui, Anelia Angelova

Figure 1 for MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks
Figure 2 for MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks
Figure 3 for MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks
Figure 4 for MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks
Viaarxiv icon

Know What I don't Know: Handling Ambiguous and Unanswerable Questions for Text-to-SQL

Dec 17, 2022
Bing Wang, Yan Gao, Zhoujun Li, Jian-Guang Lou

Figure 1 for Know What I don't Know: Handling Ambiguous and Unanswerable Questions for Text-to-SQL
Figure 2 for Know What I don't Know: Handling Ambiguous and Unanswerable Questions for Text-to-SQL
Figure 3 for Know What I don't Know: Handling Ambiguous and Unanswerable Questions for Text-to-SQL
Figure 4 for Know What I don't Know: Handling Ambiguous and Unanswerable Questions for Text-to-SQL
Viaarxiv icon

What does ChatGPT return about human values? Exploring value bias in ChatGPT using a descriptive value theory

Apr 07, 2023
Ronald Fischer, Markus Luczak-Roesch, Johannes A Karl

Figure 1 for What does ChatGPT return about human values? Exploring value bias in ChatGPT using a descriptive value theory
Figure 2 for What does ChatGPT return about human values? Exploring value bias in ChatGPT using a descriptive value theory
Figure 3 for What does ChatGPT return about human values? Exploring value bias in ChatGPT using a descriptive value theory
Figure 4 for What does ChatGPT return about human values? Exploring value bias in ChatGPT using a descriptive value theory
Viaarxiv icon

Extreme Classification for Answer Type Prediction in Question Answering

Apr 26, 2023
Vinay Setty

Figure 1 for Extreme Classification for Answer Type Prediction in Question Answering
Figure 2 for Extreme Classification for Answer Type Prediction in Question Answering
Viaarxiv icon

ArtGPT-4: Artistic Vision-Language Understanding with Adapter-enhanced MiniGPT-4

May 12, 2023
Zhengqing Yuan, Huiwen Xue, Xinyi Wang, Yongming Liu, Zhuanzhe Zhao, Kun Wang

Figure 1 for ArtGPT-4: Artistic Vision-Language Understanding with Adapter-enhanced MiniGPT-4
Figure 2 for ArtGPT-4: Artistic Vision-Language Understanding with Adapter-enhanced MiniGPT-4
Figure 3 for ArtGPT-4: Artistic Vision-Language Understanding with Adapter-enhanced MiniGPT-4
Figure 4 for ArtGPT-4: Artistic Vision-Language Understanding with Adapter-enhanced MiniGPT-4
Viaarxiv icon

Language Model Behavior: A Comprehensive Survey

Mar 20, 2023
Tyler A. Chang, Benjamin K. Bergen

Viaarxiv icon

Extending TrOCR for Text Localization-Free OCR of Full-Page Scanned Receipt Images

Dec 13, 2022
Hongkuan Zhang, Edward Whittaker, Ikuo Kitagishi

Figure 1 for Extending TrOCR for Text Localization-Free OCR of Full-Page Scanned Receipt Images
Figure 2 for Extending TrOCR for Text Localization-Free OCR of Full-Page Scanned Receipt Images
Figure 3 for Extending TrOCR for Text Localization-Free OCR of Full-Page Scanned Receipt Images
Figure 4 for Extending TrOCR for Text Localization-Free OCR of Full-Page Scanned Receipt Images
Viaarxiv icon