Alert button

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

InfoCTM: A Mutual Information Maximization Perspective of Cross-Lingual Topic Modeling

Apr 07, 2023
Xiaobao Wu, Xinshuai Dong, Thong Nguyen, Chaoqun Liu, Liangming Pan, Anh Tuan Luu

Figure 1 for InfoCTM: A Mutual Information Maximization Perspective of Cross-Lingual Topic Modeling
Figure 2 for InfoCTM: A Mutual Information Maximization Perspective of Cross-Lingual Topic Modeling
Figure 3 for InfoCTM: A Mutual Information Maximization Perspective of Cross-Lingual Topic Modeling
Figure 4 for InfoCTM: A Mutual Information Maximization Perspective of Cross-Lingual Topic Modeling
Viaarxiv icon

JEIT: Joint End-to-End Model and Internal Language Model Training for Speech Recognition

Feb 16, 2023
Zhong Meng, Weiran Wang, Rohit Prabhavalkar, Tara N. Sainath, Tongzhou Chen, Ehsan Variani, Yu Zhang, Bo Li, Andrew Rosenberg, Bhuvana Ramabhadran

Figure 1 for JEIT: Joint End-to-End Model and Internal Language Model Training for Speech Recognition
Figure 2 for JEIT: Joint End-to-End Model and Internal Language Model Training for Speech Recognition
Figure 3 for JEIT: Joint End-to-End Model and Internal Language Model Training for Speech Recognition
Figure 4 for JEIT: Joint End-to-End Model and Internal Language Model Training for Speech Recognition
Viaarxiv icon

Model Criticism for Long-Form Text Generation

Oct 16, 2022
Yuntian Deng, Volodymyr Kuleshov, Alexander M. Rush

Figure 1 for Model Criticism for Long-Form Text Generation
Figure 2 for Model Criticism for Long-Form Text Generation
Figure 3 for Model Criticism for Long-Form Text Generation
Figure 4 for Model Criticism for Long-Form Text Generation
Viaarxiv icon

Affect-Conditioned Image Generation

Feb 20, 2023
Francisco Ibarrola, Rohan Lulham, Kazjon Grace

Figure 1 for Affect-Conditioned Image Generation
Figure 2 for Affect-Conditioned Image Generation
Figure 3 for Affect-Conditioned Image Generation
Figure 4 for Affect-Conditioned Image Generation
Viaarxiv icon

CLIPER: A Unified Vision-Language Framework for In-the-Wild Facial Expression Recognition

Mar 01, 2023
Hanting Li, Hongjing Niu, Zhaoqing Zhu, Feng Zhao

Figure 1 for CLIPER: A Unified Vision-Language Framework for In-the-Wild Facial Expression Recognition
Figure 2 for CLIPER: A Unified Vision-Language Framework for In-the-Wild Facial Expression Recognition
Figure 3 for CLIPER: A Unified Vision-Language Framework for In-the-Wild Facial Expression Recognition
Figure 4 for CLIPER: A Unified Vision-Language Framework for In-the-Wild Facial Expression Recognition
Viaarxiv icon

Text2Light: Zero-Shot Text-Driven HDR Panorama Generation

Oct 02, 2022
Zhaoxi Chen, Guangcong Wang, Ziwei Liu

Figure 1 for Text2Light: Zero-Shot Text-Driven HDR Panorama Generation
Figure 2 for Text2Light: Zero-Shot Text-Driven HDR Panorama Generation
Figure 3 for Text2Light: Zero-Shot Text-Driven HDR Panorama Generation
Figure 4 for Text2Light: Zero-Shot Text-Driven HDR Panorama Generation
Viaarxiv icon

An Information Extraction Study: Take In Mind the Tokenization!

Apr 01, 2023
Christos Theodoropoulos, Marie-Francine Moens

Figure 1 for An Information Extraction Study: Take In Mind the Tokenization!
Figure 2 for An Information Extraction Study: Take In Mind the Tokenization!
Figure 3 for An Information Extraction Study: Take In Mind the Tokenization!
Figure 4 for An Information Extraction Study: Take In Mind the Tokenization!
Viaarxiv icon

Random Text Perturbations Work, but not Always

Sep 02, 2022
Zhengxiang Wang

Figure 1 for Random Text Perturbations Work, but not Always
Figure 2 for Random Text Perturbations Work, but not Always
Figure 3 for Random Text Perturbations Work, but not Always
Figure 4 for Random Text Perturbations Work, but not Always
Viaarxiv icon

Scene Text Image Super-Resolution via Content Perceptual Loss and Criss-Cross Transformer Blocks

Oct 13, 2022
Rui Qin, Bin Wang, Yu-Wing Tai

Figure 1 for Scene Text Image Super-Resolution via Content Perceptual Loss and Criss-Cross Transformer Blocks
Figure 2 for Scene Text Image Super-Resolution via Content Perceptual Loss and Criss-Cross Transformer Blocks
Figure 3 for Scene Text Image Super-Resolution via Content Perceptual Loss and Criss-Cross Transformer Blocks
Figure 4 for Scene Text Image Super-Resolution via Content Perceptual Loss and Criss-Cross Transformer Blocks
Viaarxiv icon

Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos

Mar 11, 2023
Teng Wang, Jinrui Zhang, Feng Zheng, Wenhao Jiang, Ran Cheng, Ping Luo

Figure 1 for Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos
Figure 2 for Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos
Figure 3 for Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos
Figure 4 for Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos
Viaarxiv icon