Alert button

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

From Wrong To Right: A Recursive Approach Towards Vision-Language Explanation

Nov 21, 2023
Jiaxin Ge, Sanjay Subramanian, Trevor Darrell, Boyi Li

Viaarxiv icon

The Song Describer Dataset: a Corpus of Audio Captions for Music-and-Language Evaluation

Nov 18, 2023
Ilaria Manco, Benno Weck, SeungHeon Doh, Minz Won, Yixiao Zhang, Dmitry Bodganov, Yusong Wu, Ke Chen, Philip Tovstogan, Emmanouil Benetos, Elio Quinton, György Fazekas, Juhan Nam

Viaarxiv icon

STEER: Unified Style Transfer with Expert Reinforcement

Nov 13, 2023
Skyler Hallinan, Faeze Brahman, Ximing Lu, Jaehun Jung, Sean Welleck, Yejin Choi

Viaarxiv icon

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

Oct 24, 2023
Apostol Vassilev, Honglan Jin, Munawar Hasan

Viaarxiv icon

InfoCL: Alleviating Catastrophic Forgetting in Continual Text Classification from An Information Theoretic Perspective

Oct 10, 2023
Yifan Song, Peiyi Wang, Weimin Xiong, Dawei Zhu, Tianyu Liu, Zhifang Sui, Sujian Li

Figure 1 for InfoCL: Alleviating Catastrophic Forgetting in Continual Text Classification from An Information Theoretic Perspective
Figure 2 for InfoCL: Alleviating Catastrophic Forgetting in Continual Text Classification from An Information Theoretic Perspective
Figure 3 for InfoCL: Alleviating Catastrophic Forgetting in Continual Text Classification from An Information Theoretic Perspective
Figure 4 for InfoCL: Alleviating Catastrophic Forgetting in Continual Text Classification from An Information Theoretic Perspective
Viaarxiv icon

Typing to Listen at the Cocktail Party: Text-Guided Target Speaker Extraction

Oct 11, 2023
Xiang Hao, Jibin Wu, Jianwei Yu, Chenglin Xu, Kay Chen Tan

Figure 1 for Typing to Listen at the Cocktail Party: Text-Guided Target Speaker Extraction
Figure 2 for Typing to Listen at the Cocktail Party: Text-Guided Target Speaker Extraction
Figure 3 for Typing to Listen at the Cocktail Party: Text-Guided Target Speaker Extraction
Figure 4 for Typing to Listen at the Cocktail Party: Text-Guided Target Speaker Extraction
Viaarxiv icon

Enhancing Uncertainty-Based Hallucination Detection with Stronger Focus

Nov 22, 2023
Tianhang Zhang, Lin Qiu, Qipeng Guo, Cheng Deng, Yue Zhang, Zheng Zhang, Chenghu Zhou, Xinbing Wang, Luoyi Fu

Viaarxiv icon

FuseNet: Self-Supervised Dual-Path Network for Medical Image Segmentation

Nov 22, 2023
Amirhossein Kazerouni, Sanaz Karimijafarbigloo, Reza Azad, Yury Velichko, Ulas Bagci, Dorit Merhof

Viaarxiv icon

AI Recommendation System for Enhanced Customer Experience: A Novel Image-to-Text Method

Nov 16, 2023
Mohamaed Foued Ayedi, Hiba Ben Salem, Soulaimen Hammami, Ahmed Ben Said, Rateb Jabbar, Achraf CHabbouh

Figure 1 for AI Recommendation System for Enhanced Customer Experience: A Novel Image-to-Text Method
Figure 2 for AI Recommendation System for Enhanced Customer Experience: A Novel Image-to-Text Method
Figure 3 for AI Recommendation System for Enhanced Customer Experience: A Novel Image-to-Text Method
Figure 4 for AI Recommendation System for Enhanced Customer Experience: A Novel Image-to-Text Method
Viaarxiv icon

Interpreting and Controlling Vision Foundation Models via Text Explanations

Oct 16, 2023
Haozhe Chen, Junfeng Yang, Carl Vondrick, Chengzhi Mao

Viaarxiv icon