Alert button

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

Transferable Models for Bioacoustics with Human Language Supervision

Aug 09, 2023
David Robinson, Adelaide Robinson, Lily Akrapongpisak

Viaarxiv icon

DiVa: An Iterative Framework to Harvest More Diverse and Valid Labels from User Comments for Music

Aug 09, 2023
Hongru Liang, Jingyao Liu, Yuanxin Xiang, Jiachen Du, Lanjun Zhou, Shushen Pan, Wenqiang Lei

Figure 1 for DiVa: An Iterative Framework to Harvest More Diverse and Valid Labels from User Comments for Music
Figure 2 for DiVa: An Iterative Framework to Harvest More Diverse and Valid Labels from User Comments for Music
Figure 3 for DiVa: An Iterative Framework to Harvest More Diverse and Valid Labels from User Comments for Music
Figure 4 for DiVa: An Iterative Framework to Harvest More Diverse and Valid Labels from User Comments for Music
Viaarxiv icon

Cocktail: Mixing Multi-Modality Controls for Text-Conditional Image Generation

Jun 01, 2023
Minghui Hu, Jianbin Zheng, Daqing Liu, Chuanxia Zheng, Chaoyue Wang, Dacheng Tao, Tat-Jen Cham

Figure 1 for Cocktail: Mixing Multi-Modality Controls for Text-Conditional Image Generation
Figure 2 for Cocktail: Mixing Multi-Modality Controls for Text-Conditional Image Generation
Figure 3 for Cocktail: Mixing Multi-Modality Controls for Text-Conditional Image Generation
Figure 4 for Cocktail: Mixing Multi-Modality Controls for Text-Conditional Image Generation
Viaarxiv icon

Bridging High-Quality Audio and Video via Language for Sound Effects Retrieval from Visual Queries

Aug 17, 2023
Julia Wilkins, Justin Salamon, Magdalena Fuentes, Juan Pablo Bello, Oriol Nieto

Figure 1 for Bridging High-Quality Audio and Video via Language for Sound Effects Retrieval from Visual Queries
Figure 2 for Bridging High-Quality Audio and Video via Language for Sound Effects Retrieval from Visual Queries
Figure 3 for Bridging High-Quality Audio and Video via Language for Sound Effects Retrieval from Visual Queries
Viaarxiv icon

Towards End-to-end Speech-to-text Summarization

Jun 06, 2023
Raul Monteiro, Diogo Pernes

Figure 1 for Towards End-to-end Speech-to-text Summarization
Figure 2 for Towards End-to-end Speech-to-text Summarization
Figure 3 for Towards End-to-end Speech-to-text Summarization
Figure 4 for Towards End-to-end Speech-to-text Summarization
Viaarxiv icon

Large Language Models are Effective Table-to-Text Generators, Evaluators, and Feedback Providers

May 24, 2023
Yilun Zhao, Haowei Zhang, Shengyun Si, Linyong Nan, Xiangru Tang, Arman Cohan

Figure 1 for Large Language Models are Effective Table-to-Text Generators, Evaluators, and Feedback Providers
Figure 2 for Large Language Models are Effective Table-to-Text Generators, Evaluators, and Feedback Providers
Figure 3 for Large Language Models are Effective Table-to-Text Generators, Evaluators, and Feedback Providers
Figure 4 for Large Language Models are Effective Table-to-Text Generators, Evaluators, and Feedback Providers
Viaarxiv icon

BELB: a Biomedical Entity Linking Benchmark

Aug 22, 2023
Samuele Garda, Leon Weber-Genzel, Robert Martin, Ulf Leser

Figure 1 for BELB: a Biomedical Entity Linking Benchmark
Figure 2 for BELB: a Biomedical Entity Linking Benchmark
Figure 3 for BELB: a Biomedical Entity Linking Benchmark
Figure 4 for BELB: a Biomedical Entity Linking Benchmark
Viaarxiv icon

SPANet: Frequency-balancing Token Mixer using Spectral Pooling Aggregation Modulation

Aug 22, 2023
Guhnoo Yun, Juhan Yoo, Kijung Kim, Jeongho Lee, Dong Hwan Kim

Viaarxiv icon

Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features

Aug 22, 2023
Alberto Baldrati, Marco Bertini, Tiberio Uricchio, Alberto del Bimbo

Figure 1 for Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features
Figure 2 for Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features
Figure 3 for Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features
Figure 4 for Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features
Viaarxiv icon

Can Authorship Representation Learning Capture Stylistic Features?

Aug 22, 2023
Andrew Wang, Cristina Aggazzotti, Rebecca Kotula, Rafael Rivera Soto, Marcus Bishop, Nicholas Andrews

Viaarxiv icon