Alert button

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

Unified Speech-Text Pre-training for Speech Translation and Recognition

Apr 11, 2022
Yun Tang, Hongyu Gong, Ning Dong, Changhan Wang, Wei-Ning Hsu, Jiatao Gu, Alexei Baevski, Xian Li, Abdelrahman Mohamed, Michael Auli, Juan Pino

Figure 1 for Unified Speech-Text Pre-training for Speech Translation and Recognition
Figure 2 for Unified Speech-Text Pre-training for Speech Translation and Recognition
Figure 3 for Unified Speech-Text Pre-training for Speech Translation and Recognition
Figure 4 for Unified Speech-Text Pre-training for Speech Translation and Recognition
Viaarxiv icon

Arbitrary Shape Text Detection via Boundary Transformer

May 11, 2022
Shi-Xue Zhang, Xiaobin Zhu, Chun Yang, Xu-Cheng Yin

Figure 1 for Arbitrary Shape Text Detection via Boundary Transformer
Figure 2 for Arbitrary Shape Text Detection via Boundary Transformer
Figure 3 for Arbitrary Shape Text Detection via Boundary Transformer
Figure 4 for Arbitrary Shape Text Detection via Boundary Transformer
Viaarxiv icon

SceneComposer: Any-Level Semantic Image Synthesis

Nov 21, 2022
Yu Zeng, Zhe Lin, Jianming Zhang, Qing Liu, John Collomosse, Jason Kuen, Vishal M. Patel

Figure 1 for SceneComposer: Any-Level Semantic Image Synthesis
Figure 2 for SceneComposer: Any-Level Semantic Image Synthesis
Figure 3 for SceneComposer: Any-Level Semantic Image Synthesis
Figure 4 for SceneComposer: Any-Level Semantic Image Synthesis
Viaarxiv icon

AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities

Nov 21, 2022
Zhongzhi Chen, Guang Liu, Bo-Wen Zhang, Fulong Ye, Qinghong Yang, Ledell Wu

Figure 1 for AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities
Figure 2 for AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities
Figure 3 for AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities
Figure 4 for AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities
Viaarxiv icon

T-STAR: Truthful Style Transfer using AMR Graph as Intermediate Representation

Dec 03, 2022
Anubhav Jangra, Preksha Nema, Aravindan Raghuveer

Figure 1 for T-STAR: Truthful Style Transfer using AMR Graph as Intermediate Representation
Figure 2 for T-STAR: Truthful Style Transfer using AMR Graph as Intermediate Representation
Figure 3 for T-STAR: Truthful Style Transfer using AMR Graph as Intermediate Representation
Figure 4 for T-STAR: Truthful Style Transfer using AMR Graph as Intermediate Representation
Viaarxiv icon

Infusing Commonsense World Models with Graph Knowledge

Jan 13, 2023
Alexander Gurung, Mojtaba Komeili, Arthur Szlam, Jason Weston, Jack Urbanek

Figure 1 for Infusing Commonsense World Models with Graph Knowledge
Figure 2 for Infusing Commonsense World Models with Graph Knowledge
Figure 3 for Infusing Commonsense World Models with Graph Knowledge
Figure 4 for Infusing Commonsense World Models with Graph Knowledge
Viaarxiv icon

Relevance Classification of Flood-related Twitter Posts via Multiple Transformers

Jan 01, 2023
Wisal Mukhtiar, Waliiya Rizwan, Aneela Habib, Yasir Saleem Afridi, Laiq Hasan, Kashif Ahmad

Figure 1 for Relevance Classification of Flood-related Twitter Posts via Multiple Transformers
Figure 2 for Relevance Classification of Flood-related Twitter Posts via Multiple Transformers
Figure 3 for Relevance Classification of Flood-related Twitter Posts via Multiple Transformers
Viaarxiv icon

Text Gestalt: Stroke-Aware Scene Text Image Super-Resolution

Dec 13, 2021
Jingye Chen, Haiyang Yu, Jianqi Ma, Bin Li, Xiangyang Xue

Figure 1 for Text Gestalt: Stroke-Aware Scene Text Image Super-Resolution
Figure 2 for Text Gestalt: Stroke-Aware Scene Text Image Super-Resolution
Figure 3 for Text Gestalt: Stroke-Aware Scene Text Image Super-Resolution
Figure 4 for Text Gestalt: Stroke-Aware Scene Text Image Super-Resolution
Viaarxiv icon

Topics in Contextualised Attention Embeddings

Jan 11, 2023
Mozhgan Talebpour, Alba Garcia Seco de Herrera, Shoaib Jameel

Figure 1 for Topics in Contextualised Attention Embeddings
Figure 2 for Topics in Contextualised Attention Embeddings
Figure 3 for Topics in Contextualised Attention Embeddings
Figure 4 for Topics in Contextualised Attention Embeddings
Viaarxiv icon

SensePOLAR: Word sense aware interpretability for pre-trained contextual word embeddings

Jan 11, 2023
Jan Engler, Sandipan Sikdar, Marlene Lutz, Markus Strohmaier

Figure 1 for SensePOLAR: Word sense aware interpretability for pre-trained contextual word embeddings
Figure 2 for SensePOLAR: Word sense aware interpretability for pre-trained contextual word embeddings
Figure 3 for SensePOLAR: Word sense aware interpretability for pre-trained contextual word embeddings
Figure 4 for SensePOLAR: Word sense aware interpretability for pre-trained contextual word embeddings
Viaarxiv icon