Alert button

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

Watch What You Pretrain For: Targeted, Transferable Adversarial Examples on Self-Supervised Speech Recognition models

Sep 29, 2022
Raphael Olivier, Hadi Abdullah, Bhiksha Raj

Figure 1 for Watch What You Pretrain For: Targeted, Transferable Adversarial Examples on Self-Supervised Speech Recognition models
Figure 2 for Watch What You Pretrain For: Targeted, Transferable Adversarial Examples on Self-Supervised Speech Recognition models
Figure 3 for Watch What You Pretrain For: Targeted, Transferable Adversarial Examples on Self-Supervised Speech Recognition models
Figure 4 for Watch What You Pretrain For: Targeted, Transferable Adversarial Examples on Self-Supervised Speech Recognition models
Viaarxiv icon

Recognition of Implicit Geographic Movement in Text

Jan 30, 2022
Scott Pezanowski, Prasenjit Mitra

Figure 1 for Recognition of Implicit Geographic Movement in Text
Figure 2 for Recognition of Implicit Geographic Movement in Text
Figure 3 for Recognition of Implicit Geographic Movement in Text
Figure 4 for Recognition of Implicit Geographic Movement in Text
Viaarxiv icon

PP-StructureV2: A Stronger Document Analysis System

Oct 11, 2022
Chenxia Li, Ruoyu Guo, Jun Zhou, Mengtao An, Yuning Du, Lingfeng Zhu, Yi Liu, Xiaoguang Hu, Dianhai Yu

Figure 1 for PP-StructureV2: A Stronger Document Analysis System
Figure 2 for PP-StructureV2: A Stronger Document Analysis System
Figure 3 for PP-StructureV2: A Stronger Document Analysis System
Figure 4 for PP-StructureV2: A Stronger Document Analysis System
Viaarxiv icon

Semantic-based Pre-training for Dialogue Understanding

Sep 19, 2022
Xuefeng Bai, Linfeng Song, Yue Zhang

Figure 1 for Semantic-based Pre-training for Dialogue Understanding
Figure 2 for Semantic-based Pre-training for Dialogue Understanding
Figure 3 for Semantic-based Pre-training for Dialogue Understanding
Figure 4 for Semantic-based Pre-training for Dialogue Understanding
Viaarxiv icon

EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive Pruning

Oct 14, 2022
Tiannan Wang, Wangchunshu Zhou, Yan Zeng, Xinsong Zhang

Figure 1 for EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive Pruning
Figure 2 for EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive Pruning
Figure 3 for EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive Pruning
Figure 4 for EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive Pruning
Viaarxiv icon

Hidden bawls, whispers, and yelps: can text be made to sound more than just its words?

Feb 22, 2022
Caluã de Lacerda Pataca, Paula Dornhofer Paro Costa

Figure 1 for Hidden bawls, whispers, and yelps: can text be made to sound more than just its words?
Figure 2 for Hidden bawls, whispers, and yelps: can text be made to sound more than just its words?
Figure 3 for Hidden bawls, whispers, and yelps: can text be made to sound more than just its words?
Figure 4 for Hidden bawls, whispers, and yelps: can text be made to sound more than just its words?
Viaarxiv icon

Towards Fast Adaptation of Pretrained Contrastive Models for Multi-channel Video-Language Retrieval

Jun 05, 2022
Xudong Lin, Simran Tiwari, Shiyuan Huang, Manling Li, Mike Zheng Shou, Heng Ji, Shih-Fu Chang

Figure 1 for Towards Fast Adaptation of Pretrained Contrastive Models for Multi-channel Video-Language Retrieval
Figure 2 for Towards Fast Adaptation of Pretrained Contrastive Models for Multi-channel Video-Language Retrieval
Figure 3 for Towards Fast Adaptation of Pretrained Contrastive Models for Multi-channel Video-Language Retrieval
Figure 4 for Towards Fast Adaptation of Pretrained Contrastive Models for Multi-channel Video-Language Retrieval
Viaarxiv icon

Diachronic Text Mining Investigation of Therapeutic Candidates for COVID-19

Oct 26, 2021
James Powell, Kari Sentz

Figure 1 for Diachronic Text Mining Investigation of Therapeutic Candidates for COVID-19
Figure 2 for Diachronic Text Mining Investigation of Therapeutic Candidates for COVID-19
Figure 3 for Diachronic Text Mining Investigation of Therapeutic Candidates for COVID-19
Figure 4 for Diachronic Text Mining Investigation of Therapeutic Candidates for COVID-19
Viaarxiv icon

SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training

Oct 20, 2021
Ankur Bapna, Yu-an Chung, Nan Wu, Anmol Gulati, Ye Jia, Jonathan H. Clark, Melvin Johnson, Jason Riesa, Alexis Conneau, Yu Zhang

Figure 1 for SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training
Figure 2 for SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training
Figure 3 for SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training
Figure 4 for SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training
Viaarxiv icon

SVL-Adapter: Self-Supervised Adapter for Vision-Language Pretrained Models

Oct 07, 2022
Omiros Pantazis, Gabriel Brostow, Kate Jones, Oisin Mac Aodha

Figure 1 for SVL-Adapter: Self-Supervised Adapter for Vision-Language Pretrained Models
Figure 2 for SVL-Adapter: Self-Supervised Adapter for Vision-Language Pretrained Models
Figure 3 for SVL-Adapter: Self-Supervised Adapter for Vision-Language Pretrained Models
Figure 4 for SVL-Adapter: Self-Supervised Adapter for Vision-Language Pretrained Models
Viaarxiv icon