Alert button

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

Low-rank Matrix Recovery With Unknown Correspondence

Oct 18, 2021
Zhiwei Tang, Tsung-Hui Chang, Xiaojing Ye, Hongyuan Zha

Figure 1 for Low-rank Matrix Recovery With Unknown Correspondence
Figure 2 for Low-rank Matrix Recovery With Unknown Correspondence
Figure 3 for Low-rank Matrix Recovery With Unknown Correspondence
Figure 4 for Low-rank Matrix Recovery With Unknown Correspondence
Viaarxiv icon

All you need is a second look: Towards Tighter Arbitrary shape text detection

Apr 26, 2020
Meng Cao, Yuexian Zou

Figure 1 for All you need is a second look: Towards Tighter Arbitrary shape text detection
Figure 2 for All you need is a second look: Towards Tighter Arbitrary shape text detection
Figure 3 for All you need is a second look: Towards Tighter Arbitrary shape text detection
Figure 4 for All you need is a second look: Towards Tighter Arbitrary shape text detection
Viaarxiv icon

TiVGAN: Text to Image to Video Generation with Step-by-Step Evolutionary Generator

Sep 04, 2020
Doyeon Kim, Donggyu Joo, Junmo Kim

Figure 1 for TiVGAN: Text to Image to Video Generation with Step-by-Step Evolutionary Generator
Figure 2 for TiVGAN: Text to Image to Video Generation with Step-by-Step Evolutionary Generator
Figure 3 for TiVGAN: Text to Image to Video Generation with Step-by-Step Evolutionary Generator
Figure 4 for TiVGAN: Text to Image to Video Generation with Step-by-Step Evolutionary Generator
Viaarxiv icon

Graph attentive feature aggregation for text-independent speaker verification

Dec 23, 2021
Hye-jin Shim, Jungwoo Heo, Jae-han Park, Ga-hui Lee, Ha-Jin Yu

Figure 1 for Graph attentive feature aggregation for text-independent speaker verification
Figure 2 for Graph attentive feature aggregation for text-independent speaker verification
Figure 3 for Graph attentive feature aggregation for text-independent speaker verification
Figure 4 for Graph attentive feature aggregation for text-independent speaker verification
Viaarxiv icon

Highly Fast Text Segmentation With Pairwise Markov Chains

Feb 17, 2021
Elie Azeraf, Emmanuel Monfrini, Emmanuel Vignon, Wojciech Pieczynski

Figure 1 for Highly Fast Text Segmentation With Pairwise Markov Chains
Figure 2 for Highly Fast Text Segmentation With Pairwise Markov Chains
Figure 3 for Highly Fast Text Segmentation With Pairwise Markov Chains
Figure 4 for Highly Fast Text Segmentation With Pairwise Markov Chains
Viaarxiv icon

DeepHate: Hate Speech Detection via Multi-Faceted Text Representations

Mar 14, 2021
Rui Cao, Roy Ka-Wei Lee, Tuan-Anh Hoang

Figure 1 for DeepHate: Hate Speech Detection via Multi-Faceted Text Representations
Figure 2 for DeepHate: Hate Speech Detection via Multi-Faceted Text Representations
Figure 3 for DeepHate: Hate Speech Detection via Multi-Faceted Text Representations
Figure 4 for DeepHate: Hate Speech Detection via Multi-Faceted Text Representations
Viaarxiv icon

Luganda Text-to-Speech Machine

May 11, 2020
Irene Nandutu, Ernest Mwebaze

Figure 1 for Luganda Text-to-Speech Machine
Figure 2 for Luganda Text-to-Speech Machine
Figure 3 for Luganda Text-to-Speech Machine
Figure 4 for Luganda Text-to-Speech Machine
Viaarxiv icon

XYLayoutLM: Towards Layout-Aware Multimodal Networks For Visually-Rich Document Understanding

Mar 15, 2022
Zhangxuan Gu, Changhua Meng, Ke Wang, Jun Lan, Weiqiang Wang, Ming Gu, Liqing Zhang

Figure 1 for XYLayoutLM: Towards Layout-Aware Multimodal Networks For Visually-Rich Document Understanding
Figure 2 for XYLayoutLM: Towards Layout-Aware Multimodal Networks For Visually-Rich Document Understanding
Figure 3 for XYLayoutLM: Towards Layout-Aware Multimodal Networks For Visually-Rich Document Understanding
Figure 4 for XYLayoutLM: Towards Layout-Aware Multimodal Networks For Visually-Rich Document Understanding
Viaarxiv icon

CrowdTSC: Crowd-based Neural Networks for Text Sentiment Classification

Apr 26, 2020
Keyu Yang, Yunjun Gao, Lei Liang, Song Bian, Lu Chen, Baihua Zheng

Figure 1 for CrowdTSC: Crowd-based Neural Networks for Text Sentiment Classification
Figure 2 for CrowdTSC: Crowd-based Neural Networks for Text Sentiment Classification
Figure 3 for CrowdTSC: Crowd-based Neural Networks for Text Sentiment Classification
Figure 4 for CrowdTSC: Crowd-based Neural Networks for Text Sentiment Classification
Viaarxiv icon

Diagonal State Spaces are as Effective as Structured State Spaces

Mar 27, 2022
Ankit Gupta

Figure 1 for Diagonal State Spaces are as Effective as Structured State Spaces
Figure 2 for Diagonal State Spaces are as Effective as Structured State Spaces
Figure 3 for Diagonal State Spaces are as Effective as Structured State Spaces
Viaarxiv icon