Alert button

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

The Impact of User Demographics and Task Types on Cross-App Mobile Search

Sep 14, 2021
Mohammad Aliannejadi, Fabio Crestani, Theo Huibers, Monica Landoni, Emiliana Murgia, Maria Soledad Pera

Figure 1 for The Impact of User Demographics and Task Types on Cross-App Mobile Search
Figure 2 for The Impact of User Demographics and Task Types on Cross-App Mobile Search
Figure 3 for The Impact of User Demographics and Task Types on Cross-App Mobile Search
Figure 4 for The Impact of User Demographics and Task Types on Cross-App Mobile Search
Viaarxiv icon

Acoustic-to-Word Models with Conversational Context Information

May 21, 2019
Suyoun Kim, Florian Metze

Figure 1 for Acoustic-to-Word Models with Conversational Context Information
Figure 2 for Acoustic-to-Word Models with Conversational Context Information
Figure 3 for Acoustic-to-Word Models with Conversational Context Information
Figure 4 for Acoustic-to-Word Models with Conversational Context Information
Viaarxiv icon

Melody Harmonization with Controllable Harmonic Rhythm

Dec 21, 2021
Shangda Wu, Yue Yang, Zhaowen Wang, Xiaobing Li, Maosong Sun

Figure 1 for Melody Harmonization with Controllable Harmonic Rhythm
Figure 2 for Melody Harmonization with Controllable Harmonic Rhythm
Figure 3 for Melody Harmonization with Controllable Harmonic Rhythm
Figure 4 for Melody Harmonization with Controllable Harmonic Rhythm
Viaarxiv icon

RGB-D Image Inpainting Using Generative Adversarial Network with a Late Fusion Approach

Oct 14, 2021
Ryo Fujii, Ryo Hachiuma, Hideo Saito

Figure 1 for RGB-D Image Inpainting Using Generative Adversarial Network with a Late Fusion Approach
Figure 2 for RGB-D Image Inpainting Using Generative Adversarial Network with a Late Fusion Approach
Figure 3 for RGB-D Image Inpainting Using Generative Adversarial Network with a Late Fusion Approach
Figure 4 for RGB-D Image Inpainting Using Generative Adversarial Network with a Late Fusion Approach
Viaarxiv icon

Learning Robust and Lightweight Model through Separable Structured Transformations

Dec 29, 2021
Xian Wei, Yanhui Huang, Yangyu Xu, Mingsong Chen, Hai Lan, Yuanxiang Li, Zhongfeng Wang, Xuan Tang

Figure 1 for Learning Robust and Lightweight Model through Separable Structured Transformations
Figure 2 for Learning Robust and Lightweight Model through Separable Structured Transformations
Figure 3 for Learning Robust and Lightweight Model through Separable Structured Transformations
Figure 4 for Learning Robust and Lightweight Model through Separable Structured Transformations
Viaarxiv icon

Extracting Attentive Social Temporal Excitation for Sequential Recommendation

Sep 28, 2021
Yunzhe Li, Yue Ding, Bo Chen, Xin Xin, Yule Wang, Yuxiang Shi, Ruiming Tang, Dong Wang

Figure 1 for Extracting Attentive Social Temporal Excitation for Sequential Recommendation
Figure 2 for Extracting Attentive Social Temporal Excitation for Sequential Recommendation
Figure 3 for Extracting Attentive Social Temporal Excitation for Sequential Recommendation
Figure 4 for Extracting Attentive Social Temporal Excitation for Sequential Recommendation
Viaarxiv icon

Learning Speaker Representation with Semi-supervised Learning approach for Speaker Profiling

Oct 24, 2021
Shangeth Rajaa, Pham Van Tung, Chng Eng Siong

Figure 1 for Learning Speaker Representation with Semi-supervised Learning approach for Speaker Profiling
Figure 2 for Learning Speaker Representation with Semi-supervised Learning approach for Speaker Profiling
Figure 3 for Learning Speaker Representation with Semi-supervised Learning approach for Speaker Profiling
Figure 4 for Learning Speaker Representation with Semi-supervised Learning approach for Speaker Profiling
Viaarxiv icon

ADD: Frequency Attention and Multi-View based Knowledge Distillation to Detect Low-Quality Compressed Deepfake Images

Dec 07, 2021
Binh M. Le, Simon S. Woo

Figure 1 for ADD: Frequency Attention and Multi-View based Knowledge Distillation to Detect Low-Quality Compressed Deepfake Images
Figure 2 for ADD: Frequency Attention and Multi-View based Knowledge Distillation to Detect Low-Quality Compressed Deepfake Images
Figure 3 for ADD: Frequency Attention and Multi-View based Knowledge Distillation to Detect Low-Quality Compressed Deepfake Images
Figure 4 for ADD: Frequency Attention and Multi-View based Knowledge Distillation to Detect Low-Quality Compressed Deepfake Images
Viaarxiv icon

Using Sentiment Information for Preemptive Detection of Toxic Comments in Online Conversations

Jun 17, 2020
Éloi Brassard-Gourdeau, Richard Khoury

Figure 1 for Using Sentiment Information for Preemptive Detection of Toxic Comments in Online Conversations
Figure 2 for Using Sentiment Information for Preemptive Detection of Toxic Comments in Online Conversations
Figure 3 for Using Sentiment Information for Preemptive Detection of Toxic Comments in Online Conversations
Figure 4 for Using Sentiment Information for Preemptive Detection of Toxic Comments in Online Conversations
Viaarxiv icon

Unsupervised Learning of Compositional Scene Representations from Multiple Unspecified Viewpoints

Dec 12, 2021
Jinyang Yuan, Bin Li, Xiangyang Xue

Figure 1 for Unsupervised Learning of Compositional Scene Representations from Multiple Unspecified Viewpoints
Figure 2 for Unsupervised Learning of Compositional Scene Representations from Multiple Unspecified Viewpoints
Figure 3 for Unsupervised Learning of Compositional Scene Representations from Multiple Unspecified Viewpoints
Figure 4 for Unsupervised Learning of Compositional Scene Representations from Multiple Unspecified Viewpoints
Viaarxiv icon