Picture for Zhongqin Wu

Zhongqin Wu

Triplet Knowledge Distillation

May 25, 2023
Figure 1 for Triplet Knowledge Distillation
Figure 2 for Triplet Knowledge Distillation
Figure 3 for Triplet Knowledge Distillation
Figure 4 for Triplet Knowledge Distillation
Viaarxiv icon

FusionFormer: Fusing Operations in Transformer for Efficient Streaming Speech Recognition

Add code
Oct 31, 2022
Figure 1 for FusionFormer: Fusing Operations in Transformer for Efficient Streaming Speech Recognition
Figure 2 for FusionFormer: Fusing Operations in Transformer for Efficient Streaming Speech Recognition
Figure 3 for FusionFormer: Fusing Operations in Transformer for Efficient Streaming Speech Recognition
Figure 4 for FusionFormer: Fusing Operations in Transformer for Efficient Streaming Speech Recognition
Viaarxiv icon

Retrieval-based Spatially Adaptive Normalization for Semantic Image Synthesis

Add code
Apr 06, 2022
Figure 1 for Retrieval-based Spatially Adaptive Normalization for Semantic Image Synthesis
Figure 2 for Retrieval-based Spatially Adaptive Normalization for Semantic Image Synthesis
Figure 3 for Retrieval-based Spatially Adaptive Normalization for Semantic Image Synthesis
Figure 4 for Retrieval-based Spatially Adaptive Normalization for Semantic Image Synthesis
Viaarxiv icon

A Character-level Span-based Model for Mandarin Prosodic Structure Prediction

Add code
Mar 31, 2022
Figure 1 for A Character-level Span-based Model for Mandarin Prosodic Structure Prediction
Figure 2 for A Character-level Span-based Model for Mandarin Prosodic Structure Prediction
Figure 3 for A Character-level Span-based Model for Mandarin Prosodic Structure Prediction
Figure 4 for A Character-level Span-based Model for Mandarin Prosodic Structure Prediction
Viaarxiv icon

Syntax-Aware Network for Handwritten Mathematical Expression Recognition

Add code
Mar 28, 2022
Figure 1 for Syntax-Aware Network for Handwritten Mathematical Expression Recognition
Figure 2 for Syntax-Aware Network for Handwritten Mathematical Expression Recognition
Figure 3 for Syntax-Aware Network for Handwritten Mathematical Expression Recognition
Figure 4 for Syntax-Aware Network for Handwritten Mathematical Expression Recognition
Viaarxiv icon

BERT-LID: Leveraging BERT to Improve Spoken Language Identification

Add code
Mar 01, 2022
Figure 1 for BERT-LID: Leveraging BERT to Improve Spoken Language Identification
Figure 2 for BERT-LID: Leveraging BERT to Improve Spoken Language Identification
Figure 3 for BERT-LID: Leveraging BERT to Improve Spoken Language Identification
Figure 4 for BERT-LID: Leveraging BERT to Improve Spoken Language Identification
Viaarxiv icon

Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation

Add code
Aug 17, 2021
Figure 1 for Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation
Figure 2 for Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation
Figure 3 for Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation
Figure 4 for Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation
Viaarxiv icon

UniCon: Unified Context Network for Robust Active Speaker Detection

Add code
Aug 05, 2021
Figure 1 for UniCon: Unified Context Network for Robust Active Speaker Detection
Figure 2 for UniCon: Unified Context Network for Robust Active Speaker Detection
Figure 3 for UniCon: Unified Context Network for Robust Active Speaker Detection
Figure 4 for UniCon: Unified Context Network for Robust Active Speaker Detection
Viaarxiv icon

Structured Multi-modal Feature Embedding and Alignment for Image-Sentence Retrieval

Aug 05, 2021
Figure 1 for Structured Multi-modal Feature Embedding and Alignment for Image-Sentence Retrieval
Figure 2 for Structured Multi-modal Feature Embedding and Alignment for Image-Sentence Retrieval
Figure 3 for Structured Multi-modal Feature Embedding and Alignment for Image-Sentence Retrieval
Figure 4 for Structured Multi-modal Feature Embedding and Alignment for Image-Sentence Retrieval
Viaarxiv icon

Locality-aware Channel-wise Dropout for Occluded Face Recognition

Jul 20, 2021
Figure 1 for Locality-aware Channel-wise Dropout for Occluded Face Recognition
Figure 2 for Locality-aware Channel-wise Dropout for Occluded Face Recognition
Figure 3 for Locality-aware Channel-wise Dropout for Occluded Face Recognition
Figure 4 for Locality-aware Channel-wise Dropout for Occluded Face Recognition
Viaarxiv icon