Picture for Boqiang Zhang

Boqiang Zhang

Self-Supervised Pre-training with Symmetric Superimposition Modeling for Scene Text Recognition

Add code
May 11, 2024
Viaarxiv icon

Choose What You Need: Disentangled Representation Learning for Scene Text Recognition, Removal and Editing

Add code
May 07, 2024
Figure 1 for Choose What You Need: Disentangled Representation Learning for Scene Text Recognition, Removal and Editing
Figure 2 for Choose What You Need: Disentangled Representation Learning for Scene Text Recognition, Removal and Editing
Figure 3 for Choose What You Need: Disentangled Representation Learning for Scene Text Recognition, Removal and Editing
Figure 4 for Choose What You Need: Disentangled Representation Learning for Scene Text Recognition, Removal and Editing
Viaarxiv icon

Symmetrical Linguistic Feature Distillation with CLIP for Scene Text Recognition

Add code
Oct 10, 2023
Figure 1 for Symmetrical Linguistic Feature Distillation with CLIP for Scene Text Recognition
Figure 2 for Symmetrical Linguistic Feature Distillation with CLIP for Scene Text Recognition
Figure 3 for Symmetrical Linguistic Feature Distillation with CLIP for Scene Text Recognition
Figure 4 for Symmetrical Linguistic Feature Distillation with CLIP for Scene Text Recognition
Viaarxiv icon

Linguistic More: Taking a Further Step toward Efficient and Accurate Scene Text Recognition

Add code
May 10, 2023
Figure 1 for Linguistic More: Taking a Further Step toward Efficient and Accurate Scene Text Recognition
Figure 2 for Linguistic More: Taking a Further Step toward Efficient and Accurate Scene Text Recognition
Figure 3 for Linguistic More: Taking a Further Step toward Efficient and Accurate Scene Text Recognition
Figure 4 for Linguistic More: Taking a Further Step toward Efficient and Accurate Scene Text Recognition
Viaarxiv icon