Picture for Maoyuan Ye

Maoyuan Ye

Adapting Segment Anything Model for Power Transmission Corridor Hazard Segmentation

Add code
May 28, 2025
Viaarxiv icon

GoMatching++: Parameter- and Data-Efficient Arbitrary-Shaped Video Text Spotting and Benchmarking

Add code
May 28, 2025
Viaarxiv icon

Reasoning-OCR: Can Large Multimodal Models Solve Complex Logical Reasoning Problems from OCR Cues?

Add code
May 19, 2025
Viaarxiv icon

LogicOCR: Do Your Large Multimodal Models Excel at Logical Reasoning on Text-Rich Images?

Add code
May 18, 2025
Viaarxiv icon

Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation

Add code
Jan 31, 2024
Figure 1 for Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation
Figure 2 for Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation
Figure 3 for Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation
Figure 4 for Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation
Viaarxiv icon

GoMatching: A Simple Baseline for Video Text Spotting via Long and Short Term Matching

Add code
Jan 13, 2024
Viaarxiv icon

DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Text Spotting

Add code
May 31, 2023
Viaarxiv icon

DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting

Add code
Nov 23, 2022
Figure 1 for DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting
Figure 2 for DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting
Figure 3 for DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting
Figure 4 for DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting
Viaarxiv icon

DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer

Add code
Jul 10, 2022
Figure 1 for DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer
Figure 2 for DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer
Figure 3 for DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer
Figure 4 for DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer
Viaarxiv icon