VisFocus: Prompt-Guided Vision Encoders for OCR-Free Dense Document Understanding.
Proceedings of the Computer Vision - ECCV 2024, 2024
GRAM: Global Reasoning for Multi-Page VQA.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
TextAdaIN: Paying Attention to Shortcut Learning in Text Recognizers.
Proceedings of the Computer Vision - ECCV 2022, 2022
Towards Weakly-Supervised Text Spotting using a Multi-Task Transformer.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022
TextAdaIN: Fine-Grained AdaIN for Robust Text Recognition.
CoRR, 2021
Single Pair Cross-Modality Super Resolution.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021
Weakly Aligned Joint Cross-Modality Super Resolution.
CoRR, 2020
ScrabbleGAN: Semi-Supervised Varying Length Handwritten Text Generation.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020
PointWise: An Unsupervised Point-wise Feature Learning Network.
CoRR, 2019
Clustering-Driven Deep Embedding With Pairwise Constraints.
IEEE Computer Graphics and Applications, 2019
Blind Visual Motif Removal From a Single Image.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019