Biguanides
发表于 2025-3-28 18:26:26
Recurrent Few-Shot Model for Document Verificationved problem. There are several factors that negatively impact their performance, including low-resolution images and videos and a lack of sufficient data to train the models. This task is particularly challenging when dealing with unseen class of ID, or travel, documents. In this paper we address th
Valves
发表于 2025-3-28 21:21:15
Document Specular Highlight Removal with Coarse-to-Fine Strategyrecursor to guide the model in achieving better removal of specular highlights. This paper introduces a novel highlight removal model, which presents an efficient end-to-end deep learning framework designed to automatically remove specular highlights from a single image. Our architecture comprises t
植物茂盛
发表于 2025-3-29 01:19:16
http://reply.papertrans.cn/29/2849/284812/284812_43.png
constellation
发表于 2025-3-29 06:44:14
KVP10k : A Comprehensive Dataset for Key-Value Pair Extraction in Business Documentsdomains. This effort has attracted substantial interest from both industry and academy, highlighting its significance in the current technological landscape. Most datasets in this area are primarily focused on Key Information Extraction (KIE), where the extraction process revolves around extracting
Communicate
发表于 2025-3-29 08:07:12
http://reply.papertrans.cn/29/2849/284812/284812_45.png
CURL
发表于 2025-3-29 14:17:51
http://reply.papertrans.cn/29/2849/284812/284812_46.png
BILIO
发表于 2025-3-29 17:01:19
Radical Similarity Based Model Optimization and Post-correction for Chinese Character Recognitionsed methods, Chinese characters are described as combinations of structures and radicals, and character recognition is achieved by the proper identifications of these components. However, there are visual similarities among radicals, leading to the ambiguity problem for CCR, which is not fully utili
小隔间
发表于 2025-3-29 20:51:53
Puzzle Pieces Picker: Deciphering Ancient Chinese Characters with Radical Reconstructionf Oracle Bone Inscriptions (OBI) remain undeciphered, making it one of the global challenges in the field of paleography today. This paper introduces a novel approach, namely Puzzle Pieces Picker (P.), to decipher these enigmatic characters through radical reconstruction. We deconstruct OBI into fou
TRAWL
发表于 2025-3-30 00:36:57
Light-Weight Multi-modality Feature Fusion Network for Visually-Rich Document Understandingmage. Recent transformer-based architectures enable an effective fusion of these features, showing great performance on the EE task. However, these models are heavy, leading to substantially high training cost and low inference speed. Thus, we propose a light-weight transformer-based model (named LM
Insensate
发表于 2025-3-30 07:57:44
http://reply.papertrans.cn/29/2849/284812/284812_50.png