31 citations · 71 across the 14 of their papers we have counts for
15 papers
E2S-Pruner: Progressive Two-Stage Evidence Fusion for Visual Token Pruning in Vision-Language Models
Taoyu Qian, Qi Wang, Daqian Shi +3
Vision-language models typically encode an image into hundreds of visual tokens, incurring substantial inference latency and GPU memory overhead. Existing pruning methods largely r…
Logographic Character Visual Pretraining via Semantic-based Contrastive Learning
Daqian Shi, Wei Cao, Xiaoyu Zheng +3
Current deep learning-based character vision studies, e.g., text recognition, character image denoising, and historical text completion, are offering new solutions for learning, ma…
AncientBench: Towards Comprehensive Evaluation on Excavated and Transmitted Chinese Corpora
Zhihan Zhou, Daqian Shi, Rui Song +3
Comprehension of ancient texts plays an important role in archaeology and understanding of Chinese history and civilization. The rapid development of large language models needs be…
InteChar: A Unified Oracle Bone Character List for Ancient Chinese Language Modeling
Xiaolei Diao, Zhihan Zhou, Lida Shi +4
Constructing historical language models (LMs) plays a crucial role in aiding archaeological provenance studies and understanding ancient cultures. However, existing resources prese…
Competitive Distillation: A Simple Learning Strategy for Improving Visual Classification
Daqian Shi, Xiaolei Diao, Xu Chen +1
Deep Neural Networks (DNNs) have significantly advanced the field of computer vision. To improve DNN training process, knowledge distillation methods demonstrate their effectivenes…
Ancient Script Image Recognition and Processing: A Review
Xiaolei Diao, Rite Bo, Yanling Xiao +8
Ancient scripts, e.g., Egyptian hieroglyphs, Oracle Bone Inscriptions, and Ancient Greek inscriptions, serve as vital carriers of human civilization, embedding invaluable historica…
Towards a Gateway for Knowledge Graph Schemas Collection, Analysis, and Embedding
Mattia Fumagalli, Marco Boffo, Daqian Shi +2
One of the significant barriers to the training of statistical models on knowledge graphs is the difficulty that scientists have in finding the best input data to address their pre…
Toward Zero-shot Character Recognition: A Gold Standard Dataset with Radical-level Annotations
Xiaolei Diao, Daqian Shi, Jian Li +5
Optical character recognition (OCR) methods have been applied to diverse tasks, e.g., street view text recognition and document analysis. Recently, zero-shot OCR has piqued the int…
Recognizing Entity Types via Properties
Daqian Shi, Fausto Giunchiglia
The mainstream approach to the development of ontologies is merging ontologies encoding different information, where one of the major difficulties is that the heterogeneity motivat…
Towards Ranking Schemas by Focus
Mattia Fumagalli, Daqian Shi, Fausto Giunchiglia
The main goal of this paper is to evaluate knowledge base schemas, modeled as a set of entity types, each such type being associated with a set of properties, according to their fo…
CharFormer: A Glyph Fusion based Attentive Framework for High-precision Character Image Denoising
Daqian Shi, Xiaolei Diao, Lida Shi +4
Degraded images commonly exist in the general sources of character images, leading to unsatisfactory character recognition results. Existing methods have dedicated efforts to resto…
RCRN: Real-world Character Image Restoration Network via Skeleton Extraction
Daqian Shi, Xiaolei Diao, Hao Tang +3
Constructing high-quality character image datasets is challenging because real-world images are often affected by image degradation. There are limitations when applying current ima…
LiveSchema: A Gateway Towards Learning on Knowledge Graph Schemas
Mattia Fumagalli, Marco Boffo, Daqian Shi +2
One of the major barriers to the training of algorithms on knowledge graph schemas, such as vocabularies or ontologies, is the difficulty that scientists have in finding the best i…
RZCR: Zero-shot Character Recognition via Radical-based Reasoning
Xiaolei Diao, Daqian Shi, Hao Tang +4
The long-tail effect is a common issue that limits the performance of deep learning models on real-world datasets. Character image datasets are also affected by such unbalanced dat…
Property-based Entity Type Graph Matching
Fausto Giunchiglia, Daqian Shi
We are interested in dealing with the heterogeneity of Knowledge bases (KBs), e.g., ontologies and schemas, modeled as sets of entity types (etypes), e.g., person, where each etype…