Changxu Cheng

4 papers · 2023–2025 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (10)

Venues

ICCV (2) CVPR (1) EMNLP (1)

Top co-authors

Cong Yao (3) Qi Zheng (3) Zirui Shao (1) Zhi Yu (1) Hangdi Xing (1) Chuwei Luo (1) Jiajun Bu (1) Senda Chen (1) Wuyue Zhao (1) Peng Wang (1)

Research topics

Artificial Intelligence (4) Core AI (4) Computer Vision (3) Deep Learning (2) Machine Learning (2) Analysis (2) Techniques (2) Natural Language Processing (1) Application Areas (1) Applications (1) Architectures (1) Core Methods (1) Domain-Specific (1)

Keywords

semantic segmentation (1) image segmentation (1) relation extraction (1) multimodal learning (1) document understanding (1) hierarchical structure (1) large multimodal model (1) length extrapolation (1) feature enhancement (1) mask token (1) scene text recognition (1) layout analysis (1) multimodal framework (1) hierarchical tokenization (1) geometric pre-training (1) visual information extraction (1) semantic entity recognition (1) document intelligence (1) character attention (1) document hierarchy parsing (1)

Papers

HiMTok: Learning Hierarchical Mask Tokens for Image Segmentation with Large Multimodal Model ICCV 2025 DocHieNet: A Large and Diverse Dataset for Document Hierarchy Parsing EMNLP 2024 GeoLayoutLM: Geometric Pre-Training for Visual Information Extraction CVPR 2023 LISTER: Neighbor Decoding for Length-Insensitive Scene Text Recognition ICCV 2023