Results 311 to 320 of about 1,724,603 (377)

DocLLM: A layout-aware generative language model for multimodal document understanding

Annual Meeting of the Association for Computational Linguistics, 2023
Enterprise documents such as forms, invoices, receipts, reports, contracts, and other similar records, often carry rich semantics at the intersection of textual and spatial modalities.
Dongsheng Wang   +8 more
semanticscholar   +1 more source

DocLayNet: A Large Human-Annotated Dataset for Document-Layout Segmentation

Knowledge Discovery and Data Mining, 2022
Accurate document layout analysis is a key requirement for high-quality PDF document conversion. With the recent availability of public, large ground-truth datasets such as PubLayNet and DocBank, deep-learning models have proven to be very effective at ...
B. Pfitzmann   +4 more
semanticscholar   +1 more source

Ctrl-Room: Controllable Text-to-3D Room Meshes Generation with Layout Constraints

International Conference on 3D Vision, 2023
Text-driven 3D indoor scene generation is useful for gaming, film industry, and AR/VR applications. However, existing methods cannot faithfully capture the scene layout based on text descriptions, nor do they allow flexible editing of individual objects ...
Chuan Fang   +3 more
semanticscholar   +1 more source

Home - About - Disclaimer - Privacy