PubMed-OCR is an OCR-centric corpus of scientific articles derived from PubMed Central Open Access PDFs. Each page image is annotated with Google Cloud Vision and released in a compact JSON schema with word-, line-, and paragraph-level bounding boxes. The corpus spans 209.5K articles (1.5M pages; ~1.3B words) and supports layout-aware modeling, coordinate-grounded QA, and evaluation of OCR-dependent pipelines. We analyze corpus characteristics (e.g., journal coverage and detected layout features) and discuss limitations, including reliance on a single OCR engine and heuristic line reconstruction. We release the data and schema to facilitate downstream research and invite extensions.
Tal Reiss, Daniel Winter +5
We introduce Alterbute, a diffusion-based method for editing an object's intrinsic attributes in an image. We allow changing color, texture, material, and even the shape of an object, while preserving...
Yang-Che Sun, Cheng Sun +5
Video object segmentation methods like SAM2 achieve strong performance through memory-based architectures but struggle under large viewpoint changes due to reliance on appearance features. Traditional...
Delong Chen, Tejaswi Kasarla +7
Inferring physical actions from visual observations is a fundamental capability for advancing machine intelligence in the physical world. Achieving this requires large-scale, open-vocabulary video act...
Chongcong Jiang, Tianxingjian Ding +8
Promptable segmentation foundation models such as SAM3 have demonstrated strong generalization capabilities through interactive and concept-based prompting. However, their direct applicability to medi...
Sangbeom Lim, Seoung Wug Oh +4
Generalizing video matting models to real-world videos remains a significant challenge due to the scarcity of labeled data. To address this, we present Video Mask-to-Matte Model (VideoMaMa) that conve...
