3 papers
cs.CV2026
B-MIM: Biased Masked Image Modeling for Generalizable Segmentation of Fine-Grained Anatomical Structures
Sebastián González, Karen Sanchez, José M. Saavedra +2
Self-supervised pretraining enables transferable representations for medical imaging, yet most CT encoders remain biased toward coarse semantic understanding, limiting their sensit…
cs.CV2026
iDocV2: Leveraging Self-Supervision and Open-Set Detection for Improving Pattern Spotting in Historical Documents
Jose M. Saavedra, Crhistopher Stears, Marcelo Pizarro +2
Considering the imminent massification of digital books, it has become critical to facilitate searching collections through graphical patterns. Current strategies for document retr…
cs.CV2026
A Benchmarking Methodology to Assess Open-Source Video Large Language Models in Automatic Captioning of News Videos
David Miranda Paredes, Jose M. Saavedra, Marcelo Pizarro
News videos are among the most prevalent content types produced by television stations and online streaming platforms, yet generating textual descriptions to facilitate indexing an…