Visual Entity Linking (VEL) is a crucial task for achieving fine-grained visual understanding, matching objects within images (visual mentions) to entities in a knowledge base. Previous VEL tasks rely on textual inputs, but writing queries for complex scenes can be challenging. Visual inputs like clicks or bounding boxes offer a more convenient alternative. Therefore, we propose a new task, Pixel-Level Visual Entity Linking (PL-VEL), which uses pixel masks from visual inputs to refer to objects, supplementing reference methods for VEL. To facilitate research on this task, we have constructed the MaskOVEN-Wiki dataset through an entirely automatic reverse region-entity annotation framework. This dataset contains over 5 million annotations aligning pixel-level regions with entity-level labels, which will advance visual understanding towards fine-grained. Moreover, as pixel masks correspond to semantic regions in an image, we enhance previous patch-interacted attention with region-interacted attention by a visual semantic tokenization approach. Manual evaluation results indicate that the reverse annotation framework achieved a 94.8% annotation success rate. Experimental results show that models trained on this dataset improved accuracy by 18 points compared to zero-shot models. Additionally, the semantic tokenization method achieved a 5-point accuracy improvement over the trained baseline.

The maintainability of open-source supply chain software is crucial for ensuring the security and efficiency of software systems. This research will focus on this area by identifying, quantifying, and validating specific maintainability indicators. Through a structured literature review, empirical surveys, and comparative analyses of projects like webpack and babel, the study develops a comprehensive set of metrics, including team health, project activity, and others. These metrics are quantified and validated, as demonstrated in a case study on AngularJs. The outcomes provide a novel framework for evaluating maintainability in open-source software, offering essential insights for sustainable development and maintenance within the complex environment of software supply chains.