PulseAugur / Brief
EN
LIVE 12:36:30

Brief

last 24h
[2/2] 224 sources

Multi-source AI news clustered, deduplicated, and scored 0–100 across authority, cluster strength, headline signal, and time decay.

  1. TOOL · arXiv cs.CV English(EN) ·

    XPASS-Vis: A Dataset for Cross-Domain Personalized Image Aesthetic Assessment

    Researchers have introduced XPASS-Vis, a novel dataset designed to explore personalized image aesthetic assessment across different visual domains. The dataset includes over 6,500 images from art, fashion, and landscape categories, rated by 129 annotators. Initial experiments using unsupervised domain adaptation show that personalized aesthetic preferences can be transferred across domains with moderate success, though a significant gap remains for PIAA-specific adaptation strategies. AI

  2. RESEARCH · arXiv cs.IR (Information Retrieval) English(EN) · · [5 sources]

    RAPT: Retrieval-Augmented Post-hoc Thresholding for Multi-Label Classification

    Researchers have developed new methods to improve multi-label classification tasks, which involve predicting multiple labels for a single instance. One approach, RAPT, acts as a model-agnostic wrapper that adapts label selection thresholds by retrieving similar past cases, outperforming static thresholding and few-shot LLMs. Another framework, PIAA, enhances patch-level inference and uses adaptive aggregation for multi-label image recognition, achieving significant gains without retraining. Additionally, a theoretical framework for optimizing generalized metrics in multi-label learning has been proposed, offering principled algorithms with provable guarantees and demonstrating scalability on large datasets. AI

    IMPACT These advancements offer more robust and efficient solutions for complex classification problems, potentially improving performance in areas like document understanding and image recognition.