Results 61 to 70 of about 2,502,977 (224)

Multiple layar kernel-based approach in relevance feedback content-based image retrieval system [PDF]

, 2005
Relevance feedback has drawn intense interest from many researchers in the field of content-based image retrieval (CBIR). In recent years, kernel-based approach has been a popular choice for the implementation of the relevance feedback based CBIR system.
Chun-Che Fung, Fung, C.C., Chung, K.P., Kien-Ping Chung   +3 more
core   +1 more source

A Generative Neuro‐Symbolic AI for Protein Sequence Design

Advanced Science, EarlyView.
We introduce EffieDes, a neuro‐symbolic framework coupling deep learning‐based fitness landscape parameterization with exact automated reasoning. Unlike greedy sampling, EffieDes identifies sequences that globally optimize fitness while satisfying intricate design constraints.
Marianne Defresne, Delphine Dessaux, Samuel Buchet, Lucie Barthe, Liza Ammar‐Khodja, Bessam Azizi, Valentin Durante, Gianluca Cioci, Simon de Givry, Alain Roussel, Luis F. Garcia‐Alles, Thomas Schiex, Sophie Barbe   +12 more
wiley   +1 more source

SPSB1 Promotes Subcutaneous Adipose Hyperplasia in Facial Port‐Wine Stains by Controlling HDAC1 Degradation and Stability Through Two Distinct Proteolytic Pathways

Advanced Science, EarlyView.
In PWS‐ASPCs, FOSL1 drives the expression of SPSB1. SPSB1, as part of the ESC complex, further binds to HDAC1 and promotes K29‐linked and K48‐linked polyubiquitination of HDAC1. These modifications facilitate the degradation of HDAC1 through the ALP and UPS pathways, respectively.
Hongrui Chen, Bin Sun, Yajing Qiu, Chen Hua, Xiaoxi Lin, Wei Gao   +5 more
wiley   +1 more source

Integrated Single‐Nucleus Multi‐Omics Atlases Reveal Lineage Plasticity and Regulatory Networks of Luminal Epithelial Cells During Mammary Gland Lactation and Involution

Advanced Science, EarlyView.
This study integrates single‐cell multi‐omics, spatial transcriptomics, and cross‐species comparative analyses to systematically characterize the cellular composition and differentiation trajectories of goat mammary epithelial cells, along with the gene regulatory networks and intercellular communication mechanisms governing these trajectories, thereby
Xiaoru Yan, Xiaoyu Mi, Guanghui Tan, Xinmei Li, Zhenliang Zhu, Zhenyu Wei, Huimei Fan, Yamei Wu, Tao Shi, Lingzhao Fang, Yuanpeng Gao, Yu Wang, Jun Liu   +12 more
wiley   +1 more source

Examining and improving the effectiveness of relevance feedback for retrieval of scanned text documents [PDF]

, 2006
Important legacy paper documents are digitized and collected in online accessible archives. This enables the preservation, sharing, and significantly the searching of these documents.
Lam-Adesina, Adenike M., Jones, Gareth J.F.   +1 more
core   +3 more sources

Green and Scalable Synthesis of Efficient and Stable CsPbBr3 Perovskite Quantum Dots Enables Low‐Threshold Amplified Spontaneous Emission

Advanced Science, EarlyView.
Green and scalable synthesis of CsPbBr3 perovskite quantum dots using bio‐sourced lecithin and hexane enables single‐batch production over 10 grams. Suppressed Auger recombination and electron‐phonon coupling yields 95% PLQY, enhanced stability, and low ASE thresholds of 230.4 (ns) and 50.1 (fs) µJ cm−2 in neat films. ABSTRACT Halide perovskite quantum
Yongfeng Liu, Mengting Zhang, Qingyu Xie, Kehao Hu, Bowen Zhang, Zhe Zhang, Jie Yang, Zhiping Hu, Juan Du, Jia Wang, Min Zhou   +10 more
wiley   +1 more source

Automated Skin Cancer Report Generation via a Knowledge-Distilled Vision-Language Model

IEEE Access
Artificial Intelligence (AI)’s capacity to analyze dermoscopic images promises a groundbreaking leap in skin cancer diagnostics, offering exceptional accuracy and an effortlessly non-invasive image acquisition process.
Lawhori Chakrabarti, Boyu Zhang, Hengyi Tian, Aleksandar Vakanski, Min Xian   +4 more
doaj   +1 more source

Computationally Evidence‐Grounded Sequence‐First Design of Peptide Binders

Advanced Science, EarlyView.
BOND‐PEP enables controllable, sequence‐first peptide binder design by grounding generation in binding evidence retrieved for each target. It uses topology‐conditioned message passing to integrate relevant peptide examples with the target protein sequence, forming a residue‐level representation that guides the generation of diverse, target‐specific ...
Wenze Ding
wiley   +1 more source

A Multi-Stage Hybrid Retrieval Framework for the Scientific Literature with Cross-Encoder Re-Ranking

Applied Sciences
Effective scientific literature retrieval requires moving beyond surface-level term matching toward structured semantic reasoning. This paper presents a controlled empirical study of multi-stage retrieval for scientific literature, integrating lexical ...
Walaa Al-Joofi, Alaa Sagheer, Hala Hamdoun   +2 more
doaj   +1 more source

Using string comparison in context for improved relevance feedback in different text media [PDF]

, 2006
Query expansion is a long standing relevance feedback technique for improving the effectiveness of information retrieval systems. Previous investigations have shown it to be generally effective for electronic text, to give proportionally better ...
Lam-Adesina, Adenike M., Adenike M. Lam-Adesina, Gareth J. F. Jones, Jones, Gareth J.F.   +3 more
core   +2 more sources