لطفا منتظر بمانید ...
0% Complete
English
صفحه اصلی
/
شانزدهمین کنفرانس بین المللی فناوری اطلاعات و دانش
Prompt-Based Composed Fashion Image Retrieval via Gated Detail-Enhanced Dual Cross-Attention Difference Modeling
نویسندگان :
Kosar Keshavarz
1
Reza Azmi
2
1- دانشگاه الزهرا(س)
2- دانشگاه الزهرا(س)
کلمات کلیدی :
Composed image retrieval،Composed query،Contrastive learning،Fashion retrieval،Multimodal retrieval،Text-guided image retrieval
چکیده :
With the rapid growth of online shopping and the vast amount of fashion-related visual content on the internet, accurate methods for fashion image retrieval have become increasingly important to enhance user satisfaction. The fashion domain is inherently fine-grained, characterized by subtle details such as color, pattern, cut, and embellishments, where even small variations lead to distinct styles. To address the limitations of purely text-based or image-based queries, we adopt a text-guided retrieval approach in which a reference image and a natural-language description jointly define the user’s intent. This paper extends sentence-level prompt-based retrieval frameworks by introducing explicit image-difference modeling. The proposed Gated Detail-Enhanced Dual Cross-Attention (GDD-CA) module models the relationship between reference and target images through dual cross-attention and a gated detail-enhancement mechanism, enabling the network to capture subtle, fine-grained visual variations. Experimental results on the Fashion-IQ dataset demonstrate that integrating detail-enhanced image-difference modeling into the prompt-based structure improves retrieval performance, achieving a 1.14% gain in Recall over previous methods.
لیست مقالات
لیست مقالات بایگانی شده
آرتمیا: پروتکل مسیریابی مبتنی بر انجمن و آگاه به نظم تماس در شبکة اجتماعی متحرک تأخیرپذیر
سعید مرادی - جمشید باقرزاده محاسفی
An Attention-Enhanced Hybrid Deep Learning Framework for Detecting Denial-of-Wallet Attacks in Serverless Platforms
Mohammad Mehmandoost - HadiShahriar Shahhoseini
تحلیل کتابسنجی از مقالات حوزه دوقلوهای دیجیتال
فاطمه مکی زاده - سارا صراف - مصطفی شیرالی
کنترل کیفیت غیرمتمرکز مبتنی بر هوش ترکیبی در سیستمهای مشارکتی برخط
مهدیه طالب زاده - هاله امین طوسی - محمد اله بخش
Spatial On–Off Keying Modulation with Mirror-Array Optical IRSs for Indoor Machine-to-Machine Visible Light Communication
Babak Sadeghi - Seyed Mohammad Sajad Sadough
A Foresight Approach to Cyber Threats Identification and Scenario Planning
MAHDI OMRANI - Masoud Shafiee - Siavash Khorsandi
A Multi-Task Framework Using Mamba for Identity, Age, and Gender Classification from Hand Images
Amirabbas Rezasoltani - Alireza Hosseini - Ramin Toosi - MohammadAli Akhaee
Non-Linear Control of Cancer Model, Considering the Drug Resistance Using Feedback Based Chemotherapy Approach
Danial Kiaei - Hami Tourajizadeh
OENMOP: Loss-Aware 4×4 and 5×5 and Scalable Non‑blocking Optical Switches Designed for Odd-Even Routing Algorithm for Chip-Scale Interconnection Networks
Negin Bagheri Renani - Elham Yaghoubi - Mina Mohammadirad
تشخیص بیماری شبکوری با استفاده از ترکیب الگوریتمهای یادگیری عمیق
میثم فتاحی
بیشتر
ثمین همایش، سامانه مدیریت همایش ها و جشنواره ها - نگارش 45.0.1