Experimental Evaluation of Static Image Sub-Region-Based Search Models Using CLIP
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3A10504478" target="_blank" >RIV/00216208:11320/25:10504478 - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.1007/978-3-032-06069-3_12" target="_blank" >http://dx.doi.org/10.1007/978-3-032-06069-3_12</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-032-06069-3_12" target="_blank" >10.1007/978-3-032-06069-3_12</a>
Alternative languages
Result language
angličtina
Original language name
Experimental Evaluation of Static Image Sub-Region-Based Search Models Using CLIP
Original language description
Advances in multimodal text-image models have enabled effective text-based querying in extensive image collections. While these models show convincing performance for everyday life scenes, querying in highly homogeneous, specialized domains remains challenging. The primary problem is that users can often provide only vague textual descriptions as they lack expert knowledge to discriminate between homogenous entities. This work investigates whether adding location-based prompts to complement these vague text queries can enhance retrieval performance. Specifically, we collected a dataset of 741 human annotations, each containing short and long textual descriptions and bounding boxes indicating regions of interest in challenging underwater scenes. Using these annotations, we evaluate the performance of CLIP when queried on various static sub-regions of images compared to the full image. Our results show that both a simple 3-by-3 partitioning and a 5-grid overlap significantly improve retrieval effectiveness and remain robust to perturbations of the annotation box.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
<a href="/en/project/GA25-16785S" target="_blank" >GA25-16785S: Empowering Multi-Objective Recommender Systems with Large Language Models</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2025
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
18th International Conference, SISAP 2025
ISBN
978-3-032-06069-3
ISSN
—
e-ISSN
—
Number of pages
14
Pages from-to
140-153
Publisher name
Springer Nature Switzerland AG
Place of publication
Cham
Event location
Reykjavik, Iceland
Event date
Oct 1, 2025
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—