Less Is More: Similarity Models for Content-Based Video Retrieval

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3A10468869" target="_blank" >RIV/00216208:11320/23:10468869 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1007/978-3-031-27818-1_5" target="_blank" >https://doi.org/10.1007/978-3-031-27818-1_5</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-27818-1_5" target="_blank" >10.1007/978-3-031-27818-1_5</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Less Is More: Similarity Models for Content-Based Video Retrieval

Popis výsledku v původním jazyce

The concept of object-to-object similarity plays a crucial role in interactive content-based video retrieval tools. Similarity (or distance) models are core components of several retrieval concepts, e.g. Query by Example or relevance feedback. In these scenarios, the common approach is to apply some feature extractor that transforms the object to a vector of features, i.e., positions it into an induced latent space. The similarity is then based on some distance metric in this space. Historically, feature extractors were mostly based on some color histograms or hand-crafted descriptors such as SIFT, but nowadays state-of-the-art tools mostly rely on some deep learning (DL) approaches. However, so far there were no systematic study of how suitable are individual feature extractors in the video retrieval domain. Or, in other words, to what extent are human-perceived and model-based similarities concordant. To fill this gap, we conducted a user study with over 4000 similarity judgements comparing over 20 variants of feature extractors. Results corroborate the dominance of deep learning approaches, but surprisingly favor smaller and simpler DL models instead of larger ones.

Název v anglickém jazyce

Less Is More: Similarity Models for Content-Based Video Retrieval

Popis výsledku anglicky

The concept of object-to-object similarity plays a crucial role in interactive content-based video retrieval tools. Similarity (or distance) models are core components of several retrieval concepts, e.g. Query by Example or relevance feedback. In these scenarios, the common approach is to apply some feature extractor that transforms the object to a vector of features, i.e., positions it into an induced latent space. The similarity is then based on some distance metric in this space. Historically, feature extractors were mostly based on some color histograms or hand-crafted descriptors such as SIFT, but nowadays state-of-the-art tools mostly rely on some deep learning (DL) approaches. However, so far there were no systematic study of how suitable are individual feature extractors in the video retrieval domain. Or, in other words, to what extent are human-perceived and model-based similarities concordant. To fill this gap, we conducted a user study with over 4000 similarity judgements comparing over 20 variants of feature extractors. Results corroborate the dominance of deep learning approaches, but surprisingly favor smaller and simpler DL models instead of larger ones.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GA22-21696S" target="_blank" >GA22-21696S: Hluboké vizuální reprezentace nestrukturovaných dat</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

MULTIMEDIA MODELING, MMM 2023, PT II

ISBN

978-3-031-27817-4

ISSN

0302-9743

e-ISSN

1611-3349

Počet stran výsledku

12

Strana od-do

54-65

Název nakladatele

SPRINGER INTERNATIONAL PUBLISHING AG

Místo vydání

CHAM

Místo konání akce

Bergen

Datum konání akce

9. 1. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000996578000005