Analysis of the Complementarity of Latent and Concept Spaces for Cross-Modal Video Search - Université Grenoble Alpes Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Analysis of the Complementarity of Latent and Concept Spaces for Cross-Modal Video Search

Résumé

This paper focuses on studying the complementarity between the spaces from hybrid crossmodal state-of-the-art systems for video retrieval like [5]. We aim at investigating if these spaces really convey different features, or if they are representing the same things. We use PCA (Principal Component Analysis) to study the optimal dimensions, CCA (Canonical Correlation Analysis) to assess the similarity of the spaces, and check if such approach is in fact similar to ensemble learning. We achieve experiments on the MST-VTT corpus, and show that in fact these two spaces are indeed very similar, paving the way for new models that could enforce more dissimilar spaces.
Fichier principal
Vignette du fichier
Paper_CBMI_Hal_Version.pdf (256.47 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03813421 , version 1 (13-10-2022)

Identifiants

Citer

Varsha Devi, Philippe Mulhem, Georges Quénot. Analysis of the Complementarity of Latent and Concept Spaces for Cross-Modal Video Search. CBMI 2022: International Conference on Content-based Multimedia Indexing, Sep 2022, Graz, Austria. pp.84-90, ⟨10.1145/3549555.3549600⟩. ⟨hal-03813421⟩
39 Consultations
87 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More