Improving Causality in Interpretable Video Retrieval - Université Grenoble Alpes Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Improving Causality in Interpretable Video Retrieval

Améliorer la causalité dans la récupération vidéo interprétable


This paper focuses on the causal relation between the detection scores of concept (or tag) classifiers and the ranking decisions based on these scores, paving the way for these tags to be used in the visual explanations. We first define a measure for quantifying a causality on a set of tags, typically those involved in visual explanations. We use this measure for evaluating the actual causality in the explanations generated using a recent interpretable video retrieval system (Dong et al. [4]), which we find to be quite low. We then propose and evaluate improvements for significantly increasing this causality without sacrificing the retrieval accuracy of the system.
Fichier principal
Vignette du fichier
Paper_CBMI_2023_Hal_Version.pdf (1.46 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04210118 , version 1 (22-09-2023)




  • HAL Id : hal-04210118 , version 1


Varsha Devi, Georges Quénot, Philippe Mulhem. Improving Causality in Interpretable Video Retrieval. CBMI 2023, 20th International Conference on Content-based Multimedia Indexing, Sep 2023, Orleans, France, France. ⟨hal-04210118⟩
14 Consultations
17 Téléchargements


Gmail Facebook X LinkedIn More