Post-Hoc Interactive Analytics of Errors in the Context of a Person Discovery Task

Abstract : Part of the research effort in automatic person discovery in multimedia content consists in analyzing the errors made by algorithms. However exploring the space of models relating algorithmic errors in person discovery to intrinsic properties of associated shots (e.g. person facing the camera) - coined as post-hoc analysis in this paper - requires data cura- tion and statistical model tuning, which can be cumbersome. In this paper we present a visual and interactive tool that facilitates this exploration. Adequate statistical building blocks are defined, and coordinated by visual and interactive components inspired from the literature in information visualization. A case study is conducted with multimedia researchers to validate the tool. Real data obtained from the MediaEval person discovery task was used for this experiment. Our approach yielded novel insight that was completely unsuspected previously.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01701954
Contributor : Limsi Publications <>
Submitted on : Tuesday, February 6, 2018 - 1:13:41 PM
Last modification on : Saturday, May 4, 2019 - 1:18:43 AM

Identifiers

  • HAL Id : hal-01701954, version 1

Citation

Pierrick Bruneau, Mickaël Stefas, Johann Poignant, Hervé Bredin, Claude Barras. Post-Hoc Interactive Analytics of Errors in the Context of a Person Discovery Task. IEEE International Symposium on Multimedia 2016, IEEE Computer Society, Jan 2016, San Jose, United States. ⟨hal-01701954⟩

Share

Metrics

Record views

48