Skip to Main content Skip to Navigation
Habilitation à diriger des recherches

Advanced features for image representation: integrating relations, weights, depth, and time

Abstract : Tremendous amounts of visual data are produced every day, such as user-generated images and videos from social media platforms, audiovisual archives, etc. It is im- portant to be able to search and retrieve documents among such large collections. Our work in computer vision and multimedia information retrieval focuses on vi- sual features for image representation. In particular, inside the entire processing chain ranging from visual data acquisition with sensors to the user interface that facilitates the interaction with the system, our research addresses the internal rep- resentation of visual data in the form of an index that serves as a reference for the system regarding the image contents. In the general context of image representation, we describe in a first part some contributions related to the widely-used paradigm of “bags of visual words”. We also discuss the general notion of relation, taken at several levels – the low level of visual words, the transversal level aiming for cross-modal annotation, and the high level of semantic objects. Finally, we focus on the definition of weighting models, that serve as visual counterparts to popular weighting schemes used for text. Because of the specificity of persons and their faces compared to general objects, we focus in a second part on specific features and methods for person recognition. Two directions are developed to overcome some limitations of static 2D approaches based on face images, with the objective of improving systems’ precision and ro- bustness. One direction integrates depth in facial features, and the other takes advantage of temporal information in video streams. In both cases, dedicated features and strategies are investigated.
Complete list of metadatas

Cited literature [165 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-01693520
Contributor : Jean Martinet <>
Submitted on : Friday, January 26, 2018 - 11:48:42 AM
Last modification on : Monday, October 19, 2020 - 11:00:07 AM
Long-term archiving on: : Friday, May 25, 2018 - 3:37:01 AM

File

HDR_Martinet.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : tel-01693520, version 1

Citation

Jean Martinet. Advanced features for image representation: integrating relations, weights, depth, and time. Computer Vision and Pattern Recognition [cs.CV]. Université de Lille 1, Sciences et Technologies, 2016. ⟨tel-01693520⟩

Share

Metrics

Record views

192

Files downloads

483