M
Maguelonne Héritier
Publications - 6
Citations - 108
Maguelonne Héritier is an academic researcher. The author has contributed to research in topics: TRECVID & Video copy detection. The author has an hindex of 5, co-authored 6 publications receiving 101 citations.
Papers
More filters
Journal ArticleDOI
Towards computer-vision software tools to increase production and accessibility of video description for people with vision loss
Langis Gagnon,Samuel Foucher,Maguelonne Héritier,Marc Lalonde,David Byrns,Claude Chapdelaine,James M. Turner,Suzanne Mathieu,Denis Laurendeau,Nath Tan Nguyen,Denis Ouellet +10 more
TL;DR: The paper provides the main conclusions of consultations with producers of video description regarding their practices and with end-users regarding their needs, as well as an analysis of described productions that lead to propose a video description typology.
CRIM's content-based copy detection system for TRECVID
Maguelonne Héritier,Vishwa Gupta,Langis Gagnon,Gilles Boulianne,Samuel Foucher,Patrick Cardinal +5 more
TL;DR: A new method for SIFT quantizing is introduced, which improves the time computation performance while keeping a good precision for SFT representation and provides easy parallel processing on a graphics processing unit, leading to a very fast search.
Proceedings ArticleDOI
A computer-vision-assisted system for Videodescription scripting
Langis Gagnon,Claude Chapdelaine,David Byrns,Samuel Foucher,Maguelonne Héritier,Vishwa Gupta +5 more
TL;DR: An application of video indexing/summarization to produce Videodescription (VD) for the blinds is presented and the main outcomes of this R&D activity started 5 years ago in the laboratory are presented.
Proceedings ArticleDOI
Key-Places Detection and Clustering in Movies Using Latent Aspects
TL;DR: A new method to find and cluster recurrent key-places in a movie based on finding links between key-frames belonging to a same key-place is described, which uses a probabilistic latent space model over the possible match points between the image sets.
Journal ArticleDOI
Places Clustering of Full-Length Film Key-Frames Using Latent Aspect Modeling Over SIFT Matches
TL;DR: An improved unsupervised classification method to extract and link places features and cluster recurrent physical locations (key-places) within a movie is presented and is very efficient for near-duplicate object/background detection with weak overlap.