Susana Zoghbi
Katholieke Universiteit Leuven
22 Papers
89 Citations
Susana Zoghbi is an academic researcher from Katholieke Universiteit Leuven. The author has contributed to research in topics: Latent Dirichlet allocation & Topic model. The author has an hindex of 9, co-authored 22 publications. Previous affiliations of Susana Zoghbi include University of British Columbia & University of Copenhagen Faculty of Science.
Chat about Author
Papers
Measurement instruments for the anthropomorphism, animacy, likeability, perceived intelligence, and perceived safety of robots
TL;DR: A literature review has been performed on the measurements of five key concepts in HRI: anthropomorphism, animacy, likeability, perceived intelligence, and perceived safety, distilled into five consistent questionnaires using semantic differential scales.
Latent Dirichlet allocation for linking user-generated content and e-commerce data
TL;DR: The proposed MiLDA model is able to deal with intrinsic multi-idiomatic data by considering the shared vocabulary between the aligned document pairs, and obtains the largest stability (less variation with changes in parameters) and highest mean average precision scores in the linking task.
36
Web Search of Fashion Items with Multimodal Querying
Katrien Laenen,Susana Zoghbi,Marie-Francine Moens +2 more
- 02 Feb 2018
TL;DR: A novel multimodal fashion search paradigm where e-commerce data is searched with a multi-modal query composed of both an image and text and it is shown that this model substantially outperforms two state-of-the-art retrieval models adapted to multimodals fashion search.
35
Measuring intent in human-robot cooperative manipulation
Davide De Carli,Evan Hohert,Chris A. C. Parker,Susana Zoghbi,Simon Leonard,Elizabeth A. Croft,Antonio Bicchi +6 more
- 18 Dec 2009
TL;DR: This research utilizes force/torque sensor measurements to identify intentional user communications specifying a change in the task direction and considers the impact of path recomputation and the resulting robot haptic feedback on user physiological response.
21
•Proceedings Article
Cross-modal search for fashion attributes
Katrien Laenen,Susana Zoghbi,Marie-Francine Moens +2 more
- 01 Jan 2017
TL;DR: A neural network which learns intermodal representations for fashion attributes to be utilized in a cross-modal search tool and demonstrates that the neural network model trained with the objective function on image fragments acquired with the rule-based segmentation approach improves the results of image search with textual queries.
21