Emmanuel Dellandréa

TL;DR: This goal is to propose a model enhancing the weakly supervised DPMs by emphasizing the importance of location and size of the initial class-specific root filter, and to adaptively select a discriminative set of candidate bounding boxes as this root filter estimate.

TL;DR: Two textual features to catch the text emotional meaning are developed: one is based on the semantic distance matrix between the text and an emotional dictionary, and the other one carries the valence and arousal meanings of words.

TL;DR: In this paper, the temporal correlation between continuous arousal peaks and Galvanic Skin Response (GSR) was calculated for all 30 movies extracted from the LIRIS-ACCEDE database.

TL;DR: A novel multimodal approach to automatically predict the visual concepts of images through an effective fusion of textual features along with visual ones is proposed, namely the Histogram of Textual Concepts (HTC), which accounts for the relatedness of semantic concepts in accumulating the contributions of words from the image caption toward a dictionary.

TL;DR: The ImageCLEF 2015 Scalable Image Annotation, Localization and Sentence Generation task was the fourth edition of a challenge aimed at developing more scalable image annotation systems and the focus this year had the goal to develop techniques to allow computers to reliably describe images, localize the different concepts depicted in the images and generate a description of the scene.