E
Eloi Zablocki
Researcher at Valeo
Publications - 19
Citations - 119
Eloi Zablocki is an academic researcher from Valeo. The author has contributed to research in topics: Computer science & Context (language use). The author has an hindex of 5, co-authored 16 publications receiving 84 citations.
Papers
More filters
Proceedings Article
Context-Aware Zero-Shot Learning for Object Recognition.
TL;DR: This work proposes a new and challenging approach, context-aware ZSL that leverages semantic representations in a new way to model the conditional likelihood of an object to appear in a given context and shows that contextual information can substantially improve the standard ZSL approach and is robust to unbalanced classes.
Proceedings Article
Learning Multi-Modal Word Representation Grounded in Visual Context.
TL;DR: This work explores various choices for what can serve as a visual context and presents an end-to-end method to integrate visual context elements in a multimodal skip-gram model and provides experiments and extensive analysis of the obtained results.
Posted Content
Explainability of vision-based autonomous driving systems: Review and challenges.
TL;DR: In this paper, a survey of explainability methods for vision-based self-driving systems is presented, which discusses definitions, context, and motivation for gaining more interpretability and explainability from selfdriving systems.
Posted Content
Incorporating Visual Semantics into Sentence Representations within a Grounded Space.
TL;DR: A model to transfer visual information to textual representations by learning an intermediate representation space: the grounded space is proposed and it is shown that this model outperforms the previous state-of-the-art on classification and semantic relatedness tasks.
Proceedings ArticleDOI
Incorporating Visual Semantics into Sentence Representations within a Grounded Space
TL;DR: The authors propose to transfer visual information to textual representations by learning an intermediate representation space: the grounded space, which can be used to enrich textual representations with visual information, and further propose two complementary objectives ensuring that sentences associated with the same visual content are close in the grounded spaces and similarities between related elements are preserved across modalities.