Concept
Detached object
Related publications (94)
Self-Supervision By Prediction For Object Discovery In Videos
Pascal Frossard, Beril Besbinar
Despite their irresistible success, deep learning algorithms still heavily rely on annotated data, and unsupervised settings pose many challenges, such as finding the right inductive bias in diverse scenarios. In this paper, we propose an object-centric mo ...
IEEE2021Inducing Meaningful Units from Character Sequences with Slot Attention
James Henderson, Melika Behjati
Characters do not convey meaning, but sequences of characters do. We propose an unsupervised distributional method to learn the abstract meaning-bearing units in a sequence of characters. Rather than segmenting the sequence, this model discovers continuous ...
2021Better Generic Objects Counting When Asking Questions to Images: A Multitask approach for Remote Sensing Visual Question Answering
Devis Tuia, Benjamin Alexander Kellenberger, Sylvain Lobry
Visual Question Answering for Remote Sensing (RSVQA) aims at extracting information from remote sensing images through queries formulated in natural language. Since the answer to the query is also provided in natural language, the system is accessible to n ...
2020Does scaling player size skew one’s ability to correctly evaluate object sizes in a virtual environment?
Ronan Boulic, Bruno Herbelin, Mathias Guy Delahaye
This paper presents the results of a study performed in order to evaluate whether a navigation technique, based on scaling the user’s avatar, impacts the user’s ability to correctly assess the size of virtual objects in a virtual environment. This study wa ...
Association for Computing Machinery2020Oclussion-Aware Motion Planning at Roundabouts
In this work, we present a motion planning framework for automated vehicles to drive safely through intersections despite occlusions and the uncertain behavior of the surrounding vehicles. A context representation based on probably-free gaps is proposed as ...
2020Event-Based Motion Segmentation by Motion Compensation
In contrast to traditional cameras, whose pixels have a common exposure time, event-based cameras are novel bio-inspired sensors whose pixels work independently and asynchronously output intensity changes (called "events"), with microsecond resolution. Sin ...
2019Peripersonal space (PPS) as a multisensory interface between the individual and the environment, defining the space of the self
Our brain has developed a specific system to represent the space closely surrounding the body, termed pen personal space (PPS). This space has a key functional role as it is where all physical interactions with objects in the environment occur. Here I desc ...
PERGAMON-ELSEVIER SCIENCE LTD2019Resonant optical trapping in hollow photonic crystal cavities and its potential use for bacterial characterisation
During the last decade, the development of optofluidic chips has become a large field of research. The integration of nano and microstructures with microfluidics layers allowed for the miniaturisation of a number of tools traditionally used in laboratories ...
EPFL2019Ultrabroadband 3D invisibility with fast-light cloaks
Hatice Altug, Dordaneh Etezadi, Kosmas Tsakmakidis, Ershad Mohammadi, Foziyeh Sohrabi
An invisibility cloak should completely hide an object from an observer, ideally across the visible spectrum and for all angles of incidence and polarizations of light, in three dimensions. However, until now, all such devices have been limited to either s ...
2019Bridging the Gap between Semantics and Multimedia Processing
Roberto Gerson De Albuquerque Azevedo
In this paper, we overview the semantic gap problem in multimedia and discuss how machine learning and symbolic AI can be combined to narrow this gap. We describe the semantic gap in terms of a classical architecture for multimedia processing and discuss a ...
IEEE2019