-
Look and Listen: A Multi-modality Late Fusion Approach to Scene Classification for Autonomous Machines
The novelty of this study consists in a multi-modality approach to scenenclassification, where image and audio complement each other in a process ofndeep late fusion. The approach is demonstrated on a difficult classificationnproblem, consisting of two synchronised and balanced datasets…
-
Traffic3D: A New Traffic Simulation Paradigm
The field of Deep Reinforcement Learning has evolved significantly over the last few years. However, an important and not yet fully-attained goal is to produce intelligent agents which can be successfully taken out of the laboratory and employed in the…
-
Dress Like a Star: Retrieving Fashion Products from Videos
This work proposes a system for retrieving clothing and fashion products from video content. Although films and television are the perfect showcase for fashion brands to promote their products, spectators are not always aware of where to buy the latest…
-
rcGAN: Learning a Generative Model for Arbitrary Size Image Generation
-
Using frontier points to recover shape, reflectance and illumination
We describe a method to recover the surface reflectance and the 3D shape of a non-Lambertian object as well as illumination, from a collection of images. It is based on the so-called frontier points, which are extracted from the outlines…
-
Variational Recurrent Sequence-to-Sequence Retrieval for Stepwise Illustration
-
QuiltGAN: An Adversarially Trained, Procedural Algorithm for Texture Generation
-
How to Read Paintings: Semantic Art Understanding with Multi-Modal Retrieval
Automatic art analysis has been mostly focused on classifying artworks intondifferent artistic styles. However, understanding an artistic representationninvolves more complex processes, such as identifying the elements in the scenenor recognizing author influences. We present SemArt, a multi-modal dataset fornsemantic art…
