Research Papers



Research Papers

RESEARCH PAPER / IEEE Transactions on Pattern Analysis and Machine Intelligence / Nov 2019 / Network & Communications, Machine/Deep Learning/AI
Efficient Nearest Neighbor (NN) search in high-dimensional spaces is a foundation of many multimedia retrieval systems. A common approach is to rely on Product Quantization, which allows the storage of large vector databases in memory and efficient distance computations. Yet, implementations of nearest neighbor search with Product Quantization have their...
RESEARCH PAPER / 2019 49th European Microwave Conference (EuMC) / Oct 2019 / Wireless communications, Antennas
This paper presents a novel planar compact integrated four-sector antenna for sub-6GHz 5G indoor access and content distribution over 2.45GHz/ 5.5GHz dual-band WiFi in 2x2 MIMO configuration. The four sectors, for 5G applications, are obtained via Vivaldi antennas with ground reuse for achieving very compact dimensions. A compact two-port slot...
RESEARCH PAPER / DIDL workshop (Rennes) / Oct 2018 / Machine/Deep Learning/AI, Network & Communications
"A recently celebrated kind of deep neural networks is Generative Adversarial Networks. GANs are generators of samples from a distribution that has been learned; they are up to now centrally trained from local data on a single location. We question the performance of training GANs using a spread dataset over...
RESEARCH PAPER / ACM Multimedia 2018 / Oct 2018 / Computer Vision, Machine, Deep learning/AI
Scene-agnostic visual inpainting remains very challenging despite progress in patch-based methods. Recently, Pathak et al. [26] have introduced convolutional "context encoders'' (CEs) for unsupervised feature learning through image completion tasks. With the additional help of adversarial training, CEs turned out to be a promising tool to complete complex structures in...
RESEARCH PAPER / ISMAR / Oct 2018 / Immersive/AR/VR/MR, Computer Vision
We present a diminished reality application running live on consumer mobile devices. In our pre-observation-based approach, the clean 3D scene, free of undesired objects, is scanned beforehand and reconstructed as a high resolution textured 3D model. At runtime, objects added in a region of interest are efficiently removed by projecting...
RESEARCH PAPER / ICIP 2018 / Oct 2018 / Image Processing, Light Field, Computer Vision
We present a new method for reconstructing a 4D light field from a random set of measurements. A 4D light field block can be represented by a sparse model in the Fourier domain. As such, the proposed algorithm reconstructs the light field, block by block, by selecting frequencies of the...
RESEARCH PAPER / IEEE AP-S 2018 / Jul 2018 / Wireless Communications, Antennas
This paper presents a novel compact, wideband, four directional radiation patterns, antenna. The radiating element topology is inspired from the Annular Slot Antenna (ASA) and printed wideband monopole. The antenna is designed for North American ATSC-TV indoor reception. For an S11<;-6dB, it covers both High-VHF and UHF bands. It presents...
RESEARCH PAPER / IEEE AP-S 2018 / Jul 2018 / Wireless Communications, Antennas
This paper presents a novel compact hybrid monopole- Annular Slot Antenna (ASA). The proposed antenna combines the advantages of an ASA with the broadband feature of a wideband monopole. The antenna simulated performance is thoroughly analyzed and validated via measurements.
RESEARCH PAPER / Picture coding symposium / Jun 2018 / Image Processing, Video Coding
Recently, the advances in transform coding have contributed to significant bitrate saving for the next generation of video coding. In particular, the combination of different discrete trigonometric transforms (DTT’s) was adopted in the Joint Video Exploration Team (JVET) solution, as well as the Bench-Mark Set (BMS) of the future video...
RESEARCH PAPER / Eurohaptics / Jun 2018 / Immersive/AR/VR/MR, Haptics, Human Machine Interface
In this paper, we propose a new format for haptic texture mapping which is not dependent on the haptic rendering setup hardware. Our “haptic material” format encodes ten elementary haptic features in dedicated maps, similarly to “materials” used in computer graphics. These ten different features enable the expression of compliance,...
RESEARCH PAPER / EuroHaptics / Jun 2018 / Immersive/AR/VR/MR, Haptics, Human Machine Interface
With the growth of virtual reality setups, digital sculpting tools become more and more immersive. It is now possible to create a piece of art within a virtual environment, directly with the controllers. However, these devices do not allow to touch the virtual material as a sculptor would do. To...
RESEARCH PAPER / Eurographics 2018 / May 2018 / Immersive/AR/VR/MR, Computer Graphics
Our work is a perceptual study into the effects of training poses on the Example-Based Facial Rigging (EBFR) method. We analyse the output of EBFR given a set of training poses to see how well the results reproduced our ground truth actor scans compared to a Deformation Transfer approach. While...
RESEARCH PAPER / Proceedings of IEEE ICASSP, 2018 / Apr 2018 / Machine/Deep Learning /AI
Inductive matrix completion (IMC) is a model for incorporating side information in form of “features” of the row and column entities of an unknown matrix in the matrix completion problem. As side information, features can substantially reduce the number of observed entries required for reconstructing an unknown matrix from its...
RESEARCH PAPER / IEEE Int. Conf. on Audio, Speech and Signal Processing (ICASSP) / Apr 2018 / Audio Processing, Machine/Deep Learning/AI
Style transfer' among images has recently emerged as a very active research topic, fuelled by the power of convolution neural networks (CNNs), and has become fast a very popular technology in social media. This paper investigates the analogous problem in the audio domain: How to transfer the style of a...
RESEARCH PAPER / IEEE Int. Conf. on Audio, Speech and Signal Processing (ICASSP) / Apr 2018 / Computer Vision, Machine/Deep learning/AI
Memorability of media content such as images and videos has recently become an important research subject in computer vision. This paper presents our computation model for predicting image memorability, which is based on a deep learning architecture designed for a classification task. We exploit the use of both convolutional neural...
RESEARCH PAPER / APMAR 2018 / Apr 2018 / Immersive/AR/VR/MR, Computer Vision
Photometric registration consists in blending real and virtual scenes in a visually coherent way. To achieve this goal, both reflectance and illumination properties must be estimated. These estimates are then used, within a rendering pipeline, to virtually simulate the real lighting's interaction with the scene. In this paper, we are...
RESEARCH PAPER / ACM ToG + ACM SIGGRAPH'18 / Apr 2018 / Immersive/AR/VR/MR, Production Workflow
Quadrotor drones equipped with high quality cameras have rapidly raised as novel, cheap and stable devices for filmmakers. While professional drone pilots can create aesthetically pleasing videos in short time, the smooth -- and cinematographic -- control of a camera drone remains challenging for most users, despite recent tools that...
RESEARCH PAPER / Electronic Displays Conference / Feb 2018 / Image Processing, Computer Vision, Color Management
A wide color gamut (WCG) display has great color rendering capability and offers the opportunity to achieve a pleasing and realistic appearance in terms of image quality. To take full advantage of the large display gamut, a new gamut extension algorithm (GEA) is proposed based on a new color appearance...
RESEARCH PAPER / CVPR 2018 / Jan 2018 / Machine/Deep Learning/AI
To work at scale, a complete image indexing system comprises two components: An inverted file index to restrict the actual search to only a subset that should contain most of the items relevant to the query; An approximate distance computation mechanism to rapidly scan these lists. While supervised deep learning...
RESEARCH PAPER / IEEE Transactions on Image Processing / Dec 2017 / Image Processing, Video Coding
Thanks to the increasing number of images stored in the cloud, external image similarities can be leveraged to efficiently compress images by exploiting inter-images correlations. In this paper, we propose a novel image prediction scheme for cloud storage. Unlike current state-of-the-art methods, we use a semi-local approach to exploit inter-image...