Research Papers




Research Papers

RESEARCH PAPER / Jan 2022 / Immersive/AR/VR/MR, Optics, Light Field
Waveguide based optical combiners for Augmented Reality (AR) glasses are integrating several Surface Relief Gratings (SRG) whose pitch sizes can be as small as 200 nm for the blue wavelength. All SRG components exploit the first diffraction order to couple in and out or to deviate the light. We present...
RESEARCH PAPER / MediaEval Workshop 2021 / Dec 2021 / Computer Vision, Machine learning/ Deep learning /Artificial Intelligence
This paper describes the MediaEval 2021 Predicting Media Memorability task. After first being proposed at MediaEval 2018, the Predicting Media Memorability task is in its 4th edition this year, as the prediction of short-term and long-term video memorability remains a challenging task. This year, two datasets of videos are used:...
RESEARCH PAPER / Globecomm 2021 / Dec 2021 / 5G, Wireless communication
Techniques which leverage channel state information (CSI) at a transmitter to adapt wireless signals to changing propagation conditions have been shown to improve the reliability of modern multiple input multiple output (MIMO) communication systems. Due to the difficulty of estimating downlink CSI at the transmitter in many wireless systems, CSI...
RESEARCH PAPER / DataInBrief / Dec 2021 / Image processing
Using a collection of publicly available links to short form video clips of an average of 6 seconds duration each, 1,275 users manually annotated each video multiple times to indicate both longterm and short-term memorability of the videos. The annotations were gathered as part of an online memory game and...
RESEARCH PAPER / 25th International ITG Workshop on Smart Antennas (WSA 2021) / Nov 2021 / 5G, Wireless communication
In this work, we propose a novel deep learning-based framework for the adaptive configuration of DMRS used for MIMO CCE. Specifically, a neural network architecture is proposed at the terminal side which based on statistical learning indicates to the network the preferred configuration of DMRS in time, frequency, and code...
RESEARCH PAPER / Nov 2021 / Displays
We propose the new type of color splitter, which guides a selected bandwidth of incident light towards the proper photosensitive area of the image sensor by exploiting the nanojet (NJ) beam phenomenon. Such splitting can be performed as an alternative to filtering out part of the received light on each...
Human character animation is often critical in entertainment content production, including video games, virtual reality or fiction films. To this end, deep neural networks drive most recent advances through deep learning (DL) and deep reinforcement learning (DRL). In this article, we propose a comprehensive survey on the state-of-the-art approaches based...
RESEARCH PAPER / IEEE International Conference on Computer Vision (ICCV) / Oct 2021 / Machine learning/Deep learning /Artificial Intelligence, Neural network
The backdoor attack raises a serious security concern to deep neural networks, by fooling a model to misclassify certain inputs designed by an attacker. In particular, the trigger-free backdoor attack is a great challenge to be detected and mitigated. It targets one or a few specific samples, called target samples,...
Music source separation is the task of isolating individual instruments which are mixed in a musical piece. This task is particularly challenging, and even state-of-the-art models can hardly generalize to unseen test data. Nevertheless, prior knowledge about individual sources can be used to better adapt a generic source separation model...
RESEARCH PAPER / ICCV 2021 / Oct 2021 / Computer Vision
High-level understanding of stories in video such as movies and TV shows from raw data is extremely challenging. Modern video question answering (VideoQA) systems often use additional human-made sources like plot synopses, scripts, video descriptions or knowledge bases. In this work, we present a new approach to understand the whole...
RESEARCH PAPER / International conference on computer vision / Oct 2021 / Computer Vision, Neural network, Machine learning/ Deep learning /Artificial Intelligence
High quality facial attribute editing in videos is a challenging problem as it requires the modifications to be realistic and consistent throughout the video frames. Previous works address the problem with auto-encoder architectures and rely on adversarial training to ensure the attribute editing and the temporal consistency of the results....
RESEARCH PAPER / Future Network Artificial Intelligence and Machine Learning Workshop / Sep 2021 / Wireless communication, 5G
Next generation Terabit per second (Tbps) wireless communication systems aim for sub-THz and THz bands where noise and hardware impairments are known to be dominantly non-linear and lack accurate closed form analytical models. The physical layer (PHY) blocks designed under linearity and Gaussian noise assumptions will fall short of satisfying...
Recently, learning methods have been designed to create Multiplane Images (MPIs) for view synthesis. While MPIs are extremely powerful and facilitate high quality renderings, a great amount of memory is required, making them impractical for many applications. In this paper, we propose a learning method that optimizes the available memory...
Despite many modern applications of Deep Neural Networks (DNNs), the large number of parameters in the hidden layers makes them unattractive for deployment on devices with storage capacity constraints. In this paper we propose a Data-Driven Low-rank (DDLR) method to reduce the number of parameters of pretrained DNNs and expedite...
RESEARCH PAPER / IEEE International Symposium on Networks, Computers and Communications (ISNCC'21) / Sep 2021
In this paper, a novel scheme that utilizes soft decision LLR values of CRC bits to aid BP decoding in polar codes is proposed. We show that the proposed periodic CRC scheduling for the factor graphs of BP decoding, combined with relaxation operations can prevent short cycles and improve FER...
RESEARCH PAPER / SPIE - Optical system Design 2021 / Sep 2021 / Optics, Machine learning/ Deep learning /Artificial Intelligence, Image processing
In recent years, we have seen the development of integrated plenoptic sensors, where multiple pixels are placed under one microlens. It is mainly used by cameras and smartphones to drive the autofocus of the main lens, and it often takes the form of dual-pixels with 2 rectangular sub-pixels. We study...
Deep neural networks (DNNs) have recently achieved great success in many machine learning tasks including computer vision and speech recognition. However, existing DNN models are computationally expensive and memory demanding, hindering their deployment in devices with low memory and computational resources or in applications with strict latency requirements. In addition,...
RESEARCH PAPER / IEEE VTC'21-Fall / Aug 2021 / 5G, Wireless communication, Antennas
Reconfigurable intelligent surfaces (RIS) have the ability to steer the electromagnetic waves to a desired direction. This enables the improvement of the wireless link performance by allowing the illumination of receivers otherwise shadowed by buildings or hills. In this paper, a link level simulations are used to study the performance...
Deep bi-prediction blending. This paper presents a learning-based method to improve bi-prediction in video coding. In conventional video coding solutions, block-based motion compensation blocks from already decoded reference pictures stand out as the main tool used to predict the current frame. Especially, bi-predicted blocks, i.e. blocks that combine two different...
RESEARCH PAPER / SPIE / Applications of Digital Image Processing / Aug 2021 / Video coding
Film grain is often desirable feature in video production. Content creators can use film grain to create a natural appearance and to express their creative-artistic impression. With the expansion of the streaming services, prior to delivery, video typically undergo various pre-processing steps, where the inevitable video compression is presented. Modern...