We report a new neural backdoor attack, named Hibernated Backdoor, which is stealthy, aggressive and devastating. The backdoor is planted in a hibernated mode to avoid being detected. Once deployed and fine-tuned on end devices, the hibernated backdoor turns into the active state that can be exploited by the attacker....
RESEARCH PAPER / Jan 2022
/
Immersive / AR/VR/MR,
Light Field,
Volumetric Imaging,
Machine learning/ Deep learning /Artificial Intelligence
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...
RESEARCH PAPER / 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:...
AI will become an essential part of our lives in the next few years, with the promise of delivering super-intelligent computers that exceed human analytical abilities. This is, however, several years away; indeed, the industry has only just embarked upon understanding what’s possible. Arguably the hype surrounding AI thus far...
RESEARCH PAPER / Oct 2021
/
Computer Graphics,
Machine learning/ Deep learning /Artificial Intelligence
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 / Oct 2021
/
Audio processing,
Neural network,
Machine learning/ Deep learning /Artificial Intelligence
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...
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,...
RESEARCH PAPER / 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 / Sep 2021
/
Video coding,
Compression,
Machine learning/ Deep learning /Artificial Intelligence Neural network
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 / Sep 2021
/
Video coding,
Machine learning/ Deep learning /Artificial Intelligence,
Image processing,
Computer Graphics
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...
RESEARCH PAPER / 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...
RESEARCH PAPER / Aug 2021
/
Neural network,
Machine learning/ Deep learning /Artificial Intelligence,
Computer Vision
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 / Aug 2021
/
Video coding,
Compression,
Machine learning/ Deep learning /Artificial Intelligence
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 / Jul 2021
/
5G,
Wireless communication,
Machine learning/ Deep learning /Artificial Intelligence
Building upon on a digital transformation, Industry 4.0 (I4.0) aims to build the factories of the future, which feature additional flexibility, increasingly connected infrastructures and automated processes. 5G is playing a paramount role in this transformation, as it can offer high bandwidth, reliable and low latency wireless connectivity to meet...
RESEARCH PAPER / Dec 2020
/
["Volumetric Imaging",
"Machine learning/ Deep learning /Artificial Intelligence"]
We present a novel learning-based approach to synthesize new views of a light field image. In particular, given the four corner views of a light field, the presented method estimates any in-between view. We use three sequential convolutional neural networks for feature extraction, scene geometry estimation and view selection. Compared...
RESEARCH PAPER / Dec 2020
/
5G,
Machine learning/ Deep learning /Artificial Intelligence,
Network and Communications
This document describes the winning solution to the GNN Challenge 2020 organized by the Barcelona Neural Networking Center for the ITU Artificial Intelligence/Machine Learning in 5G Challenge. We first describe our methodology, then give the set of hyper-parameters that allowed us to achieve the best score with an average relative...
In this paper we address the problem of view synthesis from large baseline light fields, by turning a sparse set of input views into a Multi-plane Image (MPI). Because available datasets are scarce, we propose a lightweight network that does not require extensive training. Unlike latest approaches, our model does...
This paper presents CompressAI, an open-source library that provides custom operations, layers, models and tools to research, develop, and evaluate end-to-end image and video codecs. In particular, CompressAI includes pre-trained models and evaluation tools to compare learned methods with traditional codecs. Multiple models from the state-of-the-art on learned end-to-end image...
arxiv version of https://interdigital.sharepoint.com/sites/RI/Lists/ID Publications/DispForm.aspx?ID=794
RESEARCH PAPER / May 2017
/
Machine learning/ Deep learning /Artificial Intelligence,
Computing and Optimization
Learning from multi-label data in an interactive framework is a challenging problem as algorithms must withstand some additional constraints: in particular, learning from few training examples in a limited time. A recent study of multi-label classifier behaviors in this context has identified the potential of the ensemble method “Random Forest...
Generating complex discrete distributions remains as one of the challenging problems in machine learning. Existing techniques for generating complex distributions with high degrees of freedom depend on standard generative models like Generative Adversarial Networks (GAN), Wasserstein GAN, and associated variations. Such models are based on an optimization involving the distance...
In October 2016, the International Academy, Research and Industry Association (IARIA) hosted its eighth International Conference on Emerging Networks and Intelligence, and last month awarded five “Best Papers” from the event’s call for papers including a submission from an InterDigital engineer and her collaborators. IARIA’s International Conference on Emerging Networks...