InterDigital logo which acts as a link to the home page
  • Research & Innovation  
    • Overview
    • WIRELESS LAB
    • Video Lab
    • Emerging Technologies Lab
    • Talent
  • Thought Leadership  
    • Vault
    • Sustainability
    • Blog
    • Creators
  • About Us  
    • Overview
      • Leadership
      • History
      • Licensing
      • Contact
    • Government Solutions
    • Careers
    • Media
  • Investors  
    • Investor Relations
    • ESG / SUSTAINABILITY
  • Search

Results for Machine




Results for Machine

Hibernated Backdoor: A Mutual Information Empowered Backdoor Attack to Deep Neural Networks
RESEARCH PAPER / Mar 2022 / Security, Machine Learning/Deep Learning/Artificial Intelligence
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....
Deep View Synthesis with Compact and Adaptive Multiplane Images
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...
Overview of The MediaEval 2021 Predicting MediaMemorability Task
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 and Machine Learning in the Video Industry: New opportunities for the entertainment sector
WHITE PAPER / Dec 2021 / AI, Machine Learning, Video
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...
A Survey on Deep Learning for Skeleton-Based Human Animation
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...
User-guided one-shot deep model adaptation for music source separation
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...
CLEAR: Clean-up Trigger-Free Backdoor in Neural Networks
RESEARCH PAPER / 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,...
Disentangled Face Attribute Editing for High Quality Videos
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....
Data-Driven Low-Rank Neural Network Compression
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...
Compact and Adaptive Multiplane Images for View Synthesis
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...
Deep learning applied to quad pixel plenoptic sensor
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...
Inplace knowledge distillation with teacher assistant for improved training of flexible neural networks
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,...
Deep bi-prediction blending
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...
Public and Non-Public Network Integration for 5Growth Industry 4.0 Use Cases
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...
Learning Occlusion-Aware View Synthesis for Light Fields
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...
Graph Neural Networking Challenge 2020 - Steredeg's solution
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...
Learning light field synthesis from MPI: scene encoding as a segmentation task
RESEARCH PAPER / Oct 2020 / Light Field, Machine learning/ Deep learning /Artificial Intelligence
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...
A PyTorch library and evaluation platform for end-to-end compression research
RESEARCH PAPER / Sep 2020 / Video coding, Machine learning/ Deep learning /Artificial Intelligence
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...
Flexible Recurrent Neural Networks
RESEARCH PAPER / Sep 2020 / Machine learning/ Deep learning /Artificial Intelligence
arxiv version of https://interdigital.sharepoint.com/sites/RI/Lists/ID Publications/DispForm.aspx?ID=794
Haptic Images: a survey on surface haptics
RESEARCH PAPER / Sep 2020 / Haptic, Human Machine Interface
The development of tactile screens opens new perspectives for co-located images and haptic rendering, leading to the concept of “haptic images.” They emerge from the combination of image data, rendering hardware, and haptic perception. This enables one to perceive haptic feedback while manually exploring an image. This raises nevertheless two...
Quicker ADC : Unlocking the hidden potential of Product Quantization with SIMD
RESEARCH PAPER / 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...
Gossiping GANs
RESEARCH PAPER / 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...
Structural Inpainting
RESEARCH PAPER / 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...
Haptic Material: A Holistic Approach for Haptic Texture Mapping
RESEARCH PAPER / 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,...
A Tangible Surface for Digital Sculpting in Virtual Environments
RESEARCH PAPER / 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...
Global Optimality in Inductive Matrix Completion
RESEARCH PAPER / 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...
Deep Learning for Image Memorability Prediction
RESEARCH PAPER / 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...
Audio Style Transfer
RESEARCH PAPER / 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...
Learning a Complete Image Indexing Pipeline
RESEARCH PAPER / 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...
Sketching for Large Scale Learning of Mixture Models
RESEARCH PAPER / Nov 2017 / Machine/Deep Learning/AI, Network & Communications
Learning parameters from voluminous data can be prohibitive in terms of memory and computational requirements. We propose a ‘compressive learning’ framework, where we estimate model parameters from a sketch of the training data. This sketch is a collection of generalized moments of the underlying probability distribution of the data. It...
The Topological Face of Recommendation
RESEARCH PAPER / Nov 2017 / Machine/Deep Learning/AI, Network & Communications
The success of Google’s PageRank algorithm popularized graphs as a tool to model the web’s navigability. At that time, the web topology was resulting from human edition of hyper-links. Nowadays, that topology is mostly resulting from algorithms. In this paper, we propose to study the topology realized by a class...
Scattering Features for Multimodal Gait Recognition
RESEARCH PAPER / Nov 2017 / Machine/Deep Learning/AI, IoT Computer Vision
We consider the problem of identifying people on the basis of their walk (gait) pattern. Classical approaches to tackle this problem are based on, e.g., video recordings or piezoelectric sensors embedded in the floor. In this work, we rely on acoustic and vibration measurements, obtained from a microphone and a...
Distributed Deep Learning on Edge-Devices: Feasibility Via Adaptive Compression
RESEARCH PAPER / Oct 2017 / Machine/Deep Learning/AI, Network & Communications
A large portion of data mining and analytic services use modern machine learning techniques, such as deep learning. The state-of-the-art results by deep learning come at the price of an intensive use of computing resources. The leading frameworks (e.g., TensorFlow) are executed on GPUs or on high-end servers in datacenters....
Supervised Structured Binary Codes for Image Search
RESEARCH PAPER / Oct 2017 / Machine/Deep Learning/AI Computer Vision
For large-scale visual search, highly compressed yet meaningful representations of images are essential. Structured vector quantizers based on product quantization and its variants are usually employed to achieve such compression while minimizing the loss of accuracy. Yet, unlike binary hashing schemes, these unsupervised methods have not yet benefited from the...
MoFA: Model-based deep convolutional face autoencoder for unsupervised monocular reconstruction
RESEARCH PAPER / Oct 2017 / Machine/Deep Learning/AI, Image Processing Computer Vision
In this work we propose a novel model-based deep convolutional autoencoder that addresses the highly challenging problem of reconstructing a 3D human face from a single in-the-wild color image. To this end, we combine a convolutional encoder network with an expert-designed generative model that serves as decoder. The core innovation...
Emotion recognition based on high-resolution EEG recordings and reconstructed brain sources
RESEARCH PAPER / Oct 2017 / Machine/Deep Learning/AI, Human Machine Interface
Electroencephalography (EEG)-based emotion recognition is currently a hot issue in the affective computing community. Numerous studies have been published on this topic, following generally the same schema: 1) presentation of emotional stimuli to a number of subjects during the recording of their EEG, 2) application of machine learning techniques to...
MR TV Mozaik: A New Mixed Reality Interactive TV Experience
RESEARCH PAPER / Oct 2017 / Immersive/AR/VR/MR, Human Machine Interface
Technicolor has been investigating how Mixed Reality technology could impact the future of home entertainment. We have designed and implemented a system to extend a standard TV experience with AR content, using a consumer tablet or a headset. A virtual TV mosaic is displayed around the TV screen and used...
Role detection in online forums based on growth models for trees
RESEARCH PAPER / Oct 2017 / Machine/Deep Learning/AI, Network & Communications
Some structural characteristics of online discussions have been successfully modeled in the recent years. When parameters of these models are properly estimated, the models are able to generate synthetic discussions that are structurally similar to the real discussions. A common aspect of these models is that they consider that all...
Comparative study of example-guided audio source separation approaches based on nonnegative matrix factorization
RESEARCH PAPER / Sep 2017 / Audio Processing, Machine/Deep Learning/AI
We consider example-guided audio source separation approaches, where the audio mixture to be separated is supplied with source examples that are assumed matching the sources in the mixture both in frequency and time. These approaches were successfully applied to the tasks such as source separation by humming, score-informed music source...
Multimodality and Deep Learning when predicting Media
RESEARCH PAPER / Sep 2017 / Machine/Deep Learning/AI, Computer Vision
This paper summarizes the computational models that Technicolor proposes to predict interestingness of images and videos within the MediaEval 2017 PredictingMedia Interestingness Task. Our systems are based on deep learning architectures and exploit the use of both semantic and multimodal features. Based on the obtained results, we discuss our findings...
MediaEval 2017 Predicting Media Interestingness Task
RESEARCH PAPER / Sep 2017 / Machine/Deep Learning/AI, Computer Vision
In this paper, the Predicting Media Interestingness task which is running for the second year as part of the MediaEval 2017 Benchmarking Initiative for Multimedia Evaluation, is presented. For the task, participants are expected to create systems that automatically select images and video segments that are considered to be the...
Learn to unify local and non-local signal processings with graph CNN
RESEARCH PAPER / Sep 2017 / Machine/Deep Learning/AI, Computer Vision, Image Process
This paper deals with the unification of local and non-local signal processing on graphs within a single convolutional neural network (CNN) framework. Building upon recent works on graph CNNs, we propose to use convolutional layers that take as inputs two variables, a signal and a graph, allowing the network to...
Maximum Margin Linear Classifiers in Unions of Subspaces
RESEARCH PAPER / Sep 2017 / Machine/Deep Learning/AI
In this work, we propose a framework, dubbed Union-of-Subspaces SVM (US-SVM), to learn linear classifiers as sparse codes over a learned dictionary. In contrast to discriminative sparse coding with a learned dictionary, it is not the data but the classifiers that are sparsely encoded. Experiments in visual categorization demonstrate that,...
CNN-BASED TRANSFORM SYNTAX PREDICTION IN ADAPTIVE MULTIPLE TRANSFORMS FRAMEWORK TO ASSIST ENTROPY CODING IN HEVC
RESEARCH PAPER / Aug 2017 / Machine/Deep Learning /AI, Image Processing, Video Coding
Recent work in video compression has shown that using multiple 2D transforms instead of a single transform in order to de-correlate residuals provides better compression efficiency. These transforms are tested competitively inside a video encoder and the optimal transform is selected based on the Rate Distortion Optimization (RDO) cost. However,...
Inverse Covariance Estimation with Structured Groups
RESEARCH PAPER / Aug 2017 / Machine/Deep Learning /AI
Estimating the inverse covariance matrix of p variables from n observations is challenging when n  p, since the sample covariance matrix is singular and cannot be inverted. A popular solution is to optimize for the `1 penalized estimator; however, this does not incorporate structure domain knowledge and can be...
Goal Directed Inductive Matrix Completion
RESEARCH PAPER / Aug 2017 / Machine/Deep Learning /AI
Matrix completion (MC) with additional information has found wide applicability in several machine learning applications. Among algorithms for solving such problems, Inductive Matrix Completion(IMC) has drawn a considerable amount of attention, not only for its well established theoretical guarantees but also for its superior performance in various real-world applications. However,...
Kernel square-loss exemplar machines for image retrieval
RESEARCH PAPER / Jul 2017 / Machine/Deep Learning/AI, Computer Vision
Zepeda and Perez [41] have recently demonstrated the promise of the exemplar SVM (ESVM) as a feature encoder for image retrieval. This paper extends this approach in several directions: We first show that replacing the hinge loss by the square loss in the ESVM cost function significantly reduces encoding time...
Real-time embodiment for omnidirectional videos
RESEARCH PAPER / Jul 2017 / Immersive/AR/VR/MR, Human Machine Interface
This paper investigates the role of the embodiment in an immersive video experience. A system allowing to play back omnidirectional videos enhanced with real-time 3D content is presented. It enables the user to be embodied in an avatar and to interact with 3D objects added to the video. A user...
DEEP LEARNING FOR MULTIMODAL-BASED VIDEO INTERESTINGNESS PREDICTION
RESEARCH PAPER / Jul 2017 / Machine/Deep Learning/AI, Image Processing
Predicting interestingness of media content remains an important, but challenging research subject. The difficulty comes first from the fact that, besides being a high-level semantic concept, interestingness is highly subjective and its global definition has not been agreed yet. This paper presents the use of up-to-date deep learning techniques for...
Video Style Transfer by Adaptive Patch Sampling
RESEARCH PAPER / Jun 2017 / Image Processing, Computer Vision, Machine/Deep Learning/ AI
This paper addresses the example-based stylization of videos. Style transfer aims at editing an image so that it matches the style of an example. This topic has recently been investigated massively, both in the industry and academia. The difficulty lies in how to capture the style of an image. For...
Accelerated Nearest Neighbor Search with Quick ADC
RESEARCH PAPER / Jun 2017 / Computing & Optimization, Machine/Deep Learning/AI
Efficient Nearest Neighbor (NN) search in high-dimensional spaces is a foundation of many multimedia retrieval systems. Because it offers low responses times, Product Quantization (PQ) is a popular solution. PQ compresses high-dimensional vectors into short codes using several sub-quantizers, which enables in-RAM storage of large databases. This allows fast answers...
Which saliency weighting for omni directional image quality assessment?
RESEARCH PAPER / May 2017 / Image processing, Human Machine Interface
With the explosion of Virtual Reality technologies, the production and usage of omni directional images (a.k.a 360 images) is presenting new challenges in the domains of compression, transmission and rendering. The evaluation of the quality of images generated by these technologies is therefore paramount. As the exploration of 360 images...
Prédiction de pannes DSL par mesure passive sur des passerelles domestiques
RESEARCH PAPER / May 2017 / Machine/Deep Learning/AI, Network & Communications
Les liens DSL peuvent subir des pannes sporadiques entraînant des deconnexions ou un acces Internet dégradé. Ces pannes sont a l’origine d’une expérience utilisateur négative et générent des coûts pour les fournisseurs d’accès Internet (FAI) via des appels d’assistance technique. La prediction de pannes permet aux FAI de mettre en...
La face topologique des recommandations
RESEARCH PAPER / May 2017 / Machine/Deep Learning/AI, Network & Communications
La recommandation joue un rôle central dans le e-commerce et dans l'industrie du divertissement. L'intérêt croissant pour la transparence algorithmique nous motive dans cet article à observer les résultats de recommandations sous la forme d'un graphe capturant les navigations proposées dans l'espace des items. Nous argumentons qu'une telle approche en...
Combining dimensionality reduction with random forests for multi-label classification under interactivity constraints
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...
Discrete Wasserstein GANs (Generative Adversarial Networks)
RESEARCH PAPER / Apr 2017 / Machine learning/ Deep learning /Artificial Intelligence
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...
Analysing elements of styles from annotated film clips
RESEARCH PAPER / Apr 2017 / Computer Graphics, Machine/Deep Learning/AI
This paper presents an open database of annotated film clips together with an analysis of elements of film style related to how the shots are composed, how the transitions are performed between shots and how the shots are sequenced to compose a film unit. The purpose is to initiate a...
Uncovering Influence Cookbooks : Reverse Engineering the Topological Impact in Peer Ranking Services
RESEARCH PAPER / Mar 2017 / Machine/Deep Learning/AI, Network & Communications
Ensuring the early detection of important social network users is a challenging task. Some peer ranking services are now well established, such as PeerIndex, Klout, or Kred. Their function is to rank users according to their influence. This notion of influence is however abstract, and the algorithms achieving this ranking...
Attention guidance for immersive video content in head-mounted displays
RESEARCH PAPER / Mar 2017 / Immersive/AR/VR/MR, Human Machine Interface
Immersive videos allow users to freely explore 4 π steradian scenes within head-mounted displays (HMD), leading to a strong feeling of immersion. However users may miss important elements of the narrative if not facing them. Hence, we propose four visual effects to guide the user's attention. After an informal pilot...
The Group k-Support Norm for Learning with Structured Sparsity
RESEARCH PAPER / Mar 2017 / Machine/Deep Learning/AI
Several high-dimensional learning applications require the parameters to satisfy a “group sparsity” constraint, where clusters of coefficients are required to be simultaneously selected or rejected. The group lasso and its variants are common methods to solve problems of this form. Recently, in the standard sparse setting, it has been noted...
Motion Informed Source Separation
RESEARCH PAPER / Mar 2017 / Audio Processing, Machine/Deep Learning/AI
In this paper we tackle the problem of single channel audio source separation driven by descriptors of the sounding object's motion. As opposed to previous approaches, motion is included as a soft-coupling constraint within the nonnegative matrix factorization framework. The proposed method is applied to a multimodal dataset of instruments...
INFRASTRUCTURE-LESS INDOOR LOCALIZATION USING LIGHT FINGERPRINTS
RESEARCH PAPER / Mar 2017 / Machine/Deep Learning/AI, IoT
An infrastructure-less indoor localization system is proposed based on fingerprints of light signals acquired at high frequencies. In contrast to other systems that modulate lights, the proposed system distinguishes lights by learning from training samples. Due to slight differences in the electronic components used in the construction of compact fluorescent...
INFORMED SOURCE SEPARATION BY COMPRESSIVE GRAPH SIGNAL SAMPLING
RESEARCH PAPER / Mar 2017 / Audio Processing, Machine/Deep Learning/AI
We propose a novel informed source separation method for audio object coding based on a recent sampling theory for smooth signals on graphs. Assuming that only one source is active at each time-frequency point, we compute an ideal map indicating which source is active at each time-frequency point at the...
Node Embedding for Network Community Detection
RESEARCH PAPER / Mar 2017 / Machine/Deep Learning/AI
Neural node embedding has been recently developed as a powerful representation for supervised tasks with graph data. We leverage this recent advance and propose a novel approach for unsupervised community discovery in graphs. Through extensive experimental studies on simulated and real-world data, we demonstrate consistent improvement of the proposed approach...
Noisy Tensor Completion for Tensors With a Sparse Canonical Polyadic Factor
RESEARCH PAPER / Feb 2017 / Image Processing, Machine/Deep Learning/AI
“To be considered for the 2017 IEEE Jack Keil Wolf ISIT Student Paper Award.” In this paper we study the problem of noisy tensor completion for tensors that admit a canonical polyadic or CANDE-COMP/PARAFAC (CP) decomposition with one of the factors being sparse. We present general theoretical error bounds for...
Structured sampling and fast reconstruction of smooth graph signals
RESEARCH PAPER / Feb 2017 / Image Processing, Computer Vision, Machine/Deep Learning/AI
This work concerns sampling of smooth signals on arbitrary graphs. We first study a structured sampling strategy for such smooth graph signals that consists of a random selection of few pre-defined groups of nodes. The number of groups to sample to stably embed the set of $k$-bandlimited signals is driven...
Predicting Interestingness of Visual Content
RESEARCH PAPER / Jan 2017 / Machine/Deep Learning/AI, Computer Vision
The ability of multimedia data to attract and keep people’s interest for longer periods of time is gaining more and more importance in the fields of information retrieval and recommendation, especially in the context of the ever growing market value of social media and advertising. In this chapter we introduce...
Time-Aware User Identification with Topic Models
RESEARCH PAPER / Dec 2016 / Machine/Deep Learning/AI, Network & Communications
Accounts are often shared by multiple users, each of them having different item consumption and temporal habits. Identifying of the active user can lead to improvements in a variety of services by switching from account personalized services to user personalized services. To do so, we develop a topic model extending...
Submatrix-constrained inverse covariance estimation
RESEARCH PAPER / Dec 2016 / Machine/Deep Learning/AI
We consider inverse covariance estimation with group sparsity. The groups areoverlapping principal submatrices, which may correspond to structural similarity(e.g. pixels in adjacent regions) or categories (e.g. voter party loyalties). Wepropose a scalable method that makes use of chordal decomposition and appliesthe Frank-Wolfe algorithm. For small simulated problems with block sparsity,...
Improved Coefficient Coding for Adaptive Transforms in HEVC
RESEARCH PAPER / Dec 2016 / Video Coding, Machine/Deep Learning/AI
Adaptive transform learning schemes have been extensively studied in the literature with a goal to achieve better compression efficiency compared to extensively used Discrete Cosine Transforms (DCT) inside a video codec. These transforms are learned offline on a large training set and are tested either in competition with or in...
Temporal Regularized Matrix Factorization for High-dimensional Time Series Prediction
RESEARCH PAPER / Nov 2016 / Machine/Deep Learning/AI
Time series prediction problems are becoming increasingly high-dimensional in modern applications, such as climatology and demand forecasting. For example, in the latter problem, the number of items for which demand needs to be forecast might be as large as 50,000. In addition, the data is generally noisy and full of...
Structured Sparse Regression via Greedy Hard Thresholding
RESEARCH PAPER / Nov 2016 / Machine/Deep Learning/AI
Several learning applications require solving high-dimensional regression problems where the relevant features belong to a small number of (overlapping) groups. For very large datasets and under standard sparsity constraints, hard thresholding methods have proven to be extremely efficient, but such methods require NP hard projections when dealing with overlapping groups....
Technicolor@MediaEval 2016 Predicting Media Interestingness Task
RESEARCH PAPER / Oct 2016 / Computer Vision, Machine/Deep Learning/AI
This paper presents the work done at Technicolor regardingthe MediaEval 2016 Predicting Media Interestingness Task,which aims at predicting the interestingness of individual im-ages and video segments extracted from Hollywood movies.We participated in both the image and video subtasks.
MediaEval 2016 Predicting Media Interestingness Task
RESEARCH PAPER / Oct 2016 / Computer Vision, Machine/Deep Learning/AI
This paper provides an overview of the Predicting MediaInterestingness task that is organized as part of the Media-Eval 2016 Benchmarking Initiative for Multimedia Evalua-tion. The task, which is running for the first year, expectsparticipants to create systems that automatically select images and video segments that are considered to be the...
Approximate search with quantized sparse representations
RESEARCH PAPER / Oct 2016 / Computer Vision, Machine/Deep Learning/AI
This paper tackles the task of storing a large collection of vectors, such as visual descriptors, and of searching in it. To this end, we propose to approximate database vectors by constrained sparse coding, where possible atom weights are restricted to belong to a finite subset. This formulation encompasses, as...
SPLeaP: Soft Pooling of Learned Parts for Image Classification
RESEARCH PAPER / Oct 2016 / Computer Vision, Machine/Deep Learning/AI
The aggregation of image statistics – the so-called pooling step of image classification algorithms – as well as the construction of part-based models, are two distinct and well-studied topics in the literature. The former aims at leveraging a whole set of local descriptors that an image can contain (through spatial...
Supervised Learning Of Low-Rank Transforms For Image Retrieval
RESEARCH PAPER / Sep 2016 / Image Processing, Computer Vision, Machine/Deep Learning/AI
In this paper we propose a new method to automatically select the rank of linear transforms during supervised learning. Our approach relies on a sparsity-enforcing element-wise soft-thresholding operation applied after the linear transform. This novel approach to supervised rank learning has the important advantage that it is very simple to...
Visual Parameters Impacting Reaction Times on Smartwatches
RESEARCH PAPER / Sep 2016 / Machine/Deep Learning/AI, IoT
As a new generation of smartwatches enters the market, one common use is for displaying information such as notifications. While some content might warrant immediately interrupting a user, there is also information that might be important to display yet less urgent. It would be useful to show this content on...
Just One More: Modeling Binge Watching Behavior
RESEARCH PAPER / Sep 2016 / Machine/Deep Learning/AI
Easy accessibility can often lead to over-consumption, as seen in food and alcohol habits. On video on-demand (VOD) services, this has recently been referred to as binge watching, where potentially entire seasons of TV shows are consumed in a single viewing session. While a user viewership model may reveal this...
On Learning High Dimensional Structured Single Index Models
RESEARCH PAPER / Sep 2016 / Machine/Deep Learning/AI
Single Index Models (SIMs) are simple yet flexible semi-parametric models for machine learning, where the response variable is modeled as a monotonic function of a linear combination of features. Estimation in this context requires learning both the feature weights and the nonlinear function that relates features to observations. While methods...
The CNN News Footage Dataset: Enabling Supervision in Image Retrieval
RESEARCH PAPER / Aug 2016 / Computer Vision, Machine/Deep Learning/AI
Image retrieval in large image databases is an important problem that drives a number of applications. Yet the use of supervised approaches that address this problem has been limited due to the lack of large labeled datasets for training. Hence, in this paper we introduce two new datasets composed of...
Predicting the effect of home Wi-Fi on Web QoE
RESEARCH PAPER / Aug 2016 / Wireless Communications, Machine/Deep Learning/AI
Wi-Fi is the preferred way of accessing the Internet for many devices at home, but it is vulnerable to performance problems. The analysis of Wi-Fi quality metrics such as RSSI or PHY rate may indicate a number of problems, but users may not notice many of these problems if they...
Introducing Basic Principles of Haptic Cinematography Editing
RESEARCH PAPER / Jul 2016 / Immersive/AR/VR/MR, Haptics, Human Machine Interface
Adding the sense of touch to hearing and seeing would be necessary for a true immersive experience. This is the promise of the growing "4D-cinema" based on motion platforms and others sensory effects (water spray, wind, scent, etc.). Touch provides a new dimension for filmmakers and leads to a new...
Non-parametric clustering over user features and latent behavioral functions with dual-view mixture models
RESEARCH PAPER / Jul 2016 / Machine/Deep Learning/AI
We present a dual-view mixture model to cluster users based on their features and latent behavioral functions. Every component of the mixture model represents a probability density over a feature view for observed user attributes and a behavior view for latent behavioral functions that are indirectly observed through user actions...
Retro-ingénierer les métriques topologiques dans les algorithmes de peer-ranking
RESEARCH PAPER / May 2016 / Machine/Deep Learning/AI, Network & Communications
Détecter au plus tôt les utilisateurs importants dans les réseaux sociaux est un problème majeur. Les services de classement d'utilisateurs (peer ranking) sont maintenant des outils bien établis, par des sociétés comme PeerIndex, Klout ou Kred. Leur fonction est de ``classer'' les utilisateurs selon leur influence. Cette notion est néanmoins...
Big Social Data Analytics in Journalism and Mass Communication: Comparing Dictionary-based Text Analysis and Unsupervised Topic Modeling
RESEARCH PAPER / Apr 2016 / Machine/Deep Learning/AI
This article presents an empirical study that investigated and compared two “big data” text analysis methods: dictionary-based analysis, perhaps the most popular automated analysis approach in social science research, and unsupervised topic modeling (i.e., Latent Dirichlet Allocation [LDA] analysis), one of the most widely used algorithms in the field of...
Extrafoveal Video Extension for an Immersive Viewing Experience
RESEARCH PAPER / Mar 2016 / Immersive/AR/VR/MR, Human Machine Interface
Between the recent popularity of virtual reality (VR) and the development of 3D, immersion has become an integral part of entertainment concepts. Head-mounted Display (HMD) devices are often used to afford users a feeling of immersion in the environment. Another technique is to project additional material surrounding the viewer, as...
Experiencing the interestingness concept within and between pictures
RESEARCH PAPER / Feb 2016 / Computer Vision, Machine/Deep Learning/AI
Interestingness is the quantification of the ability of an imageto induce interest in a user. Because defining and interpretinginterestingness remain unclear in the literature, we introduce inthis paper two new notions, intra- and inter-interestingness, andinvestigate a novel set of dedicated experiments.More specifically, we propose four experimental protocols:1/ object ranking with...
InterDigital and Applied Communication Sciences Engineers Awarded Best Papers at EMERGING 2016
BLOG / Dec 2016 / Machine Learning / Posted By: Kelly Capizzi
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...

ready to
learn more?

CONTACT INVESTORS
RESEARCH & INNOVATION
  • Overview
  • Wireless Lab
  • Video Lab
  • Emerging Technologies Lab
  • Talent
THOUGHT LEADERSHIP
  • Vault
  • Blog
  • Creators
ABOUT US
  • Overview
  • Leadership
  • History
  • Licensing
  • Contact
  • Government Solutions
  • Careers
  • Media
  • LinkedIn
  • Twitter
InterDigital logo in white

   © COPYRIGHT 2023 INTERDIGITAL, INC. ALL RIGHTS RESERVED.

  • Privacy Policy
  • Forward Looking Statements
  • Legal Notices
  • Research & Innovation
    • Overview
    • Wireless Lab
    • Video Lab
    • Emerging Technologies Lab
    • Talent
  • Thought Leadership
    • Vault
    • Sustainability
    • Blog
    • Creators
  • About Us
    • Overview
    • Leadership
    • History
    • Licensing
    • Contact
    • Government Solutions
    • Careers
    • Media
  • Investors
    • Investor Relations
    • ESG / SUSTAINABILITY
  • Search