Search Results for author:
Found 49 papers, 17 papers with code
Adaptive-Rate Sparse Signal Reconstruction With Application in Compressive Background Subtraction
We propose and analyze an online algorithm for reconstructing a sequence of signals from a limited number of linear measurements.
NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks
Current NLE models explain the decision-making process of a vision or vision-language model (a. k. a., task model), e. g., a VQA model, via a language model (a. k. a., explanation model), e. g., GPT.
Uni-NLX: Unifying Textual Explanations for Vision and Vision-Language Tasks
In this work, we propose Uni-NLX, a unified framework that consolidates all NLE tasks into a single and compact multi-task model using a unified training objective of text generation.
Bias Loss for Mobile Neural Networks
In compact CNNs, due to the limited number of parameters, abundant features are unlikely to be obtained, and feature diversity becomes an essential characteristic.
Ranked #816 on
Image Classification
on ImageNet
Gradient Variance Loss for Structure-Enhanced Image Super-Resolution
Further, we minimize the distance between the computed variance maps to enforce the model to produce high variance gradient maps that will lead to the generation of high-resolution images with sharper edges.
Deep Learning Sparse Ternary Projections for Compressed Sensing of Images
Compressed sensing (CS) is a sampling theory that allows reconstruction of sparse (or compressible) signals from an incomplete number of measurements, using of a sensing mechanism implemented by an appropriate projection matrix.
Compressed Sensing With Side Information: Geometrical Interpretation and Performance Bounds
We address the problem of Compressed Sensing (CS) with side information.
Compressed Sensing with Prior Information: Optimal Strategies, Geometry, and Bounds
Our bounds and geometrical interpretations reveal that if the prior information has good enough quality, L1-L1 minimization improves the performance of CS dramatically.
Information Theory Information Theory
The STOIC2021 COVID-19 AI challenge: applying reusable training methodologies to private data
STOIC2021 consisted of a Qualification phase, where participants developed challenge solutions using 2000 publicly available CT scans, and a Final phase, where participants submitted their training methodologies with which solutions were trained on CT scans of 9724 subjects.
Multimodal Image Super-resolution via Joint Sparse Representations induced by Coupled Dictionaries
This paper proposes a new approach to construct a high-resolution (HR) version of a low-resolution (LR) image given another HR image modality as reference, based on joint sparse representations induced by coupled dictionaries.
Incorporating Prior Information in Compressive Online Robust Principal Component Analysis
In addition, we apply the proposed algorithm to online video foreground and background separation from compressive measurements.
Holistic Representation Learning for Multitask Trajectory Anomaly Detection
We encode temporally occluded trajectories, jointly learn latent representations of the occluded segments, and reconstruct trajectories based on expected motions across different temporal segments.
Ranked #1 on
Video Anomaly Detection
on UBnormal
Designing recurrent neural networks by unfolding an l1-l1 minimization algorithm
We propose a new deep recurrent neural network (RNN) architecture for sequential signal reconstruction.
Leaping Into Memories: Space-Time Deep Feature Synthesis
The success of deep learning models has led to their adaptation and adoption by prominent video understanding methods.
A Review on Fact Extraction and Verification
We study the fact checking problem, which aims to identify the veracity of a given claim.
Understanding the Impact of Evidence-Aware Sentence Selection for Fact Checking
Fact Extraction and VERification (FEVER) is a recently introduced task that consists of the following subtasks (i) document retrieval, (ii) sentence retrieval, and (iii) claim verification.
Visualizing and Understanding Contrastive Learning
Contrastive learning has revolutionized the field of computer vision, learning rich representations from unlabeled data, which generalize well to diverse vision tasks.
Extendable Neural Matrix Completion
Matrix completion is one of the key problems in signal processing and machine learning, with applications ranging from image pro- cessing and data gathering to classification and recommender sys- tems.
Twitter User Geolocation using Deep Multiview Learning
Predicting the geographical location of users on social networks like Twitter is an active research topic with plenty of methods proposed so far.
Online Decomposition of Compressive Streaming Data Using $n$-$\ell_1$ Cluster-Weighted Minimization
The proposed decomposition solves an $n$-$\ell_1$ cluster-weighted minimization to decompose a sequence of frames (or vectors), into sparse and low-rank components, from compressive measurements.
Multiview Deep Learning for Predicting Twitter Users' Location
In the context of Twitter user geolocation, we realize MENET with textual, network, and metadata features.
Measurement Bounds for Sparse Signal Reconstruction with Multiple Side Information
To address this problem, we theoretically study a generic \textcolor{black}{weighted $n$-$\ell_{1}$ minimization} framework and propose a reconstruction algorithm that leverages multiple side information signals (RAMSI).
Distributed Coding of Multiview Sparse Sources with Joint Recovery
In support of applications involving multiview sources in distributed object recognition using lightweight cameras, we propose a new method for the distributed coding of sparse sources as visual descriptor histograms extracted from multiview images.
Multi-modal dictionary learning for image separation with application in art investigation
Our dictionary learning framework can be tailored both to a single- and a multi-scale framework, with the latter leading to a significant performance improvement.
X-ray image separation via coupled dictionary learning
In support of art investigation, we propose a new source sepa- ration method that unmixes a single X-ray scan acquired from double-sided paintings.
Vectors of Locally Aggregated Centers for Compact Video Representation
We create vectors of locally aggregated centers (VLAC) by first clustering SIFT features to obtain local feature centers (LFCs) and then encoding the latter with respect to given centers of local feature centers (CLFCs), extracted from a training set.
Regularizing Autoencoder-Based Matrix Completion Models via Manifold Learning
Specifically, we propose an autoencoder-based matrix completion model that performs prediction of the unknown matrix values as a main task, and manifold learning as an auxiliary task.
Matrix Completion With Variational Graph Autoencoders: Application in Hyperlocal Air Quality Inference
Existing inference methods typically use low spatial resolution data collected by fixed monitoring stations and infer the concentration of air pollutants using additional types of data, e. g., meteorological and traffic information.
Matrix Factorization via Deep Learning
Matrix completion is one of the key problems in signal processing and machine learning.
Geometric Matrix Completion with Deep Conditional Random Fields
We consider matrix completion as a structured prediction problem in a conditional random field (CRF), which is characterized by a maximum a posterior (MAP) inference, and we propose a deep model that predicts the missing entries by solving the MAP inference problem.
Rumour Detection via News Propagation Dynamics and User Representation Learning
Many methods have been introduced to detect rumours using the content or the social context of news.
Fake News Detection using Deep Markov Random Fields
While the correlations among news articles have been shown to be effective cues for online news analysis, existing deep-learning-based methods often ignore this information and only consider each news article individually.
Deep Coupled-Representation Learning for Sparse Linear Inverse Problems with Side Information
In linear inverse problems, the goal is to recover a target signal from undersampled, incomplete or noisy linear measurements.
Multimodal Image Super-resolution via Deep Unfolding with Side Information
Deep learning methods have been successfully applied to various computer vision tasks.
DeepFPC: Deep Unfolding of a Fixed-Point Continuation Algorithm for Sparse Signal Recovery from Quantized Measurements
We present DeepFPC, a novel deep neural network designed by unfolding the iterations of the fixed-point continuation algorithm with one-sided l1-norm (FPC-l1), which has been proposed for solving the 1-bit compressed sensing problem.
Multimodal Deep Unfolding for Guided Image Super-Resolution
The deep unfolding architecture is used as a core component of a multimodal framework for guided image super-resolution.
Interpretable Deep Recurrent Neural Networks via Unfolding Reweighted $\ell_1$-$\ell_1$ Minimization: Architecture Design and Generalization Analysis
In this line of research, this paper develops a novel deep recurrent neural network (coined reweighted-RNN) by the unfolding of a reweighted $\ell_1$-$\ell_1$ minimization algorithm and applies it to the task of sequential signal reconstruction.
Graph Convolutional Neural Networks with Node Transition Probability-based Message Passing and DropNode Regularization
Among the existing GCNNs, many methods can be viewed as instances of a neural message passing motif; features of nodes are passed around their neighbors, aggregated and transformed to produce better nodes' representations.
Interpretable Deep Multimodal Image Super-Resolution
Multimodal image super-resolution (SR) is the reconstruction of a high resolution image given a low-resolution observation with the aid of another image modality.
A Deep-Unfolded Reference-Based RPCA Network For Video Foreground-Background Separation
This paper proposes a new deep-unfolding-based network design for the problem of Robust Principal Component Analysis (RPCA) with application to video foreground-background separation.
Temporal Collaborative Filtering with Graph Convolutional Neural Networks
Motivated by this, we propose a novel TCF method that leverages GNNs to learn user and item representations, and RNNs to model their temporal dynamics.
Explainable-by-design Semi-Supervised Representation Learning for COVID-19 Diagnosis from CT Imaging
Our motivating application is a real-world problem: COVID-19 classification from CT imaging, for which we present an explainable Deep Learning approach based on a semi-supervised classification pipeline that employs variational autoencoders to extract efficient feature embedding.
Learned Gradient Compression for Distributed Deep Learning
In contrast, we advocate that the gradients across the nodes are correlated and propose methods to leverage this inter-node redundancy to improve compression efficiency.
Traffic Event Detection as a Slot Filling Problem
In particular, we experiment with several models to identify (i) whether a tweet is traffic-related or not, and (ii) in the case that the tweet is traffic-related to identify more fine-grained information regarding the event (e. g., the type of the event, where the event happened).
imec-ETRO-VUB at W-NUT 2020 Shared Task-3: A multilabel BERT-based system for predicting COVID-19 events
To mitigate the noisy nature of the Twitter stream, our system makes use of the COVID-Twitter-BERT (CT-BERT), which is a language model pre-trained on a large corpus of COVID-19 related Twitter messages.
A Deep Recurrent Neural Network via Unfolding Reweighted l1-l1 Minimization
In this line of research, this paper develops a novel deep recurrent neural network (coined reweighted-RNN) by unfolding a reweighted l1-l1 minimization algorithm and applies it to the task of sequential signal reconstruction.
Representation Learning with Information Theory for COVID-19 Detection
Successful data representation is a fundamental factor in machine learning based medical imaging analysis.
Entropy-Based Feature Extraction For Real-Time Semantic Segmentation
Patches with high entropy are being processed by the encoder with the largest number of parameters, patches with moderate entropy are processed by the encoder with a moderate number of parameters, and patches with low entropy are processed by the smallest encoder.
Learned layered coding for Successive Refinement in the Wyner-Ziv Problem
We propose a data-driven approach to explicitly learn the progressive encoding of a continuous source, which is successively decoded with increasing levels of quality and with the aid of correlated side information.
