Search Results for author:
Found 42 papers, 9 papers with code
Multiple Random Masking Autoencoder Ensembles for Robust Multimodal Semi-supervised Learning
There is an increasing number of real-world problems in computer vision and machine learning requiring to take into consideration multiple interpretation layers (modalities or views) of the world and learn how they relate to each other.
Maia: A Real-time Non-Verbal Chat for Human-AI Interaction
Our goal is to track and analyze facial expressions, and other non-verbal cues in real-time, and use this information to build models that can predict and understand human behavior.
Explaining Vision and Language through Graphs of Events in Space and Time
Artificial Intelligence makes great advances today and starts to bridge the gap between vision and language.
Multi-Task Hypergraphs for Semi-supervised Learning using Earth Observations
There are many ways of interpreting the world and they are highly interdependent.
Self-supervised Hypergraphs for Learning Multiple World Interpretations
Thus, each node could be an input node in some hyperedges and an output node in others.
JEDI: Joint Expert Distillation in a Semi-Supervised Multi-Dataset Student-Teacher Scenario for Video Action Recognition
We propose JEDI, a multi-dataset semi-supervised learning method, which efficiently combines knowledge from multiple experts, learned on different datasets, to train and improve the performance of individual, per dataset, student models.
Self-supervised novel 2D view synthesis of large-scale scenes with efficient multi-scale voxel carving
First, we manage to stay anchored in the real 3D world, by introducing an efficient multi-scale voxel carving method, which is able to accommodate significant noises in pose, depth, and illumination variations, while being able to reconstruct the view of the world from drastically different poses at test time.
GEST: the Graph of Events in Space and Time as a Common Representation between Vision and Language
GEST alows us to measure the similarity between texts and videos in a semantic and fully explainable way, through graph matching.
Anatomically aware dual-hop learning for pulmonary embolism detection in CT pulmonary angiograms
Pulmonary Embolisms (PE) represent a leading cause of cardiovascular death.
Learning a Fast 3D Spectral Approach to Object Segmentation and Tracking over Space and Time
Our motivation for a spectral space-time clustering approach, unique in video semantic segmentation literature, is that such clustering is dedicated to preserving object consistency over time, which we evaluate using our novel segmentation consistency measure.
TEACHTEXT: CrossModal Generalized Distillation for Text-Video Retrieval
In recent years, considerable progress on the task of text-video retrieval has been achieved by leveraging large-scale pretraining on visual and audio datasets to construct powerful video encoders.
Self-Supervised Learning in Multi-Task Graphs through Iterative Consensus Shift
The human ability to synchronize the feedback from all their senses inspired recent works in multi-task and multi-modal learning.
Iterative Knowledge Exchange Between Deep Learning and Space-Time Spectral Clustering for Unsupervised Segmentation in Videos
A novel spectral space-time clustering process on the graph produces unsupervised segmentation masks passed to the network as pseudo-labels.
A hierarchical approach to vision-based language generation: from simple sentences to complex natural language
Automatically describing videos in natural language is an ambitious problem, which could bridge our understanding of vision and language.
Semantics through Time: Semi-supervised Segmentation of Aerial Videos with Iterative Label Propagation
Motivated by the lack of a large video aerial dataset, we also introduce Ruralscapes, a new dataset with high resolution (4K) images and manually-annotated dense labels every 50 frames - the largest of its kind, to the best of our knowledge.
Semi-Supervised Learning for Multi-Task Scene Understanding by Neural Graph Consensus
The unsupervised learning process is repeated over several generations, in which each edge becomes a "student" and also part of different ensemble "teachers" for training other students.
Discovering Dynamic Salient Regions for Spatio-Temporal Graph Neural Networks
Graph Neural Networks are perfectly suited to capture latent interactions between various entities in the spatio-temporal domain (e. g. videos).
A regime switching on Covid19 analysis and prediction in Romania
The second issue is that there were many factors which affected the evolution of the pandemic.
A self-supervised neural-analytic method to predict the evolution of COVID-19 in Romania
More specifically, we want to statistically estimate all the relevant parameters for the new coronavirus COVID-19, such as the reproduction number, fatality rate or length of infectiousness period, based on Romanian patients, as well as be able to predict future outcomes.
In Search of Life: Learning from Synthetic Data to Detect Vital Signs in Videos
Moreover, our system, which is trained in a purely automatic manner and needs no human annotation, also learns to predict the respiration or heart intensity signal for each moment in time and to detect the region of interest that is most relevant for the given task, e. g. the nose area in the case of respiration.
Towards Automatic Annotation for Semantic Segmentation in Drone Videos
Semantic segmentation is a crucial task for robot navigation and safety.
Image Difficulty Curriculum for Generative Adversarial Networks (CuGAN)
All strategies are first based on ranking the training images by their difficulty scores, which are estimated by a state-of-the-art image difficulty predictor.
Ranked #108 on
Image Generation
on CIFAR-10
Learning Navigation by Visual Localization and Trajectory Prediction
Our system learns to predict in real-time vehicle's current location and future trajectory, as a function of time, on a known map, given only the raw video stream and the intended destination.
Spacetime Graph Optimization for Video Object Segmentation
While the actual matrix is not computed explicitly, the proposed algorithm efficiently computes, in a few iteration steps, the principal eigenvector that captures the segmentation of the main object in the video.
A 3D Convolutional Approach to Spectral Object Segmentation in Space and Time
Our method is based on the power iteration for finding the principal eigenvector of a matrix, which we prove is equivalent to performing a specific set of 3D convolutions in the space-time feature volume.
Ranked #45 on
Semi-Supervised Video Object Segmentation
on DAVIS 2016
(Jaccard (Mean) metric)
Shift R-CNN: Deep Monocular 3D Object Detection with Closed-Form Geometric Constraints
We propose Shift R-CNN, a hybrid model for monocular 3D object detection, which combines deep learning with the power of geometry.
Recurrent Space-time Graph Neural Networks
Our model is general and could learn to recognize a variety of high level spatio-temporal concepts and be applied to different learning tasks.
Ranked #58 on
Action Recognition
on Something-Something V1
(using extra training data)
Unsupervised learning of foreground object detection
We train a student deep network to predict the output of a teacher pathway that performs unsupervised object discovery in videos or large image collections.
Mining for meaning: from vision to language through multiple networks consensus
Here we propose an approach to describe videos in natural language by reaching a consensus among multiple encoder-decoder networks.
Learning a Robust Society of Tracking Parts using Co-occurrence Constraints
We address this challenge by proposing a deep neural network composed of different parts, which functions as a society of tracking parts.
A Multi-Stage Multi-Task Neural Network for Aerial Scene Interpretation and Geolocalization
The first stage of our network predicts pixelwise class labels, while the second stage provides a precise location using two branches.
Learning a Robust Society of Tracking Parts
They are classifiers that respond at different scales and locations.
How hard can it be? Estimating the difficulty of visual search in an image
We address the problem of estimating image difficulty defined as the human response time for solving a visual search task.
Unsupervised object segmentation in video by efficient selection of highly probable positive features
We also present theoretical properties of our unsupervised learning method, that under some mild constraints is guaranteed to learn a correct discriminative classifier even in the unsupervised case.
Unsupervised learning from video to detect foreground objects in single images
Our approach is different from the published literature that performs unsupervised discovery in videos or in collections of images at test time.
Aerial image geolocalization from recognition and matching of roads and intersections
We offer a complete pipeline for geolocalization, from the detection of roads and intersections, to the identification of the enclosing geographic region by matching detected intersections to previously learned manually labeled ones, followed by accurate geometric alignment between the detected roads and the manually labeled maps.
Dual Local-Global Contextual Pathways for Recognition in Aerial Imagery
Our model learns to combine local object appearance as well as information from the larger scene at the same time and in a complementary way, such that together they form a powerful classifier.
Labeling the Features Not the Samples: Efficient Video Classification with Minimal Supervision
Our method works both as a feature selection mechanism and as a fully competitive classifier.
Stories in the Eye: Contextual Visual Interactions for Efficient Video to Language Translation
Integrating higher level visual and linguistic interpretations is at the heart of human intelligence.
Features in Concert: Discriminative Feature Selection meets Unsupervised Clustering
Feature selection is an essential problem in computer vision, important for category learning and recognition.
Thoughts on a Recursive Classifier Graph: a Multiclass Network for Deep Object Recognition
In this manner we can learn and grow both a deep, complex graph of classifiers and a rich pool of features at different levels of abstraction and interpretation.
An Integer Projected Fixed Point Method for Graph Matching and MAP Inference
When applied to MAP inference, the algorithm is a parallel extension of Iterated Conditional Modes (ICM) with climbing and convergence properties that make it a compelling alternative to the sequential ICM.
