arXiv subjects

Mohamed Elhoseiny

Publications and source records attributed to Mohamed Elhoseiny.

139 records · Page 8Linked to original sources

arXiv2017

CAN: Creative Adversarial Networks, Generating "Art" by Learning About Styles and Deviating from Style Norms

We propose a new system for generating art. The system generates art by looking at art and learning about style; and becomes creative by increasing the arousal potential of the generated art by deviating from the learned styles. We build over Generative Adversarial Networks (GAN), which have shown the ability to learn to generate novel images simulating a given distribution. We argue that such networks are limited in their ability to generate creative products in their original design. We propose modifications to its objective to make it capable of generating creative art by maximizing deviation from established styles and minimizing deviation from art distribution. We conducted experiments to compare the response of human subjects to the generated art with their response to art created by artists. The results show that human subjects could not distinguish art generated by the proposed system from art generated by contemporary artists and shown in top art fairs. Human subjects even rated the generated images higher on various scales.

cs.AI↗

arXiv2017

Overlapping Cover Local Regression Machines

We present the Overlapping Domain Cover (ODC) notion for kernel machines, as a set of overlapping subsets of the data that covers the entire training set and optimized to be spatially cohesive as possible. We show how this notion benefit the speed of local kernel machines for regression in terms of both speed while achieving while minimizing the prediction error. We propose an efficient ODC framework, which is applicable to various regression models and in particular reduces the complexity of Twin Gaussian Processes (TGP) regression from cubic to quadratic. Our notion is also applicable to several kernel methods (e.g., Gaussian Process Regression(GPR) and IWTGP regression, as shown in our experiments). We also theoretically justified the idea behind our method to improve local prediction by the overlapping cover. We validated and analyzed our method on three benchmark human pose estimation datasets and interesting findings are discussed.

cs.LG↗

arXiv2016

Write a Classifier: Predicting Visual Classifiers from Unstructured Text

People typically learn through exposure to visual concepts associated with linguistic descriptions. For instance, teaching visual object categories to children is often accompanied by descriptions in text or speech. In a machine learning context, these observations motivates us to ask whether this learning process could be computationally modeled to learn visual classifiers. More specifically, the main question of this work is how to utilize purely textual description of visual classes with no training images, to learn explicit visual classifiers for them. We propose and investigate two baseline formulations, based on regression and domain transfer, that predict a linear classifier. Then, we propose a new constrained optimization formulation that combines a regression function and a knowledge transfer function with additional constraints to predict the parameters of a linear classifier. We also propose a generic kernelized models where a kernel classifier is predicted in the form defined by the representer theorem. The kernelized models allow defining and utilizing any two RKHS (Reproducing Kernel Hilbert Space) kernel functions in the visual space and text space, respectively. We finally propose a kernel function between unstructured text descriptions that builds on distributional semantics, which shows an advantage in our setting and could be useful for other applications. We applied all the studied models to predict visual classifiers on two fine-grained and challenging categorization datasets (CU Birds and Flower Datasets), and the results indicate successful predictions of our final model over several baselines that we designed.

cs.CV↗

arXiv2016

Digging Deep into the layers of CNNs: In Search of How CNNs Achieve View Invariance

This paper is focused on studying the view-manifold structure in the feature spaces implied by the different layers of Convolutional Neural Networks (CNN). There are several questions that this paper aims to answer: Does the learned CNN representation achieve viewpoint invariance? How does it achieve viewpoint invariance? Is it achieved by collapsing the view manifolds, or separating them while preserving them? At which layer is view invariance achieved? How can the structure of the view manifold at each layer of a deep convolutional neural network be quantified experimentally? How does fine-tuning of a pre-trained CNN on a multi-view dataset affect the representation at each layer of the network? In order to answer these questions we propose a methodology to quantify the deformation and degeneracy of view manifolds in CNN layers. We apply this methodology and report interesting results in this paper that answer the aforementioned questions.

cs.CV↗

arXiv2016

Convolutional Models for Joint Object Categorization and Pose Estimation

In the task of Object Recognition, there exists a dichotomy between the categorization of objects and estimating object pose, where the former necessitates a view-invariant representation, while the latter requires a representation capable of capturing pose information over different categories of objects. With the rise of deep architectures, the prime focus has been on object category recognition. Deep learning methods have achieved wide success in this task. In contrast, object pose regression using these approaches has received relatively much less attention. In this paper we show how deep architectures, specifically Convolutional Neural Networks (CNN), can be adapted to the task of simultaneous categorization and pose estimation of objects. We investigate and analyze the layers of various CNN models and extensively compare between them with the goal of discovering how the layers of distributed representations of CNNs represent object pose information and how this contradicts with object category representations. We extensively experiment on two recent large and challenging multi-view datasets. Our models achieve better than state-of-the-art performance on both datasets.

cs.CV↗

arXiv2016

Automatic Annotation of Structured Facts in Images

Motivated by the application of fact-level image understanding, we present an automatic method for data collection of structured visual facts from images with captions. Example structured facts include attributed objects (e.g., ), actions (e.g., ), interactions (e.g., ), and positional information (e.g., ). The collected annotations are in the form of fact-image pairs (e.g., and an image region containing this fact). With a language approach, the proposed method is able to collect hundreds of thousands of visual fact annotations with accuracy of 83% according to human judgment. Our method automatically collected more than 380,000 visual fact annotations and more than 110,000 unique visual facts from images with captions and localized them in images in less than one day of processing time on standard CPU platforms.

cs.CL↗

arXiv2016

Sherlock: Scalable Fact Learning in Images

We study scalable and uniform understanding of facts in images. Existing visual recognition systems are typically modeled differently for each fact type such as objects, actions, and interactions. We propose a setting where all these facts can be modeled simultaneously with a capacity to understand unbounded number of facts in a structured way. The training data comes as structured facts in images, including (1) objects (e.g., $<$boy$>$), (2) attributes (e.g., $<$boy, tall$>$), (3) actions (e.g., $<$boy, playing$>$), and (4) interactions (e.g., $<$boy, riding, a horse $>$). Each fact has a semantic language view (e.g., $<$ boy, playing$>$) and a visual view (an image with this fact). We show that learning visual facts in a structured way enables not only a uniform but also generalizable visual understanding. We propose and investigate recent and strong approaches from the multiview learning literature and also introduce two learning representation models as potential baselines. We applied the investigated methods on several datasets that we augmented with structured facts and a large scale dataset of more than 202,000 facts and 814,000 images. Our experiments show the advantage of relating facts by the structure by the proposed models compared to the designed baselines on bidirectional fact retrieval.

cs.CV↗

arXiv2015

Zero-Shot Event Detection by Multimodal Distributional Semantic Embedding of Videos

We propose a new zero-shot Event Detection method by Multi-modal Distributional Semantic embedding of videos. Our model embeds object and action concepts as well as other available modalities from videos into a distributional semantic space. To our knowledge, this is the first Zero-Shot event detection model that is built on top of distributional semantics and extends it in the following directions: (a) semantic embedding of multimodal information in videos (with focus on the visual modalities), (b) automatically determining relevance of concepts/attributes to a free text query, which could be useful for other applications, and (c) retrieving videos by free text event query (e.g., "changing a vehicle tire") based on their content. We embed videos into a distributional semantic space and then measure the similarity between videos and the event query in a free text form. We validated our method on the large TRECVID MED (Multimedia Event Detection) challenge. Using only the event title as a query, our method outperformed the state-of-the-art that uses big descriptions from 12.6% to 13.5% with MAP metric and 0.73 to 0.83 with ROC-AUC metric. It is also an order of magnitude faster.

cs.CV↗

arXiv2015

Tell and Predict: Kernel Classifier Prediction for Unseen Visual Classes from Unstructured Text Descriptions

In this paper we propose a framework for predicting kernelized classifiers in the visual domain for categories with no training images where the knowledge comes from textual description about these categories. Through our optimization framework, the proposed approach is capable of embedding the class-level knowledge from the text domain as kernel classifiers in the visual domain. We also proposed a distributional semantic kernel between text descriptions which is shown to be effective in our setting. The proposed framework is not restricted to textual descriptions, and can also be applied to other forms knowledge representations. Our approach was applied for the challenging task of zero-shot learning of fine-grained categories from text descriptions of these categories.

cs.CV↗

arXiv2015

Generalized Twin Gaussian Processes using Sharma-Mittal Divergence

There has been a growing interest in mutual information measures due to their wide range of applications in Machine Learning and Computer Vision. In this paper, we present a generalized structured regression framework based on Shama-Mittal divergence, a relative entropy measure, which is introduced to the Machine Learning community in this work. Sharma-Mittal (SM) divergence is a generalized mutual information measure for the widely used Rényi, Tsallis, Bhattacharyya, and Kullback-Leibler (KL) relative entropies. Specifically, we study Sharma-Mittal divergence as a cost function in the context of the Twin Gaussian Processes (TGP)~\citep{Bo:2010}, which generalizes over the KL-divergence without computational penalty. We show interesting properties of Sharma-Mittal TGP (SMTGP) through a theoretical analysis, which covers missing insights in the traditional TGP formulation. However, we generalize this theory based on SM-divergence instead of KL-divergence which is a special case. Experimentally, we evaluated the proposed SMTGP framework on several datasets. The results show that SMTGP reaches better predictions than KL-based TGP, since it offers a bigger class of models through its parameters that we learn from the data.

cs.LG↗

arXiv2015

Learning Hypergraph-regularized Attribute Predictors

We present a novel attribute learning framework named Hypergraph-based Attribute Predictor (HAP). In HAP, a hypergraph is leveraged to depict the attribute relations in the data. Then the attribute prediction problem is casted as a regularized hypergraph cut problem in which HAP jointly learns a collection of attribute projections from the feature space to a hypergraph embedding space aligned with the attribute space. The learned projections directly act as attribute classifiers (linear and kernelized). This formulation leads to a very efficient approach. By considering our model as a multi-graph cut task, our framework can flexibly incorporate other available information, in particular class label. We apply our approach to attribute prediction, Zero-shot and $N$-shot learning tasks. The results on AWA, USAA and CUB databases demonstrate the value of our methods in comparison with the state-of-the-art approaches.

cs.CV↗

arXiv2014

Text to Multi-level MindMaps: A Novel Method for Hierarchical Visual Abstraction of Natural Language Text

MindMapping is a well-known technique used in note taking, which encourages learning and studying. MindMapping has been manually adopted to help present knowledge and concepts in a visual form. Unfortunately, there is no reliable automated approach to generate MindMaps from Natural Language text. This work firstly introduces MindMap Multilevel Visualization concept which is to jointly visualize and summarize textual information. The visualization is achieved pictorially across multiple levels using semantic information (i.e. ontology), while the summarization is achieved by the information in the highest levels as they represent abstract information in the text. This work also presents the first automated approach that takes a text input and generates a MindMap visualization out of it. The approach could visualize text documents in multilevel MindMaps, in which a high-level MindMap node could be expanded into child MindMaps. \ignore{ As far as we know, this is the first work that view MindMapping as a new approach to jointly summarize and visualize textual information.} The proposed method involves understanding of the input text and converting it into intermediate Detailed Meaning Representation (DMR). The DMR is then visualized with two modes; Single level or Multiple levels, which is convenient for larger text. The generated MindMaps from both approaches were evaluated based on Human Subject experiments performed on Amazon Mechanical Turk with various parameter settings.

cs.CL↗

arXiv2013

GPU-Framework for Teamwork Action Recognition

Real time processing for teamwork action recognition is a challenge, due to complex computational models to achieve high system performance. Hence, this paper proposes a framework based on Graphical Processing Units (GPUs) to achieve a significant speed up in the performance of role based activity recognition of teamwork. The framework can be applied in various fields, especially athletic and military applications. Furthermore, the framework can be customized for many action recognition applications. The paper presents the stages of the framework where GPUs are the main tool for performance improvement. The speedup is achieved by performing video processing and Machine learning algorithms on GPU. Video processing and machine learning algorithms covers all computations involved in our framework. Video processing tasks on involves GPU implementation of Motion detection, segmentation and object tracking algorithms. In addition, our framework is integrated with GPUCV, a GPU version of OpenCV functions. Machine learning tasks are supported under our framework with GPU implementations of Support Vector Machine (SVM) for object classification and feature discretization, Hidden Marcov Model (HMM) for activity recognition phase, and ID3 algorithm for role recognition of team members. The system was tested against UC-Teamwork dataset and speedup of 20X has been achieved on NVidia 9500GT graphics card (32 500MHZ processors).

cs.DC↗