Mohamed Elhoseiny

Mohamed Elhoseiny
King Abdullah University of Science and Technology | KAUST · Department of Computer Science

PhD, MSc, MSc
Hiring students, and Postdocs at KAUST

About

98
Publications
45,026
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
2,498
Citations
Additional affiliations
December 2016 - present
Meta
Position
  • PostDoc Position
September 2011 - October 2016
Rutgers, The State University of New Jersey
Position
  • PhD Student
January 2009 - December 2010
Ain Shams University

Publications

Publications (98)
Preprint
Full-text available
PointNet++ is one of the most influential neural architectures for point cloud understanding. Although the accuracy of PointNet++ has been largely surpassed by recent networks such as PointMLP and Point Transformer, we find that a large portion of the performance gain is due to improved training strategies, i.e. data augmentation and optimization t...
Preprint
World models in model-based reinforcement learning usually face unrealistic long-time-horizon prediction issues due to compounding errors as the prediction errors accumulate over timesteps. Recent works in graph-structured world models improve the long-horizon reasoning ability via building a graph to represent the environment, but they are designe...
Preprint
Self-supervised learning for computer vision has achieved tremendous progress and improved many downstream vision tasks such as image classification, semantic segmentation, and object detection. Among these, generative self-supervised vision learning approaches such as MAE and BEiT show promising performance. However, their global masked reconstruc...
Preprint
Full-text available
Datasets that capture the connection between vision, language, and affection are limited, causing a lack of understanding of the emotional aspect of human intelligence. As a step in this direction, the ArtEmis dataset was recently introduced as a large-scale dataset of emotional reactions to images along with language explanations of these chosen e...
Preprint
Full-text available
Best-of-N (BoN) Average Displacement Error (ADE)/ Final Displacement Error (FDE) is the most used metric for evaluating trajectory prediction models. Yet, the BoN does not quantify the whole generated samples, resulting in an incomplete view of the model's prediction quality and performance. We propose a new metric, Average Mahalanobis Distance (AM...
Preprint
Full-text available
The main question we address in this paper is how to scale up visual recognition of unseen classes, also known as zero-shot learning, to tens of thousands of categories as in the ImageNet-21K benchmark. At this scale, especially with many fine-grained categories included in ImageNet-21K, it is critical to learn quality visual semantic representatio...
Preprint
Full-text available
This paper proposes an efficient approach to learning disentangled representations with causal mechanisms based on the difference of conditional probabilities in original and new distributions. We approximate the difference with models' generalization abilities so that it fits in the standard machine learning framework and can be efficiently comput...
Preprint
Full-text available
Videos show continuous events, yet most - if not all - video synthesis frameworks treat them discretely in time. In this work, we think of videos of what they should be - time-continuous signals, and extend the paradigm of neural representations to build a continuous-time video generator. For this, we first design continuous motion representations...
Preprint
Full-text available
We introduce Domain Aware Continual Zero-Shot Learning (DACZSL), the task of visually recognizing images of unseen categories in unseen domains sequentially. We created DACZSL on top of the DomainNet dataset by dividing it into a sequence of tasks, where classes are incrementally provided on seen domains during training and evaluation is conducted...
Preprint
Full-text available
Visual relationship recognition (VRR) is a fundamental scene understanding task. The structure that VRR provides is essential to improve the AI interpretability in downstream tasks such as image captioning and visual question answering. Several recent studies showed that the long-tail problem in VRR is even more critical than that in object recogni...
Preprint
Full-text available
We propose a novel loss for generative models, dubbed as GRaWD (Generative Random Walk Deviation), to improve learning representations of unexplored visual spaces. Quality learning representation of unseen classes (or styles) is crucial to facilitate novel image generation and better generative understanding of unseen visual classes (a.k.a. Zero-Sh...
Preprint
Full-text available
In this work, we develop a method to generate infinite high-resolution images with diverse and complex content. It is based on a perfectly equivariant generator with synchronous interpolations in the image and latent spaces. Latent codes, when sampled, are positioned on the coordinate grid, and each pixel is computed from an interpolation of the ne...
Preprint
Full-text available
In this paper, we aim to improve the data efficiency of image captioning. We propose VisualGPT, a data-efficient image captioning model that leverages the linguistic knowledge from a large pretrained language model (LM). A crucial challenge is to balance between the use of visual information in the image and prior linguistic knowledge acquired from...
Preprint
Full-text available
We present a novel large-scale dataset and accompanying machine learning models aimed at providing a detailed understanding of the interplay between visual content, its emotional effect, and explanations for the latter in language. In contrast to most existing annotation datasets in computer vision, we focus on the affective experience triggered by...
Preprint
Full-text available
Zero-shot learning (ZSL) aims at understanding unseen categories with no training examples from class-level descriptions. To improve the discriminative power of ZSL, we model the visual learning process of unseen categories with inspiration from the psychology of human creativity for producing novel art. First, we propose CIZSL-v1 as a creativity i...
Preprint
Full-text available
In most existing learning systems, images are typically viewed as 2D pixel arrays. However, in another paradigm gaining popularity, a 2D image is represented as an implicit neural representation (INR) -- an MLP that predicts an RGB pixel value given its (x,y) coordinate. In this paper, we propose two novel architectural techniques for building INR-...
Chapter
In this work we study the problem of using referential language to identify common objects in real-world 3D scenes. We focus on a challenging setup where the referred object belongs to a fine-grained object class and the underlying scene contains multiple object instances of that class. Due to the scarcity and unsuitability of existent 3D-oriented...
Preprint
Full-text available
Understanding the relationships between biomedical terms like viruses, drugs, and symptoms is essential in the fight against diseases. Many attempts have been made to introduce the use of machine learning to the scientific process of hypothesis generation(HG), which refers to the discovery of meaningful implicit connections between biomedical terms...
Preprint
An ability to grasp new concepts from their descriptions is one of the key features of human intelligence, and zero-shot learning (ZSL) aims to incorporate this property into machine learning models. In this paper, we theoretically investigate two very popular tricks used in ZSL: "normalize+scale" trick and attributes normalization and show how the...
Preprint
We introduce Inner Ensemble Networks (IENs) which reduce the variance within the neural network itself without an increase in the model complexity. IENs utilize ensemble parameters during the training phase to reduce the network variance. While in the testing phase, these parameters are removed without a change in the enhanced performance. IENs red...
Preprint
Full-text available
In natural language processing, relation extraction seeks to rationally understand unstructured text. Here, we propose a novel SpanBERT-based graph convolutional network (DG-SpanBERT) that extracts semantic features from a raw sentence using the pre-trained language model SpanBERT and a graph convolutional network to pool latent features. Our DG-Sp...
Preprint
Scaling up the vocabulary and complexity of current visual understanding systems is necessary in order to bridge the gap between human and machine visual intelligence. However, a crucial impediment to this end lies in the difficulty of generalizing to data distributions that come from real-world scenarios. Typically such distributions follow Zipf's...
Preprint
Full-text available
Better machine understanding of pedestrian behaviors enables faster progress in modeling interactions between agents such as autonomous vehicles and humans. Pedestrian trajectories are not only influenced by the pedestrian itself but also by interaction with surrounding objects. Previous methods modeled these interactions by using a variety of aggr...
Article
Large scale visual understanding is challenging, as it requires a model to handle the widely-spread and imbalanced distribution of 〈subject, relation, object〉 triples. In real-world scenarios with large numbers of objects and relations, some are seen very commonly while others are barely seen. We develop a new relationship detection model that embe...
Preprint
Continual learning aims to learn new tasks without forgetting previously learned ones. This is especially challenging when one cannot access data from previous tasks and when the model has a fixed capacity. Current regularization-based continual learning algorithms need an external representation and extra computation to measure the parameters' imp...
Chapter
So far life-long learning (LLL) has been studied in relatively small-scale and relatively artificial setups. Here, we introduce a new large-scale alternative. What makes the proposed setup more natural and closer to human-like visual systems is threefold: First, we focus on concepts (or facts, as we call them) of varying complexity, ranging from si...
Preprint
Zero-shot learning (ZSL) aims at understanding unseen categories with no training examples from class-level descriptions. To improve the discriminative power of zero-shot learning, we model the visual learning process of unseen categories with an inspiration from the psychology of human creativity for producing novel art. We relate ZSL to human cre...
Preprint
Full-text available
Learning from a few examples is a key characteristic of human intelligence that AI researchers have been excited about modeling. With the web-scale data being mostly unlabeled, few recent works showed that few-shot learning performance can be significantly improved with access to unlabeled data, known as semi-supervised few shot learning (SS-FSL)....
Preprint
Full-text available
Learning with less supervision is a major challenge in artificial intelligence. One sensible approach to decrease the amount of supervision is to leverage prior experience and transfer knowledge from tasks seen in the past. However, a necessary condition for a successful transfer is the ability to remember how to perform previous tasks. The Continu...
Chapter
Can an algorithm create original and compelling fashion designs to serve as an inspirational assistant? To help answer this question, we design and investigate different image generation models associated with different loss functions to boost novelty in fashion generation. The dimensions of our explorations include: (i) different Generative Advers...
Preprint
So far life-long learning (LLL) has been studied in relatively small-scale and relatively artificial setups. Here, we introduce a new large-scale alternative. What makes the proposed setup more natural and closer to human-like visual systems is threefold: First, we focus on concepts (or facts, as we call them) of varying complexity, ranging from si...
Preprint
Full-text available
In lifelong learning, the learner is presented with a sequence of tasks, incrementally building a data-driven prior which may be leveraged to speed up learning of a new task. In this work, we investigate the efficiency of current lifelong approaches, in terms of sample complexity, computational and memory cost. Towards this end, we first introduce...
Preprint
Generative models have proven to be an outstanding tool for representing high-dimensional probability distributions and generating realistic looking images. A fundamental characteristic of generative models is their ability to produce multi-modal outputs. However, while training, they are often susceptible to mode collapse, which means that the mod...
Preprint
Full-text available
Video segmentation is a challenging task that has many applications in robotics. Learning segmentation from few examples on-line is important for robotics in unstructured environments. The total number of objects and their variation in the real world is intractable, but for a specific task the robot deals with a small subset. Our network is taught,...
Chapter
Humans can learn in a continuous manner. Old rarely utilized knowledge can be overwritten by new incoming information while important, frequently used knowledge is prevented from being erased. In artificial learning systems, lifelong learning so far has focused mainly on accumulating knowledge over tasks and overcoming catastrophic forgetting. In t...
Chapter
Individual neurons in convolutional neural networks supervised for image-level classification tasks have been shown to implicitly learn semantically meaningful concepts ranging from simple textures and shapes to whole or partial objects – forming a “dictionary” of concepts acquired through the learning process. In this work we introduce a simple, e...
Preprint
Full-text available
Individual neurons in convolutional neural networks supervised for image-level classification tasks have been shown to implicitly learn semantically meaningful concepts ranging from simple textures and shapes to whole or partial objects - forming a "dictionary" of concepts acquired through the learning process. In this work we introduce a simple, e...
Conference Paper
Full-text available
Most existing zero-shot learning methods consider the problem as a visual semantic embedding one. Given the demonstrated capability of Generative Adversarial Networks(GANs) to generate images, we instead leverage GANs to imagine unseen categories from text descriptions and hence recognize novel classes with no examples being seen. Specifically, we...
Preprint
Large scale visual understanding is challenging, as it requires a model to handle the widely-spread and imbalanced distribution of <subject, relation, object> triples. In real-world scenarios with large numbers of objects and relations, some are seen very commonly while others are barely seen. We develop a new relationship detection model that embe...
Article
How does the machine classify styles in art? And how does it relate to art historians' methods for analyzing style? Several studies showed the ability of the machine to learn and predict styles, such as Renaissance, Baroque, Impressionism, etc., from images of paintings. This implies that the machine can learn an internal representation encoding di...
Article
Full-text available
Can an algorithm create original and compelling fashion designs to serve as an inspirational assistant? To help answer this question, we design and investigate different image generation models associated with different loss functions to boost creativity in fashion generation. The dimensions of our explorations include: (i) different Generative Adv...
Conference Paper
Full-text available
How does the machine classify styles in art? And how does it relate to art historians's methods for analyzing style? Several studies have shown the ability of the machine to learn and predict style categories, such as Renaissance, Baroque, Impressionism, etc., from images of paintings. This implies that the machine can learn an internal representat...
Article
People typically learn through exposure to visualconcepts associated with linguistic descriptions. For instance,teaching visual object categories to children is often accompa-nied by descriptions in text or speech. In a machine learningcontext, these observations motivates us to ask whether thislearning process could be computationally modeled to l...
Article
Humans can learn in a continuous manner. Old rarely utilized knowledge can be overwritten by new incoming information while important, frequently used knowledge is prevented from being erased. In artificial learning systems, lifelong learning so far has focused mainly on accumulating knowledge over tasks and overcoming catastrophic forgetting. In t...
Article
In this paper, we study learning visual classifiers from unstructured text descriptions at part precision with no training images. We propose a learning framework that is able to connect text terms to its relevant parts and suppress connections to non-visual text terms without any part-text annotations. For instance, this learning process enables t...
Conference Paper
Full-text available
In this paper, we study learning visual classifiers from un-structured text descriptions at part precision with no training images. We propose a learning framework that is able to connect text terms to its relevant parts and suppress connections to non-visual text terms without any part-text annotations. For instance, this learning process enables...
Conference Paper
Full-text available
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 simul...
Article
Full-text available
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 pr...
Conference Paper
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., <flower, red>), actions (e.g., <baby, smile>), interactions (e.g., <man, walking, dog>), and positional information (e.g.,...
Article
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 s...
Conference Paper
Full-text available
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 s...
Article
Full-text available
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 t...
Article
How to build a machine learning method that can continuously gain structured visual knowledge by learning structured facts? Our goal in this paper is to address this question by proposing a problem setting, where training data comes as structured facts in images with different types including (1) objects(e.g., < boy >), (2) attributes (e.g., < boy,...
Article
Full-text available
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 p...