Hieu M Le

Stony Brook University | Stony Brook · Department of Computer Science

We propose a novel deep learning method for shadow removal. Inspired by physical models of shadow formation, we use a linear illumination transformation to model the shadow effects in the image that allows the shadow image to be expressed as a combination of the shadow-free image, the shadow parameters, and a matte layer. We use two deep networks,...

Abstract Satellite imagery is now well established as a method of finding and estimating the abundance of Antarctic penguin colonies. However, the delineation and classification of penguin colonies in sub‐meter satellite imagery has required the use of expert observers and is highly labor intensive, precluding regular censuses at the pan‐Antarctic...

While single image shadow detection has been improving rapidly in recent years, video shadow detection remains a challenging task due to data scarcity and the difficulty in modelling temporal consistency. The current video shadow detection method achieves this goal via co-attention, which mostly exploits information that is temporally coherent but...

We propose a novel deep learning method for shadow removal. Inspired by physical models of shadow formation, we use a linear illumination transformation to model the shadow effects in the image that allows the shadow image to be expressed as a combination of the shadow-free image, the shadow parameters, and a matte layer. We use two deep networks,...

The requirement for paired shadow and shadow-free images limits the size and diversity of shadow removal datasets and hinders the possibility of training large-scale, robust shadow removal algorithms. We propose a shadow removal method that can be trained using only shadow and non-shadow patches cropped from the shadow images themselves. Our method...

The requirement for paired shadow and shadow-free images limits the size and diversity of shadow removal datasets and hinders the possibility of training large-scale, robust shadow removal algorithms. We propose a shadow removal method that can be trained using only shadow and non-shadow patches cropped from the shadow images themselves. Our method...

Most cetacean species are wide-ranging and highly mobile, creating significant challenges for researchers by limiting the scope of data that can be collected and leaving large areas un-surveyed. Aerial surveys have proven an effective way to locate and study cetacean movements but are costly and limited in spatial extent. Here we present a semi-aut...

We propose a novel deep learning method for shadow removal. Inspired by physical models of shadow formation, we use a linear illumination transformation to model the shadow effects in the image that allows the shadow image to be expressed as a combination of the shadow-free image, the shadow parameters, and a matte layer. We use two deep networks,...

Relationship-based access control (ReBAC) is a flexible and expressive framework that allows policies to be expressed in terms of chains of relationship between entities as well as attributes of entities. ReBAC policy mining algorithms have a potential to significantly reduce the cost of migration from legacy access control systems to ReBAC, by par...

Antarctic penguins are important ecological indicators -- especially in the face of climate change. In this work, we present a deep learning based model for semantic segmentation of Ad\'elie penguin colonies in high-resolution satellite imagery. To train our segmentation models, we take advantage of the Penguin Colony Dataset: a unique dataset with...

Relationship-based access control (ReBAC) is a flexible and expressive framework that allows policies to be expressed in terms of chains of relationship between entities as well as attributes of entities. ReBAC policy mining algorithms have a potential to significantly reduce the cost of migration from legacy access control systems to ReBAC, by par...

We propose a novel GAN-based framework for detecting shadows in images, in which a shadow detection network (D-Net) is trained together with a shadow attenuation network (A-Net) that generates adversarial training examples. The A-Net modifies the original training images constrained by a simplified physical shadow model and is focused on fooling th...

In this work, we tackle the problem of crowd counting in images. We present a Convolutional Neural Network (CNN) based density estimation approach to solve this problem. Predicting a high resolution density map in one go is a challenging task. Hence, we present a two branch CNN architecture for generating high resolution density maps, where the fir...

Single image shadow detection is a very challenging problem because of the limited amount of information available in one image, as well as the scarcity of annotated training data. In this work, we propose a novel adversarial training based framework that yields a high performance shadow detection network (D-Net). D-Net is trained together with an...

This paper proposes a geodesic-distance-based feature that encodes global information for improved video segmentation algorithms. The feature is a joint histogram of intensity and geodesic distances, where the geodesic distances are computed as the shortest paths between superpixels via their boundaries. We also incorporate adaptive voting weights...

Co-localization is the problem of localizing categorical objects using only positive sets of example images, without any form of further supervision. This is a challenging task as there is no pixel-level annotations. Motivated by human visual learning, we find the common features of an object category from convolutional kernels of a pre-trained con...

Video segmentation is the task of grouping similar pix-els in the spatio-temporal domain, and has become an important preprocessing step for subsequent video analysis. Most video segmentation and supervoxel methods output a hierarchy of segmentations, but while this provides useful multiscale information, it also adds difficulty in selecting the ap...

The subject of “handwritten digit recognition” is a great concern and has many applications in various fields. Although highly restricted forms of digit recognition are widely utilized, reading incomplete and occluded digit image is still a challenge for both academia and industries. In this paper, we attack the problems of recognizing occluded han...