Related papers: Free-Space Detection with Self-Supervised and Onli…
Most of current computer vision-based advanced driver assistance systems (ADAS) perform detection and tracking of objects quite successfully under regular conditions. However, under adverse weather and changing lighting conditions, and in…
Fully convolutional neural networks (FCNNs) trained on a large number of images with strong pixel-level annotations have become the new state of the art for the semantic segmentation task. While there have been recent attempts to learn…
Visual surveillance aims to perform robust foreground object detection regardless of the time and place. Object detection shows good results using only spatial information, but foreground object detection in visual surveillance requires…
This paper addresses the problem of photometric stereo for non-Lambertian surfaces. Existing approaches often adopt simplified reflectance models to make the problem more tractable, but this greatly hinders their applications on real-world…
In this paper we propose a novel deep neural network that is able to jointly reason about 3D detection, tracking and motion forecasting given data captured by a 3D sensor. By jointly reasoning about these tasks, our holistic approach is…
Fully convolutional neural networks give accurate, per-pixel prediction for input images and have applications like semantic segmentation. However, a typical FCN usually requires lots of floating point computation and large run-time memory,…
Object detection is a crucial task in computer vision that aims to identify and localize objects in images or videos. The recent advancements in deep learning and Convolutional Neural Networks (CNNs) have significantly improved the…
Recently, change detection (CD) of remote sensing images have achieved great progress with the advances of deep learning. However, current methods generally deliver incomplete CD regions and irregular CD boundaries due to the limited…
This work examines the use of a fully convolutional net (FCN) to find an image segment, given a pixel within this segment region. The net receives an image, a point in the image and a region of interest (RoI ) mask. The net output is a…
Deep learning based methods, such as Convolution Neural Network (CNN), have demonstrated their efficiency in hyperspectral image (HSI) classification. These methods can automatically learn spectral-spatial discriminative features within…
Robust detection of moving vehicles is a critical task for any autonomously operating outdoor robot or self-driving vehicle. Most modern approaches for solving this task rely on training image-based detectors using large-scale vehicle…
Deep learning using Convolutional Neural Networks (CNNs) has been shown to significantly out-performed many conventional vision algorithms. Despite efforts to increase the CNN efficiency both algorithmically and with specialized hardware,…
Understanding visual scenes relies more and more on dense pixel-wise classification obtained via deep fully convolutional neural networks. However, due to the nature of the networks, predictions often suffer from blurry boundaries and…
This paper proposes an efficient unsupervised method for detecting relevant changes between two temporally different images of the same scene. A convolutional neural network (CNN) for semantic segmentation is implemented to extract…
In this paper, we exploit a Fully Convolutional Network (FCN) to analyze the audio data of spontaneous speech for dementia detection. A fully convolutional network accommodates speech samples with varying lengths, thus enabling us to…
Change detection is the process of identifying pixelwise differences in bitemporal co-registered images. It is of great significance to Earth observations. Recently, with the emergence of deep learning (DL), the power and feasibility of…
In many machine learning applications, labeled data is scarce and obtaining more labels is expensive. We introduce a new approach to supervising neural networks by specifying constraints that should hold over the output space, rather than…
In this work, we address the challenging task of 3D object recognition without the reliance on real-world 3D labeled data. Our goal is to predict the 3D shape, size, and 6D pose of objects within a single RGB-D image, operating at the…
The splendid success of convolutional neural networks (CNNs) in computer vision is largely attributable to the availability of massive annotated datasets, such as ImageNet and Places. However, in medical imaging, it is challenging to create…
Although a polygon is a more accurate representation than an upright bounding box for text detection, the annotations of polygons are extremely expensive and challenging. Unlike existing works that employ fully-supervised training with…