Related papers: Learning a perceptual manifold with deep features …

This paper shows how to extract dense optical flow from videos with a convolutional neural network (CNN). The proposed model constitutes a potential building block for deeper architectures to allow using motion without resorting to an…

We propose augmenting deep neural networks with an attention mechanism for the visual object detection task. As perceiving a scene, humans have the capability of multiple fixation points, each attended to scene content at different…

Humans can intuitively decompose an image into a sequence of strokes to create a painting, yet existing methods for generating drawing processes are limited to specific data types and often rely on expensive human-annotated datasets. We…

While deep feature learning has revolutionized techniques for static-image understanding, the same does not quite hold for video processing. Architectures and optimization techniques used for video are largely based off those for static…

High-level shape understanding and technique evaluation on large repositories of 3D shapes often benefit from additional information known about the shapes. One example of such information is the semantic segmentation of a shape into…

We present a novel online unsupervised method for face identity learning from video streams. The method exploits deep face descriptors together with a memory based learning mechanism that takes advantage of the temporal coherence of visual…

This paper presents a deep relational metric learning (DRML) framework for image clustering and retrieval. Most existing deep metric learning methods learn an embedding space with a general objective of increasing interclass distances and…

Recently, deep neural network has shown promising performance in face image recognition. The inputs of most networks are face images, and there is hardly any work reported in literature on network with face videos as input. To sufficiently…

Traditional computer graphics rendering pipeline is designed for procedurally generating 2D quality images from 3D shapes with high performance. The non-differentiability due to discrete operations such as visibility computation makes it…

We propose a deep neural network for the prediction of future frames in natural video sequences. To effectively handle complex evolution of pixels in videos, we propose to decompose the motion and content, two key components generating…

The tracking-by-detection framework usually consist of two stages: drawing samples around the target object in the first stage and classifying each sample as the target object or background in the second stage. Current popular trackers…

In this work, we present a novel background subtraction system that uses a deep Convolutional Neural Network (CNN) to perform the segmentation. With this approach, feature engineering and parameter tuning become unnecessary since the…

We present a novel framework for self-supervised grasped object segmentation with a robotic manipulator. Our method successively learns an agnostic foreground segmentation followed by a distinction between manipulator and object solely by…

We present a solution for the goal of extracting a video from a single motion blurred image to sequentially reconstruct the clear views of a scene as beheld by the camera during the time of exposure. We first learn motion representation…

Deep learning has brought an unprecedented progress in computer vision and significant advances have been made in predicting subjective properties inherent to visual data (e.g., memorability, aesthetic quality, evoked emotions, etc.).…

Recent co-part segmentation methods mostly operate in a supervised learning setting, which requires a large amount of annotated data for training. To overcome this limitation, we propose a self-supervised deep learning method for co-part…

Object detection in challenging situations such as scale variation, occlusion, and truncation depends not only on feature details but also on contextual information. Most previous networks emphasize too much on detailed feature extraction…

Deep learning has successfully been leveraged for medical image segmentation. It employs convolutional neural networks (CNN) to learn distinctive image features from a defined pixel-wise objective function. However, this approach can lead…

Non-linear manifold learning enables high-dimensional data analysis, but requires out-of-sample-extension methods to process new data points. In this paper, we propose a manifold learning algorithm based on deep learning to create an…

Image-generating machine learning models are typically trained with loss functions based on distance in the image space. This often leads to over-smoothed results. We propose a class of loss functions, which we call deep perceptual…