Related papers: LOAD: Local Orientation Adaptive Descriptor for Te…
In this paper, we propose a zoom-out-and-in network for generating object proposals. A key observation is that it is difficult to classify anchors of different sizes with the same set of features. Anchors of different sizes should be placed…
Region-based object detection infers object regions for one or more categories in an image. Due to the recent advances in deep learning and region proposal methods, object detectors based on convolutional neural networks (CNNs) have been…
Feature descriptors of point clouds are used in several applications, such as registration and part segmentation of 3D point clouds. Learning discriminative representations of local geometric features is unquestionably the most important…
This paper presents a new deep neural network design for salient object detection by maximizing the integration of local and global image context within, around, and beyond the salient objects. Our key idea is to adaptively propagate and…
With the widespread availability of cellphones and cameras that have GPS capabilities, it is common for images being uploaded to the Internet today to have GPS coordinates associated with them. In addition to research that tries to predict…
Video salient object detection (VSOD) is an important task in many vision applications. Reliable VSOD requires to simultaneously exploit the information from both the spatial domain and the temporal domain. Most of the existing algorithms…
Academic documents are packed with texts, equations, tables, and figures, requiring comprehensive understanding for accurate Optical Character Recognition (OCR). While end-to-end OCR methods offer improved accuracy over layout-based…
The advent of a panoply of resource limited devices opens up new challenges in the design of computer vision algorithms with a clear compromise between accuracy and computational requirements. In this paper we present new binary image…
Existing approaches to unsupervised object discovery (UOD) do not scale up to large datasets without approximations that compromise their performance. We propose a novel formulation of UOD as a ranking problem, amenable to the arsenal of…
The main aim of this paper is to propose a color texture classification approach which uses color sensor information and texture features jointly. High accuracy, low noise sensitivity and low computational complexity are specified aims for…
We address the problem of visual place recognition with perceptual changes. The fundamental problem of visual place recognition is generating robust image representations which are not only insensitive to environmental changes but also…
Transfer learning aims to make the most of existing pre-trained models to achieve better performance on a new task in limited data scenarios. However, it is unclear which models will perform best on which task, and it is prohibitively…
Object detectors are usually trained with large amount of labeled data, which is expensive and labor-intensive. Pre-trained detectors applied to unlabeled dataset always suffer from the difference of dataset distribution, also called domain…
Deep learning techniques have become prominent in modern fault diagnosis for complex processes. In particular, convolutional neural networks (CNNs) have shown an appealing capacity to deal with multivariate time-series data by converting…
A serious problem in image classification is that a trained model might perform well for input data that originates from the same distribution as the data available for model training, but performs much worse for out-of-distribution (OOD)…
This paper proposes a novel point-cloud-based place recognition system that adopts a deep learning approach for feature extraction. By using a convolutional neural network pre-trained on color images to extract features from a range image…
Progress has been achieved recently in object detection given advancements in deep learning. Nevertheless, such tools typically require a large amount of training data and significant manual effort to label objects. This limits their…
We introduce a novel loss for learning local feature descriptors which is inspired by the Lowe's matching criterion for SIFT. We show that the proposed loss that maximizes the distance between the closest positive and closest negative patch…
Modern image classification is based upon directly predicting classes via large discriminative networks, which do not directly contain information about the intuitive visual features that may constitute a classification decision. Recently,…
Pixel-level labels are particularly expensive to acquire. Hence, pretraining is a critical step to improve models on a task like semantic segmentation. However, prominent algorithms for pretraining neural networks use image-level…