The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
An open question in facial landmark localization in video is whether one should perform tracking or tracking-by-detection (i.e. face alignment). Tracking produces fittings of high accuracy but is prone to drifting. Tracking-by-detection is drift-free but results in low accuracy fittings. To provide a solution to this problem, we describe the very first, to the best of our knowledge, synergistic approach...
We propose to help weakly supervised object localization for classes where location annotations are not available, by transferring things and stuff knowledge from a source set with available annotations. The source and target classes might share similar appearance (e.g. bear fur is similar to cat fur) or appear against similar background (e.g. horse and sheep appear against grass). To exploit this,...
This paper proposes a probabilistic approach to recover affine camera calibration and objects position/occupancy from multi-view images using solely the information from image detections. We show that remarkable object localisation and volumetric occupancy can be recovered by including both geometrical constraints and prior information given by objects CAD models from the ShapeNet dataset. This can...
This paper introduces a novel approach for modeling visual relations between pairs of objects. We call relation a triplet of the form (subject; predicate; object) where the predicate is typically a preposition (eg. ’under’, ’in front of’) or a verb (’hold’, ’ride’) that links a pair of objects (subject; object). Learning such relations is challenging as the objects have different spatial configurations...
Multi-person pose estimation in the wild is challenging. Although state-of-the-art human detectors have demonstrated good performance, small errors in localization and recognition are inevitable. These errors can cause failures for a single-person pose estimator (SPPE), especially for methods that solely depend on human detection results. In this paper, we propose a novel regional multi-person pose...
We present Deeply Supervised Object Detector (DSOD), a framework that can learn object detectors from scratch. State-of-the-art object objectors rely heavily on the off the-shelf networks pre-trained on large-scale classification datasets like Image Net, which incurs learning bias due to the difference on both the loss functions and the category distributions between classification and detection tasks...
Current state-of-the-art approaches for spatio-temporal action localization rely on detections at the frame level that are then linked or tracked across time. In this paper, we leverage the temporal continuity of videos instead of operating at the frame level. We propose the ACtion Tubelet detector (ACT-detector) that takes as input a sequence of frames and outputs tubelets, i.e., sequences of bounding...
In this paper, we investigate a weakly-supervised object detection framework. Most existing frameworks focus on using static images to learn object detectors. However, these detectors often fail to generalize to videos because of the existing domain shift. Therefore, we investigate learning these detectors directly from boring videos of daily activities. Instead of using bounding boxes, we explore...
We propose a method for geometric calibration of multifocus plenoptic cameras using raw images. Multi-focus plenoptic cameras feature several types of micro-lenses spatially aligned in front of the camera sensor to generate micro-images at different magnifications. This multi-lens arrangement provides computational-photography benefits but complicates calibration. Our methodology achieves the detection...
Traditional vehicle detectors always utilize singletemplate model to represent the vehicle which can not encircle vehicles with different aspect ratios. In this paper, we propose a fast and accurate approach for detecting vehicles which joints classification and aspect ratio regression. The key idea is extending the boosting decision trees method to estimate vehicle's aspect ratio during vehicle detection,...
We propose “Areas of Attention”, a novel attentionbased model for automatic image captioning. Our approach models the dependencies between image regions, caption words, and the state of an RNN language model, using three pairwise interactions. In contrast to previous attentionbased approaches that associate image regions only to the RNN state, our method allows a direct association between caption...
Since convolutional neural network (CNN) lacks an inherent mechanism to handle large scale variations, we always need to compute feature maps multiple times for multiscale object detection, which has the bottleneck of computational cost in practice. To address this, we devise a recurrent scale approximation (RSA) to compute feature map once only, and only through this map can we approximate the rest...
Herein we present a novel 50 channel, charge integrating, Faraday plate detector system for the detection, characterization and imaging of charged particles emitted from an ambient ionization source. The detector is capable of spatial positioning of ion beams with sub nA current intensity, high linearity, large dynamic range and dark current noise <10 pA. Each channel is connected to its own calibrated...
A fiber-optic capillary (FOCap) gas chromatography detector was employed to measure eluting volatile organic compounds (VOCs) through the localized surface plasmon resonance (LSPR) of thiolate monolayer-protected nanoparticles. The 1-octanethiol silver nanoparticles (C8-AgNP) were synthesized through reduction with sodium borohydride. The inner wall surface of the FOCap detector is modified with (3-mercaptopropyl)...
We present a digital system for measurement of neutron spectra in mixed gamma-neutron fields. The signal from a standard scintillation detector is sampled at rate up to 1 GHz, using 12-bit analog-to-digital converters. First stage of the signal processing is performed on a Virtex 6 FPGA and partial results are streamed through a fast Ethernet link to a computer, where the final processing takes place...
The ability to remotely monitor the radiation dose in environments where the radiation dose rate precludes the use of conventional technology offers a step change in capability. Through the use of wide band gap semiconductor materials, we show that it is possible to develop a self-powered system that harvests energy from the X-ray photon flux in the environment. This opens up the possibility of developing...
Manually annotating object bounding boxes is central to building computer vision datasets, and it is very time consuming (annotating ILSVRC [53] took 35s for one high-quality box [62]). It involves clicking on imaginary comers of a tight box around the object. This is difficult as these comers are often outside the actual object and several adjustments are required to obtain a tight box. We propose...
This paper presents the design and implementation of a low power, wideband and high sensitivity CMOS power detector in 130 nm standard CMOS technology. It utilises a travelling-wave structure to achieve wideband input matching bandwidth from 7 GHz to more than 70 GHz. By biasing the power detectors in subthreshold regime, it achieves a measured peak voltage sensitivity of 75 dB at 7 GHz while maintaining...
The application of machine learning to software fault injection data has been shown to be an effective approach for the generation of efficient error detection mechanisms (EDMs). However, such approaches to the design of EDMs have invariably adopted a fault model with a single-fault assumption, limiting the practical relevance of the detectors and their evaluation. Software containing more than a...
This paper presents a vibration control design to the string-tip-mass system by using a non-symmetric peak-detector mechanism. Previously, this peak-detector system was used as an easy algorithm to mitigate vibration on a real flexible structure. Moreover, its mathematical representation is simple and it just has two parameters to tune. Following this former experience, we adequate this strategy to...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.