Serwis Infona wykorzystuje pliki cookies (ciasteczka). Są to wartości tekstowe, zapamiętywane przez przeglądarkę na urządzeniu użytkownika. Nasz serwis ma dostęp do tych wartości oraz wykorzystuje je do zapamiętania danych dotyczących użytkownika, takich jak np. ustawienia (typu widok ekranu, wybór języka interfejsu), zapamiętanie zalogowania. Korzystanie z serwisu Infona oznacza zgodę na zapis informacji i ich wykorzystanie dla celów korzytania z serwisu. Więcej informacji można znaleźć w Polityce prywatności oraz Regulaminie serwisu. Zamknięcie tego okienka potwierdza zapoznanie się z informacją o plikach cookies, akceptację polityki prywatności i regulaminu oraz sposobu wykorzystywania plików cookies w serwisie. Możesz zmienić ustawienia obsługi cookies w swojej przeglądarce.
Object detection aims at high speed and accuracy simultaneously. However, fast models are usually less accurate, while accurate models cannot satisfy our need for speed. A fast model can be 10 times faster but 50% less accurate than an accurate model. In this paper, we propose Adaptive Feeding (AF) to combine a fast (but less accurate) detector and an accurate (but slow) detector, by adaptively determining...
In this paper, we propose a novel approach to incorporate structure knowledge into Convolutional Neural Networks (CNNs) for articulated human pose estimation from a single still image. Recent research on pose estimation adopt CNNs as base blocks to combine with other graphical models. Different from existing methods using features from CNNs to model the tree structure, we directly use the structure...
Recent work on neural network models shows success in dependency parsing. In this paper, we present a sequence learning dependency parsing (SLDP) model using long short-term memory for shift-reduce parser. A feed-forward neural network is used to build greedy model from rich local features. With the features extracted by the local model, we further train a long short-term memory (LSTM) model optimized...
Recently, the deep learning based methods, especially the ones based on convolutional neural network (CNN), achieved remarkable progresses in sentiment analysis. However, the CNN based methods do not take the latent topic in text into consideration. In this paper, we propose a CNN based Diversified Restrict Boltzmann Machine (RBM) method to model the sequence level latent topics in the sentences for...
The investors in financial market have shown great concerns in the events that may cause fluctuations in the capital market. Traditional event detection and type recognition methods were majorly based on text processing techniques while few research considers the financial time-series features. As we know, there are large amount of financial time-series data available such as stock transaction data...
A novel multiscale phase congruency (MPC) based analysis method is proposed in this paper for edge saliency detection and non-salient region texture suppression. Several MPC maps are proposed to be merged. Gaussian function based center priors and threshold processing are applied for the final edge saliency map generation, which can effectively suppress the textures and the detailed edges of non-salient...
This paper aims at presenting a simple and efficient single target tracking approach, which is suitable for the applications for modern smart glasses. Specifically, a novel set-to-set similarity measurement is proposed, which takes the critical appearance cues, the contextual structure of the points inside the set and the points' coordinate related to the bounding box into consideration jointly. In...
Given 3D outdoor scenes acquired by a LIDAR sensor, we address the problem of semantic segmentation of 3D point clouds involving simultaneously segmenting and classifying the data. The capability of semantic segmentation is essential for several applications, such as autonomous robot navigation and 3D reconstruction of point clouds. In this paper, we present a higher-order class-specific CRF model...
This paper proposes a framework based on the Hidden Markov Models (HMMs) benefited from the low rank approximation of the original sign videos for two aspects. First, under the observations that most visual information of a sign sequence typically concentrates on limited key frames, we apply an online low rank approximation of sign videos for the first time to select the key frames. Second, rather...
Misclassification of bug reports inevitably sacrifices the performance of bug prediction models. Manual examinations can help reduce the noise but bring a heavy burden for developers instead. In this paper, we propose a hybrid approach by combining both text mining and data mining techniques of bug report data to automate the prediction process. The first stage leverages text mining techniques to...
Phishing uses a fake Web page to steal personal sensitive information such as credit card numbers and passwords. Generally, the fake Web page is visually similar to the legitimate target Web page. The phishers can obtain financial benefits through these information. Anti-phishing is very important for a variety of applications such as phishing attacks, online transaction security, and user privacy...
The unstructured road detection plays a key role in an autonomous vehicle navigation system. However, the unstructured road images often contain shadows and are easily affected by ambient light, resulting to an inaccuracy with road detection. A robust road detection technique is required. In this paper, we adopted an improved fuzzy c-means(FCM) clustering algorithm to address these issues. The new...
To understand scenes and help autonomous robots and cars, researchers' attention is directed through the problem of classifying 3D point cloud. In this paper, we present a novel approach to semantically segment 3D point cloud of residential scenes captured by a lidar sensor. Our approach is based on a dual-scale analysis: a small-scale clustering and a large-scale grouping. Features used to train...
Video enhancement plays an important role in various video applications. It is desirable to achieve high visual quality of the entire picture where multiple region-of-interests (ROIs) within the frame can be adaptively and simultaneously enhanced. In this paper, a new global-based video enhancement algorithm is proposed. The proposed algorithm first analyzes features from different ROIs. Then, a ‘global’...
Mode parameters extraction with Morlet wavelet continuous transformation is an important algorithm in fault diagnosis area. However, there is aliasing phenomenon between two modes on the scale image of wavelet continuous transformation while vibration modes are concentrated. A new wavelet function named mode wavelet is put forward in this paper. The mode wavelet continuous transformation can split...
This paper reports our recent work on optimizing the AF (articulatory features) based confidence measures, and combining them with the traditional HMM-based confidence measures. Different articulatory properties are analyzed using a separate AF-based confidence calculation method proposed in this paper, and are observed to be both complementary and redundant. A more compact subset is chosen and assembled...
In this paper, we propose a speech emotion recognition system using both spectral and prosodic features. Most traditional systems have focused on spectral features or prosodic features. Since both the spectral and the prosodic features contain emotion information, it is believed that the combining of spectral features and prosodic features will improve the performance of the emotion recognition system...
This paper tries to deal with the problem of performance degradation in emotion affected speech recognition. The F-ratio analysis method in statistics is utilized to analyze the significance of different frequency bands for speech unit classification. The result is then used to optimize filter bank design for Mel-frequency cepstral coefficients (MFCC) and perceptual linear prediction (PLP) features...
In this paper, we present an approach that using articulatory features (AFs) derived from spectral features for speech emotion recognition. Also, we investigated the combination of AFs and spectral features. Systems based on AFs only and combined spectral-articulatory features are tested on the CASIA Mandarin emotional corpus. Experiments results show that AFs alone are not suitable for speech emotion...
In this study, some research activities on expressive speech recognition and conversion will be introduced. A database consisting of five kinds of speech emotions (i.e. happiness, sadness, surprise, anger and neutral) is used. Not only those traditional features such as mfcc, plp, and pitch are studied, but also a new feature extraction method based on fisher's F-Ratio is proposed and reported. In...
Podaj zakres dat dla filtrowania wyświetlonych wyników. Możesz podać datę początkową, końcową lub obie daty. Daty możesz wpisać ręcznie lub wybrać za pomocą kalendarza.