RESUMEN

This article introduces a novel self-supervised method that leverages incoherence detection for video representation learning. It stems from the observation that the visual system of human beings can easily identify video incoherence based on their comprehensive understanding of videos. Specifically, we construct the incoherent clip by multiple subclips hierarchically sampled from the same raw video with various lengths of incoherence. The network is trained to learn the high-level representation by predicting the location and length of incoherence given the incoherent clip as input. Additionally, we introduce intravideo contrastive learning to maximize the mutual information between incoherent clips from the same raw video. We evaluate our proposed method through extensive experiments on action recognition and video retrieval using various backbone networks. Experiments show that our proposed method achieves remarkable performance across different backbone networks and different datasets compared to previous coherence-based methods.

RESUMEN

Domain adaptation (DA) approaches address domain shift and enable networks to be applied to different scenarios. Although various image DA approaches have been proposed in recent years, there is limited research toward video DA. This is partly due to the complexity in adapting the different modalities of features in videos, which includes the correlation features extracted as long-range dependencies of pixels across spatiotemporal dimensions. The correlation features are highly associated with action classes and proven their effectiveness in accurate video feature extraction through the supervised action recognition task. Yet correlation features of the same action would differ across domains due to domain shift. Therefore, we propose a novel adversarial correlation adaptation network (ACAN) to align action videos by aligning pixel correlations. ACAN aims to minimize the distribution of correlation information, termed as pixel correlation discrepancy (PCD). Additionally, video DA research is also limited by the lack of cross-domain video datasets with larger domain shifts. We, therefore, introduce a novel HMDB-ARID dataset with a larger domain shift caused by a larger statistical difference between domains. This dataset is built in an effort to leverage current datasets for dark video classification. Empirical results demonstrate the state-of-the-art performance of our proposed ACAN for both existing and the new video DA datasets.

RESUMEN

Hough transform (HT) is one of the most well-known techniques in computer vision that has been the basis of many practical image processing algorithms. HT however is designed to work for frame-based systems such as conventional digital cameras. Recently, event-based systems such as Dynamic Vision Sensor (DVS) cameras, has become popular among researchers. Event-based cameras have a significantly high temporal resolution (1 µs), but each pixel can only detect change and not color. As such, the conventional image processing algorithms cannot be readily applied to event-based output streams. Therefore, it is necessary to adapt the conventional image processing algorithms for event-based cameras. This paper provides a systematic explanation, starting from extending conventional HT to 3D HT, adaptation to event-based systems, and the implementation of the 3D HT using Spiking Neural Networks (SNNs). Using SNN enables the proposed solution to be easily realized on hardware using FPGA, without requiring CPU or additional memory. In addition, we also discuss techniques for optimal SNN-based implementation using efficient number of neurons for the required accuracy and resolution along each dimension, without increasing the overall computational complexity. We hope that this will help to reduce the gap between event-based and frame-based systems.

RESUMEN

In modern manufacturing systems and industries, more and more research efforts have been made in developing effective machine health monitoring systems. Among various machine health monitoring approaches, data-driven methods are gaining in popularity due to the development of advanced sensing and data analytic techniques. However, considering the noise, varying length and irregular sampling behind sensory data, this kind of sequential data cannot be fed into classification and regression models directly. Therefore, previous work focuses on feature extraction/fusion methods requiring expensive human labor and high quality expert knowledge. With the development of deep learning methods in the last few years, which redefine representation learning from raw data, a deep neural network structure named Convolutional Bi-directional Long Short-Term Memory networks (CBLSTM) has been designed here to address raw sensory data. CBLSTM firstly uses CNN to extract local features that are robust and informative from the sequential input. Then, bi-directional LSTM is introduced to encode temporal information. Long Short-Term Memory networks(LSTMs) are able to capture long-term dependencies and model sequential data, and the bi-directional structure enables the capture of past and future contexts. Stacked, fully-connected layers and the linear regression layer are built on top of bi-directional LSTMs to predict the target value. Here, a real-life tool wear test is introduced, and our proposed CBLSTM is able to predict the actual tool wear based on raw sensory data. The experimental results have shown that our model is able to outperform several state-of-the-art baseline methods.

RESUMEN

New optimization models and algorithms for online learning with Kernels (OLK) in classification, regression, and novelty detection are proposed in a reproducing Kernel Hilbert space. Unlike the stochastic gradient descent algorithm, called the naive online Reg minimization algorithm (NORMA), OLK algorithms are obtained by solving a constrained optimization problem based on the proposed models. By exploiting the techniques of the Lagrange dual problem like Vapnik's support vector machine (SVM), the solution of the optimization problem can be obtained iteratively and the iteration process is similar to that of the NORMA. This further strengthens the foundation of OLK and enriches the research area of SVM. We also apply the obtained OLK algorithms to problems in classification, regression, and novelty detection, including real time background substraction, to show their effectiveness. It is illustrated that, based on the experimental results of both classification and regression, the accuracy of OLK algorithms is comparable with traditional SVM-based algorithms, such as SVM and least square SVM (LS-SVM), and with the state-of-the-art algorithms, such as Kernel recursive least square (KRLS) method and projectron method, while it is slightly higher than that of NORMA. On the other hand, the computational cost of the OLK algorithm is comparable with or slightly lower than existing online methods, such as above mentioned NORMA, KRLS, and projectron methods, but much lower than that of SVM-based algorithms. In addition, different from SVM and LS-SVM, it is possible for OLK algorithms to be applied to non-stationary problems. Also, the applicability of OLK in novelty detection is illustrated by simulation results.

Asunto(s)

RESUMEN

AIMS: We aimed to develop an image analysis software that enabled measurement of glomerular basement membrane (GBM) thickness. METHODS: With this software, we evaluated the range of GBM widths found in a cohort of Asian patients diagnosed with a spectrum of renal diseases including minimal change/IgM nephropathy, focal and segmental glomerulosclerosis, IgA nephropathy, systemic lupus erythematosus nephritis, diabetic nephropathy, pauci-immune crescentic glomerulonephritis, thin basement membrane disease, and tubulointerstitial nephritis. Measurements were taken from a minimum of five glomerular capillary loops of each glomerulus. For each loop, at least 10 different points of the GBM were measured. RESULTS: The average GBM width measured for minimal change disease was 347.4 +/- 9.0 nm, with the highest value being 403.9 nm and lowest being 214.7 nm. No association was found between GBM width and gender. We found a significant increase in GBM width in pathological states like lupus nephropathy (p < 0.0001), diabetic nephritis (p < 0.001) and tubulointerstitial nephritis (p < 0.01) as compared with minimal change disease. Only one case of thin membrane nephropathy (198.7 nm) was available for analysis and we found a significant thinning of the GBM. CONCLUSIONS: These observations provide insights into the range of GBM thickness in several disease states and support the use of this novel software in the daily diagnostic laboratory setting.

Asunto(s)