The performance of video action recognition has improved significantly in recent decades. Current recognition approaches mainly utilize convolutional neural networks to acquire video feature representations. In addition to the spatial information of video frames, temporal information such as motions and changes is important for recognizing videos. Therefore, the use of convolutions in a spatiotemporal three-dimensional (3D) space for representing spatiotemporal features has garnered significant attention. Herein, we introduce recent advances in 3D convolutions for video action recognition.

In this paper, we evaluate a prediction method of regions including dislocation clusters which are crystallographic defects in a photoluminescence (PL) image of multicrystalline silicon wafers. We applied a method of a transfer learning of the convolutional neural network to solve this task. For an input of a sub-region image of a whole PL image, the network outputs the dislocation cluster regions are included in the upper wafer image or not. A network learned using image in lower wafers of the bottom of dislocation clusters as positive examples. We experimented under three conditions as negative examples; image of some depth wafer, randomly selected images, and both images. We examined performances of accuracies and Youden's J statistics under 2 cases; predictions of occurrences of dislocation clusters at 10 upper wafer or 20 upper wafer. Results present that values of accuracies and values of Youden's J are not so high, but they are higher results than ones of bag of features (visual words) method. For our purpose to find occurrences dislocation clusters in upper wafers from the input wafer, we obtained results that randomly select condition as negative examples is appropriate for 10 upper wafers prediction, since its results are better than other negative examples conditions, consistently.

Various cross-modal retrieval methods that can retrieve images related to a query sentence without text annotations have been proposed. Although a high level of retrieval performance is achieved by these methods, they have been developed for a single domain retrieval setting. When retrieval candidate images come from various domains, the retrieval performance of these methods might be decreased. To deal with this problem, we propose a new domain adaptive cross-modal retrieval method. By translating a modality and domains of a query and candidate images, our method can retrieve desired images accurately in a different domain retrieval setting. Experimental results for clipart and painting datasets showed that the proposed method has better retrieval performance than that of other conventional and state-of-the-art methods.

In this study, we present a novel method for removing smoke from videos based on a single image sequence. Smoke is a significant artifact in images or videos because it can reduce the visibility in disaster scenes. Our proposed method for removing smoke involves two main processes: (1) the development of a smoke imaging model and (2) smoke removal using spatio-temporal pixel compensation. First, we model the optical phenomena in natural scenes including smoke, which is called a smoke imaging model. Our smoke imaging model is developed by extending conventional haze imaging models. We then remove the smoke from a video in a frame-by-frame manner based on the smoke imaging model. Next, we refine the appearance of the smoke-free video by spatio-temporal pixel compensation, where we align the smoke-free frames using the corresponding pixels. To obtain the corresponding pixels, we use SIFT and color features with distance constraints. Finally, in order to obtain a clear video, we refine the pixel values based on the spatio-temporal weightings of the corresponding pixels in the smoke-free frames. We used simulated and actual smoke videos in our validation experiments. The experimental results demonstrated that our method can obtain effective smoke removal results from dynamic scenes. We also quantitatively assessed our method based on a temporal coherence measure.

In medical fields, detecting traumatic bleedings has always been a difficult task due to the small size, low contrast of targets and large number of images. In this work we propose an automatic traumatic bleeding detection approach from contrast enhanced CT images via deep CNN networks, containing segmentation process and classification process. CT values of DICOM images are extracted and processed via three different window settings first. Small 3D patches are cropped from processed images and segmented by a 3D CNN network. Then segmentation results are converted to point cloud data format and classified by a classifier. The proposed pre-processing approach makes the segmentation network be able to detect small and low contrast targets and achieve a high sensitivity. The additional classification network solves the boundary problem and short-sighted problem generated during the segmentation process to further decrease false positives. The proposed approach is tested with 3 CT cases containing 37 bleeding regions. As a result, a total of 34 bleeding regions are correctly detected, the sensitivity reaches 91.89%. The average false positive number of test cases is 1678. 46.1% of false positive predictions are decreased after being classified. The proposed method is proved to be able to achieve a high sensitivity and be a reference of medical doctors.

We investigated the function in the Lateral Geniculate Nucleus of avoidance behavior due to the inconsistency between binocular retinal images due to blue from vergence eye movement based on avoidance behavior caused by the inconsistency of binocular retinal images when watching the rim of a blue-yellow equiluminance column.

We paid attention the amount of change for each resolution by specifying the gaze position of images, and measured accommodation and convergence eye movement when watching high-resolution images. Change of convergence angle and accommodation were like the actual depth composition in the image when images were presented in the high-resolution.

This paper reports the evolution and application potential of image sensors with high-speed brightness gradient sensors. We propose an adaptive exposure time control method using the apparent motion estimated by this sensor, and evaluate results for the change in illuminance and global / local motion.

This paper formulates minimal word-line (WL) delay time with pre-emphasis pulses to design the pulse width as a function of the overdrive voltage for large memory arrays such as 3D NAND. Circuit theory for a single RC line only with capacitance to ground and that only with coupling capacitance as well as a general case where RC lines have both grounded and coupling capacitance is discussed to provide an optimum pre-emphasis pulse width to minimize the delay time. The theory is expanded to include the cases where the resistance of the RC line driver is not negligibly small. The minimum delay time formulas of a single RC delay line and capacitive coupling RC lines was in good agreement (i.e. within 5% error) with measurement. With this research, circuit designers can estimate an optimum pre-emphasis pulse width and the delay time for an RC line in the initial design phase.

Multikernel adaptive filtering is an attractive nonlinear approach to online estimation/tracking tasks. Despite its potential advantages over its single-kernel counterpart, a use of inappropriately weighted kernels may result in a negligible performance gain. In this paper, we propose an efficient recursive kernel weighting technique for multikernel adaptive filtering to activate all the kernels. The proposed weights equalize the convergence rates of all the corresponding partial coefficient errors. The proposed weights are implemented via a certain metric design based on the weighting matrix. Numerical examples show, for synthetic and multiple real datasets, that the proposed technique exhibits a better performance than the manually-tuned kernel weights, and that it significantly outperforms the online multiple kernel regression algorithm.

We address analysis and design problems of aggregate demand response systems composed of various consumers based on controllability to facilitate to design automated demand response machines that are installed into consumers to automatically respond to electricity price changes. To this end, we introduce a controllability index that expresses the worst-case error between the expected total electricity consumption and the electricity supply when the best electricity price is chosen. The analysis problem using the index considers how to maximize the controllability of the whole consumer group when the consumption characteristic of each consumer is not fixed. In contrast, the design problem considers the whole consumer group when the consumption characteristics of a part of the group are fixed. By solving the analysis problem, we first clarify how the controllability, average consumption characteristics of all consumers, and the number of selectable electricity prices are related. In particular, the minimum value of the controllability index is determined by the number of selectable electricity prices. Next, we prove that the design problem can be solved by a simple linear optimization. Numerical experiments demonstrate that our results are able to increase the controllability of the overall consumer group.

Hyperspectral images (HSIs) are generally susceptible to various noise, such as Gaussian and stripe noise. Recently, numerous denoising algorithms have been proposed to recover the HSIs. However, those approaches cannot use spectral information efficiently and suffer from the weakness of stripe noise removal. Here, we propose a tensor decomposition method with two different constraints to remove the mixed noise from HSIs. For a HSI cube, we first employ the tensor singular value decomposition (t-SVD) to effectively preserve the low-rank information of HSIs. Considering the continuity property of HSIs spectra, we design a simple smoothness constraint by using Tikhonov regularization for tensor decomposition to enhance the denoising performance. Moreover, we also design a new unidirectional total variation (TV) constraint to filter the stripe noise from HSIs. This strategy will achieve better performance for preserving images details than original TV models. The developed method is evaluated on both synthetic and real noisy HSIs, and shows the favorable results.