Search

With the rapid growth of multimedia data on the Internet, there has been a rapid rise in the demand for visual–textual cross-media retrieval between images and sentences. However, the heterogeneous property of visual and textual data brings huge challenges to measure the cross-media similarity for retrieval. Although existing methods have achieved great progress with the strong learning ability of the deep neural network, they rely heavily on the scale of training data with manual annotation, that is, either pairwise image–sentence annotation or category annotation as supervised information for visual–textual correlation learning, which are extremely labor and time consuming to collect. Without any pairwise or category annotation, it is highly challenging to construct a correlation between images and sentences due to their inconsistent distributions and representations. But people can naturally understand the correlation between visual and textual data in high-level semantic, and those images and sentences containing the same group of semantic concepts can be easily matched in human brain. Inspired by the above human cognitive process, this article proposes an unsupervised visual–textual correlation learning (UVCL) approach to construct correlations without any manual annotation. The contributions are summarized as follows: 1) unsupervised semantic-guided cross-media correlation mining is proposed to bridge the heterogeneous gap between visual and textual data. We measure the semantic matching degree between images and sentences, and generate descriptive sentences according to the concepts extracted from images to further augment the training data in an unsupervised manner. Therefore, the approach can exploit the semantic knowledge within both visual and textual data to reduce the gap between them for further correlation learning and 2) unsupervised visual–textual fine-grained semantic alignment is proposed to learn cross-media correlation by aligning the fine-grained visual local patches and textual keywords with fine-grained soft attention as well as semantic-guided hard attention, and the results can effectively highlight the fine-grained semantic information within both images and sentences to boost visual–textual alignment. Extensive experiments are conducted to perform visual–textual cross-media retrieval in unsupervised setting without any manual annotation on two widely used datasets, namely, Flickr-30K and MS-COCO, which verify the effectiveness of our proposed UVCL approach. [ABSTRACT FROM AUTHOR]

A novel post-oxidation annealing (POA) process with supercritical N2O (SCN2O) fluid is reported to be highly effective in improving the interface properties of the SiO2/4H–silicon carbide (SiC) (0001) systems. After SCN2O POA, the interface state density reduces to 2.8 × 1011 eV−1cm−2, which is about 3.5 times lower than that after a traditional high-temperature N2O POA process. Meanwhile, the highest oxide critical electric field shows an increase of 18.19% and the near-interfacial oxide traps is reduced by 69.90% compared with that after N2O POA process. The process temperature is as low as 120 °C. The significantly reduced processing temperature avoids additional defect generation while the supercritical state provides a stronger nitridation effect. SCN2O annealing is a promising candidate for POA process toward high-performance SiC power metal-oxide-semiconductor field effect transistors (MOSFETs). [ABSTRACT FROM AUTHOR]

Considering potential applications related to superconductivity and aerospace (typically less than 100 K), in this article, the temperature dependence of silicon carbide (SiC) power diodes is systematically characterized and analyzed over a wide temperature range of 90–478 K, especially focusing on cryogenic temperature. First, the static performance degradation mechanism of SiC diodes is established in an ultrawide temperature range, including forward/reverse I-V characteristics and junction capacitance (Cj) characteristics. Second, the reverse recovery characteristics are achieved, including peak reverse recovery current (Irm), reverse recovery charge (Qrr), and switching energy (Esw), clarifying a clearer internal relationship between reverse recovery and junction temperature. Meanwhile, the aforementioned critical parameters are further analyzed on an electrical scale with normal atmosphere temperature, including switching speed range of 62.3–2054.8 A/μs, load current range of 6–30 A, and dc voltage range of 400–1000 V. Third, based on newly proposed power loss analysis method, the continuous operation performance of SiC diodes is quantified and analyzed in actual cryogenic converters. The excellent temperature dependence indicates that SiC diodes have great superiority for extreme applications. Importantly, SiC mosfet's body diode shows the great potential to operate as a freewheeling diode in the compact converter, especially at cryogenic temperature. [ABSTRACT FROM AUTHOR]

Multi-media data including image, video, text, audio, and 3D model, has been fast emerging on the Internet. Jointly correlating the data of various media types is a challenging task. With the considerable learning ability of deep network, existing works mainly construct multi-pathway network to learn cross-media correlation, where each pathway is for one media type. However, with number of media types increasing, existing methods face the problems of high repetition and complexity, leading to overfitting and poor generalization ability, which makes adverse effect on correlation learning. For addressing the above issues, we propose cross-media deep compression and regularization (CDCR) approach for quintuple-media joint correlation learning: 1) cross-media partial weight-sharing networks is proposed, where a part of parameters are commonly shared among multiple pathways, to exploit common characteristics across different media types for capturing intrinsic cross-media correlation; 2) we propose media-adaptive network pruning to drop connections between weakly-correlated neurons, which can emphasize media-specific characteristics adaptively; and 3) cross-media network regularization is proposed to utilize relationships among quintuple-media data, which can guarantee generalization ability and enhance intra-media and inter-media correlation. The experiments verify the effectiveness of our approach, which outperforms the state-of-the-art methods on two very challenging datasets, including a large-scale dataset PKU XMediaNet with more than 100 000 quintuple-media instances. [ABSTRACT FROM AUTHOR]

Conventional switched-mode power supplies have intrinsic instantaneous power pulsation at the switching frequency thus require bulky filters. To improve the power density, this paper proposes a concept named the mixed analog–digital (MAD) which can be applied as dc–dc converters. By inserting an analog voltage component between the load and source, the output voltage naturally has much smaller fluctuation thereby much smaller passive filter is required. Simulations and experiments validate that the proposed MAD concept can be applied as dc–dc converters to significantly increase the power density. [ABSTRACT FROM AUTHOR]

The rapidly developing information technology leads to a fast growth of visual and textual contents, and it comes with huge challenges to make correlation and perform cross-media retrieval between images and sentences. Existing methods mainly explore cross-media correlation from either global-level instances as the whole images and sentences, or local-level fine-grained patches as the discriminative image regions and key words, which ignore the complementary information from the relation between local-level fine-grained patches. Naturally, relation understanding is highly important for learning cross-media correlation. People focus on not only the alignment between discriminative image regions and key words, but also their relations lying in the visual and textual context. Therefore, in this paper, we propose Multi-level Adaptive Visual-textual Alignment (MAVA) approach with the following contributions. First, we propose cross-media multi-pathway fine-grained network to extract not only the local fine-grained patches as discriminative image regions and key words, but also visual relations between image regions as well as textual relations from the context of sentences, which contain complementary information to exploit fine-grained characteristics within different media types. Second, we propose visual-textual bi-attention mechanism to distinguish the fine-grained information with different saliency from both local and relation levels, which can provide more discriminative hints for correlation learning. Third, we propose cross-media multi-level adaptive alignment to explore global, local and relation alignments. An adaptive alignment strategy is further proposed to enhance the matched pairs of different media types, and discard those misalignments adaptively to learn more precise cross-media correlation. Extensive experiments are conducted to perform image-sentence matching on 2 widely-used cross-media datasets, namely Flickr-30K and MS-COCO, comparing with 10 state-of-the-art methods, which can fully verify the effectiveness of our proposed MAVA approach. [ABSTRACT FROM AUTHOR]

The heterogeneity gap leads to inconsistent distributions and representations between image and text, which rises a challenging task to measure their similarities and construct cross-media correlation between them. The existing works mainly model the cross-media correlation in a common subspace, which causes insufficient correlation modeling in such third-party subspace with intermediate unidirectional transformation. Inspired by the recent advances of neural machine translation, which aims to establish a corresponding relationship between two entirely different languages, we can naturally discover that it has striking common characteristic with cross-media correlation learning to consider image and text as bilingual pairs, where the image is treated as a special kind of language to provide visual description, so that bidirectional transformation can be conducted between image and text to effectively explore cross-media correlation in the feature space of each media type. Thus, we propose a reinforced cross-media bidirectional translation (RCBT) approach to model the correlation between visual and textual descriptions. First, cross-media bidirectional translation mechanism is proposed to conduct direct transformation between the bilingual pairs of visual and textual descriptions bidirectionally, where the cross-media correlation can be effectively captured in both feature spaces of image and text through bidirectional translation training. Second, cross-media context-aware network with residual attention is proposed to exploit the rich spatial and temporal context hints with cross-media convolutional recurrent neural network, which can lead to more precise correlation learning for promoting bidirectional translation process. Third, cross-media reinforcement learning is proposed to perform a two-agent communication game played as a round between image and text to boost the bidirectional translation process, and we further extract inter-media and intra-media reward signals to provide complementary clues for learning cross-media correlation. Extensive experiments are conducted on cross-media retrieval to verify the effectiveness of our proposed RCBT approach, compared with 11 state-of-the-art methods on three cross-media datasets. [ABSTRACT FROM AUTHOR]

In this article, the static, dynamic, and short-circuit properties of 1.2-kV commercial 4H-SiC planar and trench gate metal–oxide–semiconductor field-effect transistors (MOSFETs) are compared and analyzed in a wide temperature range from 90 to 493 K. The temperature-dependent specific ON-resistance (${R}_{\text {sp}- \mathrm{\scriptscriptstyle ON}}$) and threshold voltage (${V}_{\text {th}}$) are analyzed in relation to the density of the interface state. The turn-on rise and turn-off fall times (${T}_{r}$ and ${T}_{f}$) and the corresponding energy loss (${E}_{r}$ and ${E}_{f}$) are extracted from a double-pulse test from cryogenic to high temperature and analyzed. The short-circuit capability of the two structures is studied at low temperature for the first time. The comprehensive comparison and analysis of the planar and trench gate MOSFET versus temperature in this work show the importance to study applications with SiC MOSFETs in a wide temperature range, especially for the cryogenic temperatures. [ABSTRACT FROM AUTHOR]

Due to the superior material properties, SiC mosfet is a promising candidate switching device for high power density and high efficiency power conversion system. The robustness of switching device under extreme temperature condition becomes a crucial factor to ensure power conversion system safely and continuously operating. In this paper, the temperature dependence of dynamic performance of 1.2-kV 4H-SiC power mosfets is systematically characterized over such wide temperature range of 90–493 K and compared with 1.2-kV Si IGBT by a layout optimized double pulse tester (DPT). The degradation of dynamic on-resistance related interface traps is analyzed specially and the energy loss caused by degradation is quantified at cryogenic temperatures. Besides, to validate the performance of SiC mosfet under safely and continuously operating conditions for cryogenic temperature application, a hard switched non-isolated dc–dc buck converter is designed and tested to estimate temperature dependence of conversion efficiency under temperature range of 90–290 K. Moreover, the further characterizations are conducted with gate resistance range of 2–20 Ω, load current range of 3–30 A, and converter output current of 5–22.5 A under different switching frequency (up to 150 kHz) to validate high power and high frequency application potential of SiC mosfet. [ABSTRACT FROM AUTHOR]

Multimedia data with various modalities, such as image and text, are huge in quantity but have inconsistent distribution and representation. Many works have been done to break the boundary between image and text to measure their correlation. However, they focus on either the transformation to common subspace or the unidirectional generation from one to another individually, which cannot fully explore their interactions. It is noted that the bidirectional generation between image and text not only can provide complementary hints and mutually boost to learn cross-modal correlation but also cross-modal correlation learning can feed back to give comprehensive clues for promoting the cross-modal generation process. Therefore, we have the motivation that information transmission between image and text should be treated as a circular process, which aims to fully understand their latent correlation, and further realize cross-modal generation to produce both realistic images and text descriptions in a unified framework. In this paper, we propose the cross-modal circular correlation learning approach to perform both cross-modal correlation learning and generation simultaneously through an efficient circular learning training procedure. First, we propose the cross-modal circular learning model to perform an image-to-text caption and text-to-image synthesis circularly and learn common representation as a round-trip bridge, which can realize efficient interactions to fully exploit latent cross-modal correlations. Second, a unified bidirectional framework is proposed to conduct cross-modal mutual generation and is trained in an efficient circular process to enhance the generative ability of common representation, which can feed back circularly to further promote cross-modal correlation learning. In summary, we simultaneously perform cross-modal retrieval, image-to-text caption, and text-to-image synthesis in a unified framework with the circular learning process, which has high scalability and generality to realize universal cognition on the cross-modal data. We conduct extensive experiments to not only evaluate the correlation performance by cross-modal retrieval but also to show the generation effectiveness of both image caption and synthesis on the MS-COCO dataset. [ABSTRACT FROM AUTHOR]

In this paper, an improved 4H-SiC U-shaped trench-gate metal–oxide–semiconductor field-effect transistors (UMOSFETs) structure with low ON-resistance (${R}_{ \mathrm{\scriptscriptstyle ON}}$) and switching energy loss is proposed. The novel structure features an added n-type region, which reduces ON-resistance of the device significantly while maintaining the breakdown voltage (${V}_{\textsf {BR}}$). In addition, the gate of the improved structure is designed as a p-n junction to reduce the switching energy loss. Simulations by Sentaurus TCAD are carried out to reveal the working mechanism of this improved structure. For the static performance, the ON-resistance and the figure of merit (FOM $= {V}_{\textsf {BR}}^{\textsf {2}}/{R}_{ \mathrm{\scriptscriptstyle ON}}$) of the optimized structure are improved by 40% and 44%, respectively, as compared to a conventional trench MOSFET without the added n-type region and modified gate. For the dynamic performance, the turn-on time (${T}_{ \mathrm{\scriptscriptstyle ON}}$) and turn-off time (${T}_{ \mathrm{\scriptscriptstyle OFF}}$) of the proposed structure are both shorter than that of the conventional structure, bringing a 43% and 30% reduction in turn-on energy loss and total switching energy loss (${E}_{\mathbf {SW}}$). [ABSTRACT FROM AUTHOR]

Cross-modal retrieval has become a highlighted research topic for retrieval across multimedia data such as image and text. A two-stage learning framework is widely adopted by most existing methods based on deep neural network (DNN): The first learning stage is to generate separate representation for each modality and the second learning stage is to get the cross-modal common representation. However the existing methods have three limitations: 1) In the first learning stage they only model intramodality correlation but ignore intermodality correlation with rich complementary context. 2) In the second learning stage they only adopt shallow networks with single-loss regularization but ignore the intrinsic relevance of intramodality and intermodality correlation. 3) Only original instances are considered while the complementary fine-grained clues provided by their patches are ignored. For addressing the above problems this paper proposes a cross-modal correlation learning (CCL) approach with multigrained fusion by hierarchical network and the contributions are as follows: 1) In the first learning stage CCL exploits multilevel association with joint optimization to preserve the complementary context from intramodality and intermodality correlation simultaneously. 2) In the second learning stage a multitask learning strategy is designed to adaptively balance the intramodality semantic category constraints and intermodality pairwise similarity constraints. 3) CCL adopts multigrained modeling which fuses the coarse-grained instances and fine-grained patches to make cross-modal correlation more precise. Comparing with 13 state-of-the-art methods on 6 widely-used cross-modal datasets the experimental results show our CCL approach achieves the best performance. [ABSTRACT FROM PUBLISHER]