In this paper, we study the challenging problem of categorizing videos according to high-level semantics such as the existence of a particular human action or a complex event. Although extensive ...efforts have been devoted in recent years, most existing works combined multiple video features using simple fusion strategies and neglected the utilization of inter-class semantic relationships. This paper proposes a novel unified framework that jointly exploits the feature relationships and the class relationships for improved categorization performance. Specifically, these two types of relationships are estimated and utilized by imposing regularizations in the learning process of a deep neural network (DNN). Through arming the DNN with better capability of harnessing both the feature and the class relationships, the proposed regularized DNN (rDNN) is more suitable for modeling video semantics. We show that rDNN produces better performance over several state-of-the-art approaches. Competitive results are reported on the well-known Hollywood2 and Columbia Consumer Video benchmarks. In addition, to stimulate future research on large scale video categorization, we collect and release a new benchmark dataset, called FCVID, which contains 91,223 Internet videos and 239 manually annotated categories.
Item-to-item collaborative filtering ( aka. item-based CF) has been long used for building recommender systems in industrial settings, owing to its interpretability and efficiency in real-time ...personalization. It builds a user's profile as her historically interacted items, recommending new items that are similar to the user's profile. As such, the key to an item-based CF method is in the estimation of item similarities. Early approaches use statistical measures such as cosine similarity and Pearson coefficient to estimate item similarities, which are less accurate since they lack tailored optimization for the recommendation task. In recent years, several works attempt to learn item similarities from data, by expressing the similarity as an underlying model and estimating model parameters by optimizing a recommendation-aware objective function. While extensive efforts have been made to use shallow linear models for learning item similarities, there has been relatively less work exploring nonlinear neural network models for item-based CF. In this work, we propose a neural network model named Neural Attentive Item Similarity model (NAIS) for item-based CF. The key to our design of NAIS is an attention network, which is capable of distinguishing which historical items in a user profile are more important for a prediction. Compared to the state-of-the-art item-based CF method Factored Item Similarity Model (FISM) <xref ref-type="bibr" rid="ref1">1 , our NAIS has stronger representation power with only a few additional parameters brought by the attention network. Extensive experiments on two public benchmarks demonstrate the effectiveness of NAIS. This work is the first attempt that designs neural network models for item-based CF, opening up new research possibilities for future developments of neural recommender systems.
The ability to quickly recognize and learn new visual concepts from limited samples enable humans to quickly adapt to new tasks and environments. This ability is enabled by the semantic association ...of novel concepts with those that have already been learned and stored in memory. Computers can start to ascertain similar abilities by utilizing a semantic concept space. A concept space is a high-dimensional semantic space in which similar abstract concepts appear close and dissimilar ones far apart. In this paper, we propose a novel approach to one-shot learning that builds on this core idea. Our approach learns to map a novel sample instance to a concept, relates that concept to the existing ones in the concept space and, using these relationships, generates new instances, by interpolating among the concepts, to help learning. Instead of synthesizing new image instance, we propose to directly synthesize instance features by leveraging semantics using a novel auto-encoder network called dual TriNet. The encoder part of the TriNet learns to map multi-layer visual features from CNN to a semantic vector. In semantic space, we search for related concepts, which are then projected back into the image feature spaces by the decoder portion of the TriNet. Two strategies in the semantic space are explored. Notably, this seemingly simple strategy results in complex augmented feature distributions in the image feature space, leading to substantially better performance.
This paper presents a novel method of global adaptive dynamic programming (ADP) for the adaptive optimal control of nonlinear polynomial systems. The strategy consists of relaxing the problem of ...solving the Hamilton-Jacobi-Bellman (HJB) equation to an optimization problem, which is solved via a new policy iteration method. The proposed method distinguishes from previously known nonlinear ADP methods in that the neural network approximation is avoided, giving rise to significant computational improvement. Instead of semiglobally or locally stabilizing, the resultant control policy is globally stabilizing for a general class of nonlinear polynomial systems. Furthermore, in the absence of the a priori knowledge of the system dynamics, an online learning method is devised to implement the proposed policy iteration technique by generalizing the current ADP theory. Finally, three numerical examples are provided to validate the effectiveness of the proposed method.
The construction of controlled biomacromolecular assemblies has become a thriving area of supramolecular chemistry. In this context, cucurbiturils (CBs), a class of macrocyclic receptors having ...robust skeletons, hydrophobic cavities, and carbonyl‐laced portals, have been drawn into the limelight because of their advantageous molecular recognition characteristics with a variety of biomacromolecules, including peptides, nucleic acids, and proteins. In this minireview, we focus on the impressive advances in CB‐based biomacromolecular assemblies, such as in biosensors and assays, the regulation of biochemical reactions, and the treatment of serious diseases. CB‐promoted subcellular bioimaging has also been demonstrated in different organelles. The case studies presented herein demonstrate the numerous applications, from fundamental research to translational applications, of diverse CB‐based supra/biomacromolecular architectures.
This minireview highlights the recent progress in and emerging applications of cucurbituril‐based biomacromolecular assemblies with peptides, nucleic acids, and proteins. This rapidly developing area involves precise control over intermolecular communication at multidimensional levels and holds great promise for the creation of innovative biomaterials and therapeutic methods.
Li‐based batteries are a hot research topic because they are the most popular energy storage system for high energy‐density devices. As an important component of the battery, the current collectors ...in both cathode and anode should be well designed. Herein, the design of 3D current collectors for Li‐based batteries is considered, including 3D metal‐based and carbon‐based current collectors. The progress in nanotechnology provides appropriate 3D current collectors characterized by highly efficient morphologies and architectures. In particular, 3D current collectors with different morphology are classified. Critical factors of current collectors that affect the electrochemical performance of Li‐based batteries are comprehensively debated. Finally, conclusion and perspectives of the future research in this field are discussed.
Building up a three‐dimensional current collector can simultaneously optimize the conductive network in the electrochemically active layers and mitigate the volume change during cycling, which leads to enhanced energy density, power density, and cycle stability. Inspiration for further exploitation of the current collectors for Li‐based batteries is given and batteries based on other electrochemistry are considered.
The Keap1–Nrf2–ARE ((Kelch‐like ECH‐Associating protein 1) nuclear factor erythroid 2 related factor 2‐antioxidant response element) pathway is one of the most important defense mechanisms against ...oxidative and/or electrophilic stresses, and it is closely associated with inflammatory diseases, including cancer, neurodegenerative diseases, cardiovascular diseases, and aging. In recent years, progress has been made in strategies aimed at modulating the Keap1–Nrf2–ARE pathway. The Nrf2 activator DMF (Dimethylfumarates) has been approved by the FDA as a new first‐line oral drug to treat patients with relapsing forms of multiple sclerosis, while a phase 3 study of another promising candidate, CDDO‐Me, was terminated for safety reasons. Directly inhibiting Keap1–Nrf2 protein–protein interactions as a novel Nrf2‐modulating strategy has many advantages over using electrophilic Nrf2 activators. The development of Keap1–Nrf2 protein–protein interaction inhibitors has become a topic of intense research, and potent inhibitors of this target have been identified. In addition, inhibiting Nrf2 activity has attracted an increasing amount of attention because it may provide an alternative cancer therapy. This review summarizes the molecular mechanisms and biological functions of the Keap1–Nrf2–ARE system. The main focus of this review is on recent progress in studies of agents that target the Keap1–Nrf2–ARE pathway and the therapeutic applications of such agents.
Plant phenotyping has been recognized as a bottleneck for improving the efficiency of breeding programs, understanding plant-environment interactions, and managing agricultural systems. In the past ...five years, imaging approaches have shown great potential for high-throughput plant phenotyping, resulting in more attention paid to imaging-based plant phenotyping. With this increased amount of image data, it has become urgent to develop robust analytical tools that can extract phenotypic traits accurately and rapidly. The goal of this review is to provide a comprehensive overview of the latest studies using deep convolutional neural networks (CNNs) in plant phenotyping applications. We specifically review the use of various CNN architecture for plant stress evaluation, plant development, and postharvest quality assessment. We systematically organize the studies based on technical developments resulting from imaging classification, object detection, and image segmentation, thereby identifying state-of-the-art solutions for certain phenotyping applications. Finally, we provide several directions for future research in the use of CNN architecture for plant phenotyping purposes.