The science and technology of ultracapacitors are reviewed for a number of electrode materials, including carbon, mixed metal oxides, and conducting polymers. More work has been done using microporous carbons than with the other materials and most of the commercially available devices use carbon electrodes and an organic electrolytes. The energy density of these devices is 3¯5 Wh/kg with a power density of 300¯500 W/kg for high efficiency (90¯95%) charge/discharges. Projections of future developments using carbon indicate that energy densities of 10 Wh/kg or higher are likely with power densities of 1¯2 kW/kg. A key problem in the fabrication of these advanced devices is the bonding of the thin electrodes to a current collector such the contact resistance is less than 0.1 cm2. Special attention is given in the paper to comparing the power density characteristics of ultracapacitors and batteries. The comparisons should be made at the same charge/discharge efficiency.

Ultracapacitors: Why, How, and Where is the Technology

Carbon dioxide (CO2) capture using solid sorbents has been recognized as a very promising technology that has attracted intense attention from both academic and industrial fields in the last decade. It is astonishing that around 2000 papers have been published from 2011 to 2014 alone, which is less than three years after our first review paper in this journal on solid CO2 sorbents was published. In this short period, much progress has been made and the major research focus has more or less changed. Therefore, we feel that it is necessary to give a timely update on solid CO2 capture materials, although we still have to keep some important literature results published in the past years so as to keep the good continuity. We believe this work will benefit researchers working in both academic and industrial areas. In this paper, we still organize the CO2 sorbents according to their working temperatures by classifying them as such: (1) low-temperature ( 400 °C). Since the sorption capacity, kinetics, recycling stability and cost are important parameters when evaluating a sorbent, these features will be carefully considered and discussed. In addition, due to the huge amounts of cost-effective CO2 sorbents demanded and the importance of waste resources, solid CO2 sorbents prepared from waste resources and their performance are reviewed. Finally, the techno-economic assessments of various CO2 sorbents and technologies in real applications are briefly discussed.

Recent advances in solid sorbents for CO2 capture and new development trends

A family of loss functions built on pair-based computation have been proposed in the literature which provide a myriad of solutions for deep metric learning. In this pa-per, we provide a general weighting framework for under-standing recent pair-based loss functions. Our contributions are three-fold: (1) we establish a General Pair Weighting (GPW) framework, which casts the sampling problem of deep metric learning into a unified view of pair weighting through gradient analysis, providing a powerful tool for understanding recent pair-based loss functions; (2) we show that with GPW, various existing pair-based methods can be compared and discussed comprehensively, with clear differences and key limitations identified; (3) we propose a new loss called multi-similarity loss (MS loss) under the GPW,which is implemented in two iterative steps (i.e., mining and weighting). This allows it to fully consider three similarities for pair weighting, providing a more principled approach for collecting and weighting informative pairs. Finally, the proposed MS loss obtains new state-of-the-art performance on four image retrieval benchmarks, where it outperforms the most recent approaches, such as ABE[14] and HTL[4], by a large margin, e.g.,60.6%→65.7%on CUB200,and 80.9%→88.0%on In-Shop Clothes Retrieval datasetat Recall@1.

/pdf/multi-similarity-loss-with-general-pair-weighting-for-deep-2q6h7ks1ee.pdf

Multi-Similarity Loss With General Pair Weighting for Deep Metric Learning

Abstract Electrochemical surface oxidation of carbon black Vulcan XC-72 and multiwalled carbon nanotube (MWNT) has been compared following potentiostatic treatments up to 168 h under condition simulating PEMFC cathode environment (60 °C, N2 purged 0.5 M H2SO4, and a constant potential of 0.9 V). The subsequent electrochemical characterization at different treatment time intervals suggests that MWNT is electrochemically more stable than Vulcan XC-72 with less surface oxide formation and 30% lower corrosion current under the investigated condition. As a result of high corrosion resistance, MWNT shows lower loss of Pt surface area and oxygen reduction reaction activity when used as fuel cell catalyst support.

http://ma.ecsdl.org/content/MA2005-02/33/1168.full.pdf

Durability Investigation of Carbon Nanotube as Catalyst Support for Proton Exchange Membrane Fuel Cell Electrode

Anomaly detection is an important problem that has been well-studied within diverse research areas and application domains. The aim of this survey is two-fold, firstly we present a structured and comprehensive overview of research methods in deep learning-based anomaly detection. Furthermore, we review the adoption of these methods for anomaly across various application domains and assess their effectiveness. We have grouped state-of-the-art research techniques into different categories based on the underlying assumptions and approach adopted. Within each category we outline the basic anomaly detection technique, along with its variants and present key assumptions, to differentiate between normal and anomalous behavior. For each category, we present we also present the advantages and limitations and discuss the computational complexity of the techniques in real application domains. Finally, we outline open issues in research and challenges faced while adopting these techniques.

Deep Learning for Anomaly Detection: A Survey.

We present a generative framework for generalized zero-shot learning where the training and test classes are not necessarily disjoint. Built upon a variational autoencoder based architecture, consisting of a probabilistic encoder and a probabilistic conditional decoder, our model can generate novel exemplars from seen/unseen classes, given their respective class attributes. These exemplars can subsequently be used to train any off-the-shelf classification model. One of the key aspects of our encoder-decoder architecture is a feedback-driven mechanism in which a discriminator (a multivariate regressor) learns to map the generated exemplars to the corresponding class attribute vectors, leading to an improved generator. Our model's ability to generate and leverage examples from unseen classes to train the classification model naturally helps to mitigate the bias towards predicting seen classes in generalized zero-shot learning settings. Through a comprehensive set of experiments, we show that our model outperforms several state-of-the-art methods, on several benchmark datasets, for both standard as well as generalized zero-shot learning.

/pdf/generalized-zero-shot-learning-via-synthesized-examples-1tf6w0e5b2.pdf

Generalized Zero-Shot Learning via Synthesized Examples

Zero shot learning in Image Classification refers to the setting where images from some novel classes are absent in the training data but other information such as natural language descriptions or attribute vectors of the classes are available. This setting is important in the real world since one may not be able to obtain images of all the possible classes at training. While previous approaches have tried to model the relationship between the class attribute space and the image space via some kind of a transfer function in order to model the image space correspondingly to an unseen class, we take a different approach and try to generate the samples from the given attributes, using a conditional variational autoencoder, and use the generated samples for classification of the unseen classes. By extensive testing on four benchmark datasets, we show that our model outperforms the state of the art, particularly in the more realistic generalized setting, where the training classes can also appear at the test time along with the novel classes.

/pdf/a-generative-model-for-zero-shot-learning-using-conditional-197izu0idy.pdf

A Generative Model for Zero Shot Learning Using Conditional Variational Autoencoders

A Generative Model For Zero Shot Learning Using Conditional Variational Autoencoders

Sketch-based image retrieval (SBIR) is the task of retrieving images from a natural image database that correspond to a given hand-drawn sketch. Ideally, an SBIR model should learn to associate components in the sketch (say, feet, tail, etc.) with the corresponding components in the image having similar shape characteristics. However, current evaluation methods simply focus only on coarse-grained evaluation where the focus is on retrieving images which belong to the same class as the sketch but not necessarily having the same shape characteristics as in the sketch. As a result, existing methods simply learn to associate sketches with classes seen during training and hence fail to generalize to unseen classes. In this paper, we propose a new benchmark for zero-shot SBIR where the model is evaluated on novel classes that are not seen during training. We show through extensive experiments that existing models for SBIR that are trained in a discriminative setting learn only class specific mappings and fail to generalize to the proposed zero-shot setting. To circumvent this, we propose a generative approach for the SBIR task by proposing deep conditional generative models that take the sketch as an input and fill the missing information stochastically. Experiments on this new benchmark created from the “Sketchy” dataset, which is a large-scale database of sketch-photo pairs demonstrate that the performance of these generative models is significantly better than several state-of-the-art approaches in the proposed zero-shot framework of the coarse-grained SBIR task.

/pdf/a-zero-shot-framework-for-sketch-based-image-retrieval-un8mjjjv99.pdf

A Zero-Shot Framework for Sketch Based Image Retrieval

We present a generative framework for zero-shot action recognition where some of the possible action classes do not occur in the training data. Our approach is based on modeling each action class using a probability distribution whose parameters are functions of the attribute vector representing that action class. In particular, we assume that the distribution parameters for any action class in the visual space can be expressed as a linear combination of a set of basis vectors where the combination weights are given by the attributes of the action class. These basis vectors can be learned solely using labeled data from the known (i.e., previously seen) action classes, and can then be used to predict the parameters of the probability distributions of unseen action classes. We consider two settings: (1) Inductive setting, where we use only the labeled examples of the seen action classes to predict the unseen action class parameters; and (2) Transductive setting which further leverages unlabeled data from the unseen action classes. Our framework also naturally extends to few-shot action recognition where a few labelled examples from unseen classes are available. Our experiments on benchmark datasets (UCF101, HMDB51 and Olympic) show significant performance improvements as compared to various baselines, in both standard zero-shot (disjoint seen and unseen classes) and generalized zero-shot learning settings.

Ashish Mishra

Papers

Generalized Zero-Shot Learning via Synthesized Examples

A Generative Model for Zero Shot Learning Using Conditional Variational Autoencoders

A Generative Model For Zero Shot Learning Using Conditional Variational Autoencoders

A Zero-Shot Framework for Sketch Based Image Retrieval

A Generative Approach to Zero-Shot and Few-Shot Action Recognition