Elucidation of aniline adsorption-desorption mechanism on various organo-mineral complexes.

Complexes formed by organic matter and clay minerals, which are active components of soil systems, play an important role in the migration and transformation of pollutants in nature. In this study, humic-acid-montmorillonite (HA-MT) and humic-acid-kaolin (HA-KL) complexes were prepared, and their structures before and after the adsorption of aniline were analyzed. The aniline adsorption-desorption characteristics of complexes with different clay minerals and varying HA contents were explored using the static adsorption-desorption equilibrium method. Compared with the pristine clay minerals, the flaky and porous structure of the complexes and the aromaticity were enhanced. The adsorption of aniline on the different clay mineral complexes was nonlinear, and the adsorption capacity increased with increasing HA content. Additionally, the adsorption capacity of HA-MT was higher than that of HA-KL. After adsorption, the specific surface area of the complexes decreased, the surfaces became more complicated, and the aromaticity decreased because aniline is primarily adsorption onto the complexes via aromatic rings. Aniline was adsorbed onto the complexes via spontaneous exothermic physical adsorption. The amount of aniline desorbed from the complexes increased with increasing HA content, and a lag in desorption was observed, with a greater lag for HA-KL than for HA-MT.

A semi-supervised zero-shot image classification method based on soft-target.

Zero-shot learning (ZSL) aims at training a classification model with data only from seen categories to recognize data from disjoint unseen categories. Domain shift and generalization capability are two fundamental challenges in ZSL. In this paper, we address them with a novel Soft-Target Semi-supervised Classification (STSC) model. Specifically, an autoencoder network is leveraged, where both labeled seen data from the seen categories and unlabeled ancillary data collected from Internet or other datasets are employed as two branches, respectively. For the branch of labeled seen data, side information are employed as the latent vectors to separately connect the input of encoder and the output of decoder. In this way, visual and side information are implicitly aligned. For the branch of unlabeled ancillary data, it explicitly strengthens the reconstruction ability of the network. Meanwhile, these ancillary data can be viewed as a smooth to the domain distribution, which contributes to the alleviation of the domain shift problem. To further guarantee the generation ability, a Softmax-T loss function is proposed by making full use of the soft target. Extensive experiments on three benchmark datasets show the superiority of the proposed approach under tasks of both traditional zero-shot learning and generalized zero-shot learning.

Deep Ranking for Image Zero-Shot Multi-Label Classification.

During the past decade, both multi-label learning and zero-shot learning have attracted huge research attention, and significant progress has been made. Multi-label learning algorithms aim to predict multiple labels given one instance, while most existing zero-shot learning approaches target at predicting a single testing label for each unseen class via transferring knowledge from auxiliary seen classes to target unseen classes. However, relatively less effort has been made on predicting multiple labels in the zero-shot setting, which is nevertheless a quite challenging task. In this work, we investigate and formalize a flexible framework consisting of two components, i.e., visual-semantic embedding and zero-shot multi-label prediction. First, we present a deep regression model to project the visual features into the semantic space, which explicitly exploits the correlations in the intermediate semantic layer of word vectors and makes label prediction possible. Then, we formulate the label prediction problem as a pairwise one and employ Ranking SVM to seek the unique multi-label correlations in the embedding space. Furthermore, we provide a transductive multi-label zeroshot prediction approach that exploits the testing data manifold structure. We demonstrate the effectiveness of the proposed approach on three popular multi-label datasets with state-of-theart performance obtained on both conventional and generalized ZSL settings.