Cross-modal semantic autoencoder with embedding consensus

Cross-modal retrieval has become a topic of popularity, since multi-data is heterogeneous and the similarities between different forms of information are worthy of attention. Traditional single-modal methods reconstruct the original information and lack of considering the semantic similarity between different data. In this work, a cross-modal semantic autoencoder with embedding consensus (CSAEC) is proposed, mapping the original data to a low-dimensional shared space to retain semantic information. Considering the similarity between the modalities, an automatic encoder is utilized to associate the feature projection to the semantic code vector. In addition, regularization and sparse constraints are applied to low-dimensional matrices to balance reconstruction errors. The high dimensional data is transformed into semantic code vector. Different models are constrained by parameters to achieve denoising. The experiments on four multi-modal data sets show that the query results are improved and effective cross-modal retrieval is achieved. Further, CSAEC can also be applied to fields related to computer and network such as deep and subspace learning. The model breaks through the obstacles in traditional methods, using deep learning methods innovatively to convert multi-modal data into abstract expression, which can get better accuracy and achieve better results in recognition.

The status of conventional metaphorical meaning in the L2 lexicon

This paper investigates how L2 speakers of English process conventional metaphorical expressions. While much of the literature on L2 processing of figurative expressions focuses on idioms only, the aim of this paper is to investigate how L2 speakers process conventional metaphorical expressions. The results of a cross-modal semantic priming task show that conventional metaphors have a special status in comparison to literal language in the L2 lexicon. The differences in reaction times show that L2 speakers are aware of the connections between literal primes and targets, resulting in slower reaction times, while this effect is not found in the metaphorical condition. This demonstrates that even when metaphorical language is very conventional, it can cause difficulties for L2 speakers. Furthermore, these results show that conventional metaphorical expressions can pose a semantic and pragmatic challenge for language learners, thus creating a need for explicit teaching of metaphorical meanings of polysemous words.

Survey and Analysis on Machine Learning Approaches for Image Annotation

In current years, a large amount of image data is being collected worldwide, which is majorly generated by corporate organizations, health industry and social networking sites. With the strength of substantial level depiction of images, Annotating image has numerous applications not only in image understanding and analysis but also in some of the concern domain like medical research, rural and urban management. Automatic Image Annotation (AIA) has been raised since the late 1990s due to inherent weaknesses of manual image annotation. In this paper, a deep review of the most recent stage in the development of AIA methods is presented by synthesizing 32 literatures published during the past decades. We classify AIA methods into five categories: 1) Kernel Logistic Regression (KLR), 2) Tri-relational Graph (TG), 3) Semantically Regularised CNN- RNN (S-CNN-RNN), 4) Label Correlation guided Deep Multi-view (LCDM), and 5) Multi-Modal Semantic Hash Learning (MMSHL). Considering inspiration on the basis of main idea, framework of model, complexity of computation, time complexity and accuracy in annotation Comparative analysis for various AIA methods are done.