No abstract

No abstract

Hate speech, quite common in the age of social media, at times harmless but can also cause mental trauma to someone or even riots in communities. Image of a religious symbol with derogatory comment or video of a man abusing a particular community, all become hate speech with its every modality (such as text, image, and audio) contributing towards it. Models based on a particular modality of hate speech post on social media are not useful, rather, we need models like multimodal fusion models that consider both image and text while classifying hate speech. Text-image fusion models are heavily parameterized, hence we propose a quaternion neural networkbased model having additional fusion components for each pair of modalities. The Model is tested on the MMHS150K twitter dataset for hate speech classification. The model shows an almost 75% reduction in parameters and also benefits us in terms of storage space and training time while being at par in terms of performance as compared to its real counterpart.

Hyperspectral image (HSI) classification is one of the important topic in the field of remote sensing. In general, HSI has to deal with complex characteristics and nonlinearity among the hyperspectral data which makes the classification task very challenging for traditional machine learning (ML) models. Recently, deep learning (DL) models have been very widely used in the classification of HSIs because of their capability to deal with complexity and nonlinearity in data. The utilization of deep learning models has been very successful and demonstrated good performance in the classification of HSIs. This paper presents a comprehensive review of deep learning models utilized in HSI classification literature and a comparison of various deep learning strategies for this topic. Precisely, the authors have categorized the literature review based upon the utilization of five most popular deep learning models and summarized their main methodologies used in feature extraction. This work may provide useful guidelines for the future research work in this area.