This work investigates the unexplored usability of self-supervised representation learning in the direction of functional knowledge transfer. In this work, functional knowledge transfer is achieved by joint optimization of self-supervised learning pseudo task and supervised learning task, improving supervised learning task performance. Recent progress in self-supervised learning uses a large volume of data, which becomes a constraint for its applications on small-scale datasets. This work shares a simple yet effective joint training framework that reinforces human-supervised task learning by learning self-supervised representations just-in-time and vice versa. Experiments on three public datasets from different visual domains, Intel Image, CIFAR, and APTOS, reveal a consistent track of performance improvements on classification tasks during joint optimization. Qualitative analysis also supports the robustness of learnt representations. Source code and trained models are available on GitHub1.

Presentation Attacks (PAs) are a common spoofing mechanism in biometric authentications, especially iris-based models. The detection of these attacks is useful for distinguishing whether a sensor is presented with a live biometric or impersonated biometric through a recording, printout or spoof In recent studies, Convolutional Neural Networks have shown exceptional performance in detecting these attacks. In this paper, we propose an attention-based iris PA detection (PAD) termed d-CBAM that uses a convolution block attention mechanism introduced between the dense blocks of DenseNet. The core of this work is inspired by the use of DenseNet as a feature extractor i.e, feature maps from the last dense block are taken and passed to the attention maps. We have tested d-CBAM on the benchmark Clarkson, Notre Dame and NDCLD15 datasets, over which d-CBAM has shown better results in comparison to some traditional PAD solutions such as DenseNet, Spoof Net and Meta-Fusion. The error metrics (APCER and BPCER) were also noted to be competitive with the state-of-the-art.

Recommendation systems (RSs) have garnered immense interest for applications in e-commerce and digital media. Traditional approaches in RSs include such as collaborative filtering (CF) and content-based filtering (CBF) through these approaches that have certain limitations, such as the necessity of prior user history and habits for performing the task of recommendation. To minimize the effect of such limitation, this article proposes a hybrid RS for the movies that leverage the best of concepts used from CF and CBF along with sentiment analysis of tweets from microblogging sites. The purpose to use movie tweets is to understand the current trends, public sentiment, and user response of the movie. Experiments conducted on the public database have yielded promising results.

The text recognition system for natural images or video frames containing multilingual text needs a method to first identify the written script and then recognize the word in the identified script. However, the occurrence of some scripts is rare as compared to others. Due to the availability of a few samples of the rare script, the supervised learning of the deep neural networks is difficult. To overcome this problem, we have proposed a zero-shot learning based method for script identification. We have also proposed architecture for script identification which fuses the global feature vector and the semantic embedding vector. The semantic embedding of the script is obtained by using the spatial dependency of the stroke's sequence via the recurrent neural network. The proposed architecture shows superior results as compared to the baseline approaches.