Deepayan Bhowmik

Johannes Scherer, Ansgar Scherp, Deepayan Bhowmik

Annotation of multimedia data by humans is time-consuming and costly, while reliable automatic generation of semantic metadata is a major challenge. We propose a framework to extract semantic metadata from automatically generated video captions. As metadata, we consider entities, the entities' properties, relations between entities, and the video category. We employ two state-of-the-art dense video captioning models with masked transformer (MT) and parallel decoding (PVDC) to generate captions for videos of the ActivityNet Captions dataset. Our experiments show that it is possible to extract entities, their properties, relations between entities, and the video category from the generated captions. We observe that the quality of the extracted information is mainly influenced by the quality of the event localization in the video as well as the performance of the event caption generation.

Oluwaseun Ajao, Deepayan Bhowmik, Shahrzad Zargari

The problem associated with the propagation of fake news continues to grow at an alarming scale. This trend has generated much interest from politics to academia and industry alike. We propose a framework that detects and classifies fake news messages from Twitter posts using hybrid of convolutional neural networks and long-short term recurrent neural network models. The proposed work using this deep learning approach achieves 82% accuracy. Our approach intuitively identifies relevant features associated with fake news stories without previous knowledge of the domain.

Nathanael L. Baisa, Deepayan Bhowmik, Andrew Wallace

Tracking a target of interest in both sparse and crowded environments is a challenging problem, not yet successfully addressed in the literature. In this paper, we propose a new long-term visual tracking algorithm, learning discriminative correlation filters and using an online classifier, to track a target of interest in both sparse and crowded video sequences. First, we learn a translation correlation filter using a multi-layer hybrid of convolutional neural networks (CNN) and traditional hand-crafted features. We combine advantages of both the lower convolutional layer which retains more spatial details for precise localization and the higher convolutional layer which encodes semantic information for handling appearance variations, and then integrate these with histogram of oriented gradients (HOG) and color-naming traditional features. Second, we include a re-detection module for overcoming tracking failures due to long-term occlusions by training an incremental (online) SVM on the most confident frames using hand-engineered features. This re-detection module is activated only when the correlation response of the object is below some pre-defined threshold. This generates high score detection proposals which are temporally filtered using a Gaussian mixture probability hypothesis density (GM-PHD) filter to find the detection proposal with the maximum weight as the target state estimate by removing the other detection proposals as clutter. Finally, we learn a scale correlation filter for estimating the scale of a target by constructing a target pyramid around the estimated or re-detected position using the HOG features. We carry out extensive experiments on both sparse and dense data sets which show that our method significantly outperforms state-of-the-art methods.