This paper describes our submission to SemEval-2019 Task 7: RumourEval: Determining Rumor Veracity and Support for Rumors. We participated in both subtasks. The goal of subtask A is to classify the type of interaction between a rumorous social media post and a reply post as support, query, deny, or comment. The goal of subtask B is to predict the veracity of a given rumor. For subtask A, we implement a CNN-based neural architecture using ELMo embeddings of post text combined with auxiliary features and achieve a F 1 -score of 44.6%. For subtask B, we employ a MLP neural network leveraging our estimates for subtask A and achieve a F 1 -score of 30.1% (second place in the competition). We provide results and analysis of our system performance and present ablation experiments.

To detect and classify vehicles in omnidirectional videos, we propose an approach based on the shape (silhouette) of the moving object obtained by background subtraction. Different from other shape-based classification techniques, we exploit the information available in multiple frames of the video. We investigated two different approaches for this purpose. One is combining silhouettes extracted from a sequence of frames to create an average silhouette, the other is making individual decisions for all frames and use consensus of these decisions. Using multiple frames eliminates most of the wrong decisions which are caused by a poorly extracted silhouette from a single video frame. The vehicle types we classify are motorcycle, car (sedan) and van (minibus). The features extracted from the silhouettes are convexity, elongation, rectangularity and Hu moments. We applied two separate methods of classification. First one is a flowchartbased method that we developed and the second is K-nearest neighbour classification. 60% of the samples in the dataset are used for training. To ensure randomization in the experiments, threefold cross-validation is applied. The results indicate that using multiple silhouettes increases the classification performance.

In a hybrid camera system combining an omnidirectional and a Pan-Tilt-Zoom (PTZ) camera, the omnidirectional camera provides 360 degree horizontal field-ofview, whereas the PTZ camera provides high resolution at a certain direction. This results in a wide field-of-view and high resolution camera system. In this paper, we exploit this hybrid system for real-time object classification and tracking for traffic scenes. The omnidirectional camera detects the moving objects and performs an initial classification using shape-based features. Concurrently, the PTZ camera classifies the objects using high resolution frames and Histogram of Oriented Gradients (HOG) features. PTZ camera also performs high-resolution tracking for the objects classified as the target class by the omnidirectional camera. The object types we worked on are pedestrian, motorcycle, car and van. Extensive experiments were conducted to compare the classification accuracy of the hybrid system with single camera alternatives.

Social media platforms are vulnerable to fake news dissemination, which causes negative consequences such as panic and wrong medication in the healthcare domain. Therefore, it is important to automatically detect fake news in an early stage before they get widely spread. This paper analyzes the impact of incorporating content information, prior knowledge, and credibility of sources into models for the early detection of fake news. We propose a framework modeling those features by using BERT language model and external sources, namely Simple English Wikipedia and source reliability tags. The conducted experiments on CONSTRAINT datasets demonstrated the benefit of integrating these features for the early detection of fake news in the healthcare domain.

No abstract