The problem addressed here is classification of videos at the highest level into pre-defined genre. The approach adopted is based on the dynamic content of short sequences ( 30 secs). This paper presents two methods of extracting motion from a video sequence: foreground object motion and background camera motion. These dynamics are extracted, processed and applied to classify 3 broad classes: s...

In this paper we describe in detail the recent publications related to video-genre-classification and present our improved approaches for classifying video sequences in real-time as ‘cartoon’, ‘commercial’, ‘music’, ‘news’ or ‘sport’ by analyzing the content with high-level audio-visual descriptors and classification methods. Such applications have also been discussed in the context of MPEG-7 [...

The problem addressed here is classification of videos at the highest level into pre-defined genre. The approach adopted is based on the dynamic content of short sequences ( 30 secs). This paper presents two methods of extracting motion from a video sequence: foreground object motion and background camera motion. These dynamics are extracted, processed and applied to classify 3 broad classes: s...

In this paper we propose an approach to high-level classification of video into genre: sport, cartoon, news, commercial and music. An important issue for automatic high-level classification systems is the amount of time needed to classify a video. Here we investigate classification performance as a function of the test sequence length. In addition we present performance against different orders...

To date, researchers have proposed different ways to compute the readability and coherence of a text using a variety of lexical, syntax, entity and discourse properties. But these metrics have not been defined with special relevance to any particular genre but rather proposed as general indicators of writing quality. In this thesis, we propose and evaluate novel text quality metrics that utiliz...

This paper discusses the influence of the corpus on the automatic identification of proper names in texts. Techniques developed for the newswire genre are generally not sufficient to deal with larger corpora containing texts that do not follow strict writing constraints (for example, e-mail messages, transcriptions of oral conversations, etc). After a brief review of the research performed on n...

Twitter is the largest source of microblog text, responsible for gigabytes of human discourse every day. Processing microblog text is difficult: the genre is noisy, documents have little context, and utterances are very short. As such, conventional NLP tools fail when faced with tweets and other microblog text. We present TwitIE, an open-source NLP pipeline customised to microblog text at every...

Recent advances in automatic text summarization have used deep neural networks to generate high-quality abstractive summaries, but the performance of these models strongly depends on large amounts of suitable training data. We propose a new method for mining social media for author-provided summaries, taking advantage of the common practice of appending a “TL;DR” to long posts. A case study usi...

Which genre of science writing contributes most to public understanding, and how does that understanding happen? Working within a in society approach, this paper examines engagement with as it occurs the comments discussion boards r/science. Researchers use content analysis identify relevant concept categories code for interaction content. The resulting data are analyzed by (scientific news jou...