Related papers: Situation and Behavior Understanding by Trope Dete…
Understanding and comprehending video content is crucial for many real-world applications such as search and recommendation systems. While recent progress of deep learning has boosted performance on various tasks using visual cues, deep…
Large Language Models (LLMs) have demonstrated effectiveness not only in language tasks but also in video reasoning. This paper introduces a novel dataset, Tropes in Movies (TiM), designed as a testbed for exploring two critical yet…
TVTropes is a wiki that describes tropes and which ones are used in which artistic work. We are mostly interested in films, so after releasing the TropeScraper Python module that extracts data from this site, in this report we use scraped…
Large language models (LLMs) equipped with chain-of-thoughts (CoT) prompting have shown significant multi-step reasoning capabilities in factual content like mathematics, commonsense, and logic. However, their performance in narrative…
Most Reading Comprehension methods limit themselves to queries which can be answered using a single sentence, paragraph, or document. Enabling models to combine disjoint pieces of textual evidence would extend the scope of machine…
Metaphors are ubiquitous in natural language, and their detection plays an essential role in many natural language processing tasks, such as language understanding, sentiment analysis, etc. Most existing approaches for metaphor detection…
The ability to infer persona from dialogue can have applications in areas ranging from computational narrative analysis to personalized dialogue generation. We introduce neural models to learn persona embeddings in a supervised character…
Automated movie genre classification has emerged as an active and essential area of research and exploration. Short duration movie trailers provide useful insights about the movie as video content consists of the cognitive and the affective…
Folksonomy of movies covers a wide range of heterogeneous information about movies, like the genre, plot structure, visual experiences, soundtracks, metadata, and emotional experiences from watching a movie. Being able to automatically…
For machine translation to tackle discourse phenomena, models must have access to extra-sentential linguistic context. There has been recent interest in modelling context in neural machine translation (NMT), but models have been principally…
When reading a story, humans can quickly understand new fictional characters with a few observations, mainly by drawing analogies to fictional and real people they already know. This reflects the few-shot and meta-learning essence of…
Detecting critical moments, such as emotional outbursts or changes in decisions during conversations, is crucial for understanding shifts in human behavior and their consequences. Our work introduces a novel problem setting focusing on…
The ability to integrate context, including perceptual and temporal cues, plays a pivotal role in grounding the meaning of a linguistic utterance. In order to measure to what extent current vision-and-language models master this ability, we…
While deep neural networks have led to human-level performance on computer vision tasks, they have yet to demonstrate similar gains for holistic scene understanding. In particular, 3D context has been shown to be an extremely important cue…
Social tagging of movies reveals a wide range of heterogeneous information about movies, like the genre, plot structure, soundtracks, metadata, visual and emotional experiences. Such information can be valuable in building automatic systems…
Word embeddings are trained to predict word cooccurrence statistics, which leads them to possess different lexical properties (syntactic, semantic, etc.) depending on the notion of context defined at training time. These properties manifest…
Popular media reflects and reinforces societal biases through the use of tropes, which are narrative elements, such as archetypal characters and plot arcs, that occur frequently across media. In this paper, we specifically investigate…
While contextualized word embeddings have been a de-facto standard, learning contextualized phrase embeddings is less explored and being hindered by the lack of a human-annotated benchmark that tests machine understanding of phrase…
Recurrent feedback connections in the mammalian visual system have been hypothesized to play a role in synthesizing input in the theoretical framework of analysis by synthesis. The comparison of internally synthesized representation with…
Smart devices of everyday use (such as smartphones and wearables) are increasingly integrated with sensors that provide immense amounts of information about a person's daily life such as behavior and context. The automatic and unobtrusive…