Related papers: FocalLens: Visualizing Narratives through Focaliza…
Exponential growth in the quantity of digital news, social media, and other textual sources makes it difficult for humans to keep up with rapidly evolving narratives about world events. Various visualisation techniques have been touted to…
Interpretability of modern visual models is crucial, particularly in high-stakes applications. However, existing interpretability methods typically suffer from either reliance on white-box model access or insufficient quantitative rigor. To…
Coreference resolution aims to identify words and phrases which refer to same entity in a text, a core task in natural language processing. In this paper, we extend this task to resolving coreferences in long-form narrations of visual…
Counterfactuals -- expressing what might have been true under different circumstances -- have been widely applied in statistics and machine learning to help understand causal relationships. More recently, counterfactuals have begun to…
Story visualization aims to generate a sequence of images to narrate each sentence in a multi-sentence story, where the images should be realistic and keep global consistency across dynamic scenes and characters. Current works face the…
Storyline visualizations are an effective means to present the evolution of plots and reveal the scenic interactions among characters. However, the design of storyline visualizations is a difficult task as users need to balance between…
Visual stories are an effective and powerful tool to convey specific information to a diverse public. Scrollytelling is a recent visual storytelling technique extensively used on the web, where content appears or changes as users scroll up…
Narrative understanding involves capturing the author's cognitive processes, providing insights into their knowledge, intentions, beliefs, and desires. Although large language models (LLMs) excel in generating grammatically coherent text,…
Story comprehension requires a deep semantic understanding of the narrative, making it a challenging task. Inspired by previous studies on ROC Story Cloze Test, we propose a novel method, tracking various semantic aspects with external…
We present a method for producing documentary-style content using real-time scientific visualization. We produce molecumentaries, i.e., molecular documentaries featuring structural models from molecular biology. We employ scalable methods…
A storyboard is a sequence of images to illustrate a story containing multiple sentences, which has been a key process to create different story products. In this paper, we tackle a new multimedia task of automatic storyboard creation to…
Detecting DeepFakes has become a crucial research area as the widespread use of AI image generators enables the effortless creation of face-manipulated and fully synthetic content, while existing methods are often limited to binary…
Language exhibits inherent structures, a property that explains both language acquisition and language change. Given this characteristic, we expect language models to manifest their own internal structures as well. While interpretability…
During the last decade, Natural Language Processing has become, after Computer Vision, the second field of Artificial Intelligence that was massively changed by the advent of Deep Learning. Regardless of the architecture, the language…
Storyline visualization has emerged as an innovative method for illustrating the development and changes in stories across various domains. Traditional approaches typically represent stories with one line per character, progressing from…
From the earliest days of computing, there have been tools to help shape narrative. Spell-checking, word counts, and readability analysis, give today's novelists tools that Dickens, Austen, and Shakespeare could only have dreamt of.…
As online news increasingly include data journalism, there is a corresponding increase in the incorporation of visualization in article thumbnail images. However, little research exists on the design rationale for visualization thumbnails,…
Neural networks are widely adopted to solve complex and challenging tasks. Especially in high-stakes decision-making, understanding their reasoning process is crucial, yet proves challenging for modern deep networks. Feature visualization…
Constructive visualization uses physical data units - tokens - to enable non-experts to create personalized visualizations engagingly. However, its physical nature limits efficiency and scalability. One potential solution to address this…
Existing digital book management platforms often fail to capture the rich spatial and visual cues inherent to physical bookshelves, hindering users' ability to fully engage with their collections. We present LibraryLens, a novel…