Yi-Chun Chen

Yi-Chun Chen, Arnav Jhala

We present a theory-inspired visual narrative generator that incorporates comic-authoring idioms, which transfers the conceptual principles of comics into system layers that integrate the theories to create comic content. The generator creates comics through sequential decision-making across layers from panel composition, object positions, panel transitions, and narrative elements. Each layer's decisions are based on narrative goals and follow the respective layer idioms of the medium. Cohn's narrative grammar provides the overall story arc. Photographic compositions inspired by the rule of thirds is used to provide panel compositions. McCloud's proposed panel transitions based on focus shifts between scene, character, and temporal changes are encoded in the transition layer. Finally, common overlay symbols (such as the exclamation) are added based on analyzing action verbs using an action-verb ontology. We demonstrate the variety of generated comics through various settings with example outputs. The generator and associated modules could be a useful system for visual narrative authoring and for further research into computational models of visual narrative understanding.

Yi-Chun Chen, Arnav Jhala

Understanding how humans communicate and perceive narratives is important for media technology research and development. This is particularly important in current times when there are tools and algorithms that are easily available for amateur users to create high-quality content. Narrative media develops over time a set of recognizable patterns of features across similar artifacts. Genre is one such grouping of artifacts for narrative media with similar patterns, tropes, and story structures. While much work has been done on genre-based classifications in text and video, we present a novel approach to do a multi-modal analysis of genre based on comics and manga-style visual narratives. We present a systematic feature analysis of an annotated dataset that includes a variety of western and eastern visual books with annotations for high-level narrative patterns. We then present a detailed analysis of the contributions of high-level features to genre classification for this medium. We highlight some of the limitations and challenges of our existing computational approaches in modeling subjective labels. Our contributions to the community are: a dataset of annotated manga books, a multi-modal analysis of visual panels and text in a constrained and popular medium through high-level features, and a systematic process for incorporating subjective narrative patterns in computational models.

Daniel Stanley Tan, Yi-Chun Chen, Trista Pei-Chun Chen et al.

In this paper, we propose a framework called TrustMAE to address the problem of product defect classification. Instead of relying on defective images that are difficult to collect and laborious to label, our framework can accept datasets with unlabeled images. Moreover, unlike most anomaly detection methods, our approach is robust against noises, or defective images, in the training dataset. Our framework uses a memory-augmented auto-encoder with a sparse memory addressing scheme to avoid over-generalizing the auto-encoder, and a novel trust-region memory updating scheme to keep the noises away from the memory slots. The result is a framework that can reconstruct defect-free images and identify the defective regions using a perceptual distance network. When compared against various state-of-the-art baselines, our approach performs competitively under noise-free MVTec datasets. More importantly, it remains effective at a noise level up to 40% while significantly outperforming other baselines.

Shih-Han Chou, Yi-Chun Chen, Kuo-Hao Zeng et al.

Narrated 360° videos are typically provided in many touring scenarios to mimic real-world experience. However, previous work has shown that smart assistance (i.e., providing visual guidance) can significantly help users to follow the Normal Field of View (NFoV) corresponding to the narrative. In this project, we aim at automatically grounding the NFoVs of a 360° video given subtitles of the narrative (referred to as "NFoV-grounding"). We propose a novel Visual Grounding Model (VGM) to implicitly and efficiently predict the NFoVs given the video content and subtitles. Specifically, at each frame, we efficiently encode the panorama into feature map of candidate NFoVs using a Convolutional Neural Network (CNN) and the subtitles to the same hidden space using an RNN with Gated Recurrent Units (GRU). Then, we apply soft-attention on candidate NFoVs to trigger sentence decoder aiming to minimize the reconstruct loss between the generated and given sentence. Finally, we obtain the NFoV as the candidate NFoV with the maximum attention without any human supervision. To train VGM more robustly, we also generate a reverse sentence conditioning on one minus the soft-attention such that the attention focuses on candidate NFoVs less relevant to the given sentence. The negative log reconstruction loss of the reverse sentence (referred to as "irrelevant loss") is jointly minimized to encourage the reverse sentence to be different from the given sentence. To evaluate our method, we collect the first narrated 360° videos dataset and achieve state-of-the-art NFoV-grounding performance.