Search

Sports highlights are becoming increasingly popular on video-sharing platforms. Yet, crafting sport highlight videos is challenging, which requires producing engaging narratives from different angles, and conforming to different platform affordances with constantly changing audiences. Many content creators therefore create derivative work of the original sports video through manga styles to enhance its expressiveness. But manually creating and inserting tailored manga-style content can still be time-consuming. We introduce Sportoonizer, a system embedding the pipeline for automatic generation of manga-style animations for highlights in sports videos and insertion into original videos. It seamlessly merges dynamic manga sequences with live-action footage, enriching the visual tapestry and deepening narrative scope. By leveraging genAIs, Sportoonizer crafts compelling storylines encapsulating the intensity of sports moments and athletes' personal journeys. Our evaluation study demonstrates that integrating manga B-rolls significantly enhances viewer engagement, visual interest, and emotional connection towards athletes' stories in the viewing experience.

The automatic generation of high-quality mathematical problems is practically valuable in many educational scenarios. Large multimodal model provides a novel technical approach for the mathematical problem generation because of its wide success in cross-modal data scenarios. However, the traditional method of separating problem solving from problem generation and the mainstream fine-tuning framework of monotonous data structure with homogeneous training objectives limit the application of large multimodal model in mathematical problem generation. Addressing these challenges, this paper proposes COMET, a "Cone of Experience" enhanced large multimodal model for mathematical problem generation. Firstly, from the perspective of mutual ability promotion and application logic, we unify stem generation and problem solving into mathematical problem generation. Secondly, a three-stage fine-turning framework guided by the "Cone of Experience" is proposed. The framework divides the fine-tuning data into symbolic experience, iconic experience, and direct experience to draw parallels with experiences in the career growth of teachers. Several fine-grained data construction and injection methods are designed in this framework. Finally, we construct a Chinese multimodal mathematical problem dataset to fill the vacancy of Chinese multimodal data in this field. Combined with objective and subjective indicators, experiments on multiple datasets fully verify the effectiveness of the proposed framework and model.

A well-motivated cosmological hybrid inflation scenario based on no-scale SUGRA is considered. It is demonstrated that an extra suppressed $R$-symmetry breaking term $S^n$ with $n\geq 4$ needs to be included in order to realize successful inflation. The resulting potential is found to be similar (but not identical) to the one in the Starobinsky inflation model. A relatively larger tensor-to-scalar ratio $r\sim 10^{-2}$ and a spectral index $n_s\approx 0.965$ are obtained, which are approximately independent of $n$., Comment: 14 pages, 5 figures and 1 table

Multimodal aspect-based sentiment analysis (MABSA) aims to understand opinions in a granular manner, advancing human-computer interaction and other fields. Traditionally, MABSA methods use a joint prediction approach to identify aspects and sentiments simultaneously. However, we argue that joint models are not always superior. Our analysis shows that joint models struggle to align relevant text tokens with image patches, leading to misalignment and ineffective image utilization. In contrast, a pipeline framework first identifies aspects through MATE (Multimodal Aspect Term Extraction) and then aligns these aspects with image patches for sentiment classification (MASC: Multimodal Aspect-Oriented Sentiment Classification). This method is better suited for multimodal scenarios where effective image use is crucial. We present three key observations: (a) MATE and MASC have different feature requirements, with MATE focusing on token-level features and MASC on sequence-level features; (b) the aspect identified by MATE is crucial for effective image utilization; and (c) images play a trivial role in previous MABSA methods due to high noise. Based on these observations, we propose a pipeline framework that first predicts the aspect and then uses translation-based alignment (TBA) to enhance multimodal semantic consistency for better image utilization. Our method achieves state-of-the-art (SOTA) performance on widely used MABSA datasets Twitter-15 and Twitter-17. This demonstrates the effectiveness of the pipeline approach and its potential to provide valuable insights for future MABSA research. For reproducibility, the code and checkpoint will be released., Comment: Code will be released upon publication

Because of its use in practice, open-world object detection (OWOD) has gotten a lot of attention recently. The challenge is how can a model detect novel classes and then incrementally learn them without forgetting previously known classes. Previous approaches hinge on strongly-supervised or weakly-supervised novel-class data for novel-class detection, which may not apply to real applications. We construct a new benchmark that novel classes are only encountered at the inference stage. And we propose a new OWOD detector YOLOOC, based on the YOLO architecture yet for the Open-Class setup. We introduce label smoothing to prevent the detector from over-confidently mapping novel classes to known classes and to discover novel classes. Extensive experiments conducted on our more realistic setup demonstrate the effectiveness of our method for discovering novel classes in our new benchmark., Comment: Withdrawn because it was submitted without consent of the first author. In addition, this submission has some errors

Human emotions are essentially molded by lived experiences, from which we construct personalised meaning. The engagement in such meaning-making process has been practiced as an intervention in various psychotherapies to promote wellness. Nevertheless, to support recollecting and recounting lived experiences in everyday life remains under explored in HCI. It also remains unknown how technologies such as generative AI models can facilitate the meaning making process, and ultimately support affective mindfulness. In this paper we present Metamorpheus, an affective interface that engages users in a creative visual storytelling of emotional experiences during dreams. Metamorpheus arranges the storyline based on a dream's emotional arc, and provokes self-reflection through the creation of metaphorical images and text depictions. The system provides metaphor suggestions, and generates visual metaphors and text depictions using generative AI models, while users can apply generations to recolour and re-arrange the interface to be visually affective. Our experience-centred evaluation manifests that, by interacting with Metamorpheus, users can recall their dreams in vivid detail, through which they relive and reflect upon their experiences in a meaningful way., Comment: Accepted by CHI 2024

In horticulture, spraying applications occur multiple times throughout any crop year. This paper presents a splittable agricultural chemical sprayed vehicle routing problem and formulates it as a mixed integer linear program. The main difference from the classical capacitated arc routing problem (CARP) is that our problem allows us to split the demand on a single demand edge amongst robotics sprayers. We are using theoretical insights about the optimal solution structure to improve the formulation and provide two different formulations of the splittable capacitated arc routing problem (SCARP), a basic spray formulation and a large edge demands formulation for large edge demands problems. This study presents solution methods consisting of lazy constraints, symmetry elimination constraints, and a heuristic repair method. Computational experiments on a set of valuable data based on the properties of real-world agricultural orchard fields reveal that the proposed methods can solve the SCARP with different properties. We also report computational results on classical benchmark sets from previous CARP literature. The tested results indicated that the SCARP model can provide cheaper solutions in some instances when compared with the classical CARP literature. Besides, the heuristic repair method significantly improves the quality of the solution by decreasing the upper bound when solving large-scale problems., Comment: 25 pages, 8 figures

VTubers, or Virtual YouTubers, are live streamers who create streaming content using animated 2D or 3D virtual avatars. In recent years, there has been a significant increase in the number of VTuber creators and viewers across the globe. This practise has drawn research attention into topics such as viewers' engagement behaviors and perceptions, however, as animated avatars offer more identity and performance flexibility than traditional live streaming where one uses their own body, little research has focused on how this flexibility influences how creators present themselves. This research thus seeks to fill this gap by presenting results from a qualitative study of 16 Chinese-speaking VTubers' streaming practices. The data revealed that the virtual avatars that were used while live streaming afforded creators opportunities to present themselves using inflated presentations and resulted in inclusive interactions with viewers. The results also unveiled the inflated, and often sexualized, gender expressions of VTubers while they were situated in misogynistic environments. The socio-technical facets of VTubing were found to potentially reduce sexual harassment and sexism, whilst also raising self-objectification concerns., Comment: To appear at ACM CSCW 2024 (Accepted to PACM HCI(CSCW))

Prewriting is the process of discovering and developing ideas before a first draft, which requires divergent thinking and often implies unstructured strategies such as diagramming, outlining, free-writing, etc. Although large language models (LLMs) have been demonstrated to be useful for a variety of tasks including creative writing, little is known about how users would collaborate with LLMs to support prewriting. The preferred collaborative role and initiative of LLMs during such a creativity process is also unclear. To investigate human-LLM collaboration patterns and dynamics during prewriting, we conducted a three-session qualitative study with 15 participants in two creative tasks: story writing and slogan writing. The findings indicated that during collaborative prewriting, there appears to be a three-stage iterative Human-AI Co-creativity process that includes Ideation, Illumination, and Implementation stages. This collaborative process champions the human in a dominant role, in addition to mixed and shifting levels of initiative that exist between humans and LLMs. This research also reports on collaboration breakdowns that occur during this process, user perceptions of using existing LLMs during Human-AI Co-creativity, and discusses design implications to support this co-creativity process., Comment: To appear at ACM CSCW 2024; Accepted to PACM HCI (CSCW); 25 pages, 2 figures

Synthesis writing is widely taught across domains and serves as an important means of assessing writing ability, text comprehension, and content learning. Synthesis writing differs from other types of writing in terms of both cognitive and task demands because it requires writers to integrate information across source materials. However, little is known about how integration of source material may influence overall writing quality for synthesis tasks. This study examined approximately 900 source-based essays written in response to four different synthesis prompts which instructed writers to use information from the sources to illustrate and support their arguments and clearly indicate from which sources they were drawing (i.e., citation use). The essays were then scored by expert raters for holistic quality, argumentation, and source use/inferencing. Hand-crafted natural language processing (NLP) features and pre-existing NLP tools were used to examine semantic and keyword overlap between the essays and the source texts, plagiarism from the source texts, and instances of source citation and quoting. These variables along with text length and prompt were then used to predict essays scores. Results reported strong models for predicting human ratings that explained between 47 and 52% of the variance in scores. The results indicate that text length was the strongest predictor of score but also that more successful writers include stronger, semantically-related information from the source, provide more citations and do so later in the text, and copy less from the text. This work introduces the use of NLP techniques to assess source integration, provides details on the types of source integration used by writers, and highlights the effects of source integration on writing quality. [This is the online version of an article published in "Reading and Writing."]

In the supersymmetric SO(10) models, the doublet-triplet splitting problem can be solved through the Dimopoulos-Wilczek mechanism. This mechanism is extended in the non-renormalizable version. Improvement on the realistic model is also made., Comment: 9 pages

Sharing autonomy between robots and human operators could facilitate data collection of robotic task demonstrations to continuously improve learned models. Yet, the means to communicate intent and reason about the future are disparate between humans and robots. We present Assistive Tele-op, a virtual reality (VR) system for collecting robot task demonstrations that displays an autonomous trajectory forecast to communicate the robot's intent. As the robot moves, the user can switch between autonomous and manual control when desired. This allows users to collect task demonstrations with both a high success rate and with greater ease than manual teleoperation systems. Our system is powered by transformers, which can provide a window of potential states and actions far into the future -- with almost no added computation time. A key insight is that human intent can be injected at any location within the transformer sequence if the user decides that the model-predicted actions are inappropriate. At every time step, the user can (1) do nothing and allow autonomous operation to continue while observing the robot's future plan sequence, or (2) take over and momentarily prescribe a different set of actions to nudge the model back on track. We host the videos and other supplementary material at https://sites.google.com/view/assistive-teleop., Comment: 9 pages, 4 figures, 1 table. NeurIPS 2021 Workshop on Robot Learning: Self-Supervised and Lifelong Learning, Virtual, Virtual

Different from fine-tuning models pre-trained on a large-scale dataset of preset classes, class-incremental learning (CIL) aims to recognize novel classes over time without forgetting pre-trained classes. However, a given model will be challenged by test images with finer-grained classes, e.g., a basenji is at most recognized as a dog. Such images form a new training set (i.e., support set) so that the incremental model is hoped to recognize a basenji (i.e., query) as a basenji next time. This paper formulates such a hybrid natural problem of coarse-to-fine few-shot (C2FS) recognition as a CIL problem named C2FSCIL, and proposes a simple, effective, and theoretically-sound strategy Knowe: to learn, normalize, and freeze a classifier's weights from fine labels, once learning an embedding space contrastively from coarse labels. Besides, as CIL aims at a stability-plasticity balance, new overall performance metrics are proposed. In that sense, on CIFAR-100, BREEDS, and tieredImageNet, Knowe outperforms all recent relevant CIL/FSCIL methods that are tailored to the new problem setting for the first time.

The great success of deep learning (DL) has inspired researchers to develop more accurate and efficient symbol detectors for multi-input multi-output (MIMO) systems. Existing DL-based MIMO detectors, however, suffer several drawbacks. To address these issues, in this paper, we develop a model-driven DL detector based on variational Bayesian inference. Specifically, the proposed unrolled DL architecture is inspired by an inverse-free variational Bayesian learning framework which circumvents matrix inversion via maximizing a relaxed evidence lower bound. Two networks are respectively developed for independent and identically distributed (i.i.d.) Gaussian channels and arbitrarily correlated channels. The proposed networks, referred to as VBINet, have only a few learnable parameters and thus can be efficiently trained with a moderate amount of training samples. The proposed VBINet-based detectors can work in both offline and online training modes. An important advantage of our proposed networks over state-of-the-art MIMO detection networks such as OAMPNet and MMNet is that the VBINet can automatically learn the noise variance from data, thus yielding a significant performance improvement over the OAMPNet and MMNet in the presence of noise variance uncertainty. Simulation results show that the proposed VBINet-based detectors achieve competitive performance for both i.i.d. Gaussian and realistic 3GPP MIMO channels., Comment: This paper has been accepted by IEEE Transactions on Signal Processing for future publication

Classical mechanical systems are central to controller design in energy shaping methods of geometric control. However, their expressivity is limited by position-only metrics and the intimate link between metric and geometry. Recent work on Riemannian Motion Policies (RMPs) has shown that shedding these restrictions results in powerful design tools, but at the expense of theoretical stability guarantees. In this work, we generalize classical mechanics to what we call geometric fabrics, whose expressivity and theory enable the design of systems that outperform RMPs in practice. Geometric fabrics strictly generalize classical mechanics forming a new physics of behavior by first generalizing them to Finsler geometries and then explicitly bending them to shape their behavior while maintaining stability. We develop the theory of fabrics and present both a collection of controlled experiments examining their theoretical properties and a set of robot system experiments showing improved performance over a well-engineered and hardened implementation of RMPs, our current state-of-the-art in controller design.