124 citations · 453 across the 18 of their papers we have counts for
7 papers · 1 filter
CMOSE: Comprehensive Multi-Modality Online Student Engagement Dataset with High-Quality Labels
Chi-hsuan Wu, Shih-yang Liu, Xijie Huang +6
Online learning is a rapidly growing industry. However, a major doubt about online learning is whether students are as engaged as they are in face-to-face classes. An engagement re…
PromptMagician: Interactive Prompt Engineering for Text-to-Image Creation
Yingchaojie Feng, Xingbo Wang, Kam Kwai Wong +5
Generative text-to-image models have gained great popularity among the public for their powerful capability to generate high-quality images based on natural language prompts. Howev…
Storyfier: Exploring Vocabulary Learning Support with Text Generation Models
Zhenhui Peng, Xingbo Wang, Qiushi Han +3
Vocabulary learning support tools have widely exploited existing materials, e.g., stories or video clips, as contexts to help users memorize each target word. However, these tools…
VideoPro: A Visual Analytics Approach for Interactive Video Programming
Jianben He, Xingbo Wang, Kam Kwai Wong +6
Constructing supervised machine learning models for real-world video analysis require substantial labeled data, which is costly to acquire due to scarce domain expertise and labori…
CommonsenseVIS: Visualizing and Understanding Commonsense Reasoning Capabilities of Natural Language Models
Xingbo Wang, Renfei Huang, Zhihua Jin +2
Recently, large pretrained language models have achieved compelling performance on commonsense benchmarks. Nevertheless, it is unclear what commonsense knowledge the models learn a…
Anchorage: Visual Analysis of Satisfaction in Customer Service Videos via Anchor Events
Kam Kwai Wong, Xingbo Wang, Yong Wang +3
Delivering customer services through video communications has brought new opportunities to analyze customer satisfaction for quality management. However, due to the lack of reliabl…
XNLI: Explaining and Diagnosing NLI-based Visual Data Analysis
Yingchaojie Feng, Xingbo Wang, Bo Pan +7
Natural language interfaces (NLIs) enable users to flexibly specify analytical intentions in data visualization. However, diagnosing the visualization results without understanding…