Publications (12)
Reviving Ancient Paintings via Poem: A Colorization Framework for Aligning Cultural Semantics
Junming Gao, Biao Zhu, Xiaosong Wang +1
The irreversible fading of ancient paintings disrupts the "congruence between poems and paintings", a core aesthetic principle where visual imagery harmonizes with literary inscrip…
SARe: Structure-Aware Generative 3D Fragment Reassembly
Hanze Jia, Chunshi Wang, Yuxiao Yang +4
3D fragment reassembly estimates the rigid pose of each fragment to recover a complete object from unordered point clouds or meshes. The task becomes increasingly challenging as th…
Shared-kernel Wavelet Neural Networks for Poisson Image Reconstruction
Yuanhao Gong, Tan Tang, Qianyan Liu
The Laplacian operator transforms the image into its Laplacian field, which usually is sparse and satisfies a stable distribution. On the other hand, an image can be uniquely recon…
PRevivor: Reviving Ancient Chinese Paintings using Prior-Guided Color Transformers
Tan Tang, Yanhong Wu, Junming Gao +1
Ancient Chinese paintings are a valuable cultural heritage that is damaged by irreversible color degradation. Reviving color-degraded paintings is extraordinarily difficult due to…
Understanding Nonlinear Collaboration between Human and AI Agents: A Co-design Framework for Creative Design
Jiayi Zhou, Renzhong Li, Junxiu Tang +4
Creative design is a nonlinear process where designers generate diverse ideas in the pursuit of an open-ended goal and converge towards consensus through iterative remixing. In con…
MetaGlyph: Automatic Generation of Metaphoric Glyph-based Visualization
Lu Ying, Xinhuan Shu, Dazhen Deng +4
Glyph-based visualization achieves an impressive graphic design when associated with comprehensive visual metaphors, which help audiences effectively grasp the conveyed information…
AtomEval: Validity-Aware Atomic Evaluation of Adversarial Claim Rewriting in Fact Verification
Hongyi Cen, Mingxin Wang, Yule Liu +3
Large language models (LLMs) can rewrite refuted claims to evade evidence-based fact verifiers, but conventional attack success rate (ASR) can be inflated when rewrites change, wea…
Narrative Transitions in Data Videos
Junxiu Tang, Lingyun Yu, Tan Tang +5
Transitions are widely used in data videos to seamlessly connect data-driven charts or connect visualizations and non-data-driven motion graphics. To inform the transition designs…
VideoModerator: A Risk-aware Framework for Multimodal Video Moderation in E-Commerce
Tan Tang, Yanhong Wu, Lingyun Yu +2
Video moderation, which refers to remove deviant or explicit content from e-commerce livestreams, has become prevalent owing to social and engaging features. However, this task is…
DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA
Jianing Yin, Tan Tang
Large language model (LLM) agents still struggle with long-term memory question answering, where answer-supporting evidence is often scattered across long conversational histories…
Real-Time Visual Analysis of High-Volume Social Media Posts
Johannes Knittel, Steffen Koch, Tan Tang +4
Breaking news and first-hand reports often trend on social media platforms before traditional news outlets cover them. The real-time analysis of posts on such platforms can reveal…
PlotThread: Creating Expressive Storyline Visualizations using Reinforcement Learning
Tan Tang, Renzhong Li, Xinke Wu +7
Storyline visualizations are an effective means to present the evolution of plots and reveal the scenic interactions among characters. However, the design of storyline visualizatio…