12 citations · 52 across the 26 of their papers we have counts for
7 papers · 1 filter
Hierarchical Masked 3D Diffusion Model for Video Outpainting
Fanda Fan, Chaoxu Guo, Litong Gong +5
Video outpainting aims to adequately complete missing areas at the edges of video frames. Compared to image outpainting, it presents an additional challenge as the model should mai…
AutoPoster: A Highly Automatic and Content-aware Design System for Advertising Poster Generation
Jinpeng Lin, Min Zhou, Ye Ma +5
Advertising posters, a form of information presentation, combine visual and linguistic modalities. Creating a poster involves multiple steps and necessitates design experience and…
Deep Task-specific Bottom Representation Network for Multi-Task Recommendation
Qi Liu, Zhilong Zhou, Gangwei Jiang +2
Neural-based multi-task learning (MTL) has gained significant improvement, and it has been successfully applied to recommendation system (RS). Recent deep MTL methods for RS (e.g.…
TextPainter: Multimodal Text Image Generation with Visual-harmony and Text-comprehension for Poster Design
Yifan Gao, Jinpeng Lin, Min Zhou +4
Text design is one of the most critical procedures in poster design, as it relies heavily on the creativity and expertise of humans to design text images considering the visual har…
Visual Captioning at Will: Describing Images and Videos Guided by a Few Stylized Sentences
Dingyi Yang, Hongyu Chen, Xinglin Hou +3
Stylized visual captioning aims to generate image or video descriptions with specific styles, making them more attractive and emotionally appropriate. One major challenge with this…
Unsupervised Domain Adaption with Pixel-level Discriminator for Image-aware Layout Generation
Chenchen Xu, Min Zhou, Tiezheng Ge +2
Layout is essential for graphic design and poster generation. Recently, applying deep learning models to generate layouts has attracted increasing attention. This paper focuses on…
CF-Font: Content Fusion for Few-shot Font Generation
Chi Wang, Min Zhou, Tiezheng Ge +3
Content and style disentanglement is an effective way to achieve few-shot font generation. It allows to transfer the style of the font image in a source domain to the style defined…