271 citations · 327 across the 18 of their papers we have counts for
18 papers
Grounded Text-to-Image Synthesis with Attention Refocusing
Quynh Phung, Songwei Ge, Jia-Bin Huang
Driven by the scalable diffusion models trained on large-scale datasets, text-to-image synthesis methods have shown compelling results. However, these models still fail to precisel…
Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models
Songwei Ge, Seungjun Nah, Guilin Liu +7
Despite tremendous progress in generating high-quality images using diffusion models, synthesizing a sequence of animated frames that are both photorealistic and temporally coheren…
Text-driven Visual Synthesis with Latent Diffusion Prior
Ting-Hsuan Liao, Songwei Ge, Yiran Xu +3
There has been tremendous progress in large-scale text-to-image synthesis driven by diffusion models enabling versatile downstream applications such as 3D object synthesis from tex…
Expressive Text-to-Image Generation with Rich Text
Songwei Ge, Taesung Park, Jun-Yan Zhu +1
Plain text has become a prevalent interface for text-to-image synthesis. However, its limited customization options hinder users from accurately describing desired outputs. For exa…
Hyperbolic Contrastive Learning for Visual Representations beyond Objects
Songwei Ge, Shlok Mishra, Simon Kornblith +2
Although self-/un-supervised methods have led to rapid progress in visual representation learning, these methods generally treat objects and scenes using the same lens. In this pap…
MUGEN: A Playground for Video-Audio-Text Multimodal Understanding and GENeration
Thomas Hayes, Songyang Zhang, Xi Yin +6
Multimodal video-audio-text understanding and generation can benefit from datasets that are narrow but rich. The narrowness allows bite-sized challenges that the research community…
Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer
Songwei Ge, Thomas Hayes, Harry Yang +5
Videos are created to express emotion, exchange information, and share experiences. Video synthesis has intrigued researchers for a long time. Despite the rapid progress driven by…
Robust Contrastive Learning Using Negative Samples with Diminished Semantics
Songwei Ge, Shlok Mishra, Haohan Wang +2
Unsupervised learning has recently made exceptional progress because of the development of more effective contrastive learning methods. However, CNNs are prone to depend on low-lev…
Visual Conceptual Blending with Large-scale Language and Vision Models
Songwei Ge, Devi Parikh
We ask the question: to what extent can recent large-scale language and image generation models blend visual concepts? Given an arbitrary object, we identify a relevant object and…
Shift Invariance Can Reduce Adversarial Robustness
Songwei Ge, Vasu Singla, Ronen Basri +1
Shift invariance is a critical property of CNNs that improves performance on classification. However, we show that invariance to circular shifts can also lead to greater sensitivit…
Creative Sketch Generation
Songwei Ge, Vedanuj Goswami, C. Lawrence Zitnick +1
Sketching or doodling is a popular creative activity that people engage in. However, most existing work in automatic sketch understanding or generation has focused on sketches that…
Learned Interpolation for 3D Generation
Austin Dill, Songwei Ge, Eunsu Kang +2
In order to generate novel 3D shapes with machine learning, one must allow for interpolation. The typical approach for incorporating this creative process is to interpolate in a le…
Getting Topology and Point Cloud Generation to Mesh
Austin Dill, Chun-Liang Li, Songwei Ge +1
In this work, we explore the idea that effective generative models for point clouds under the autoencoding framework must acknowledge the relationship between a continuous surface,…
Personalizing Search Results Using Hierarchical RNN with Query-aware Attention
Songwei Ge, Zhicheng Dou, Zhengbao Jiang +2
Search results personalization has become an effective way to improve the quality of search engines. Previous studies extracted information such as past clicks, user topical intere…
From Text to Sound: A Preliminary Study on Retrieving Sound Effects to Radio Stories
Songwei Ge, Curtis Xuan, Ruihua Song +3
Sound effects play an essential role in producing high-quality radio stories but require enormous labor cost to add. In this paper, we address the problem of automatically adding s…
Developing Creative AI to Generate Sculptural Objects
Songwei Ge, Austin Dill, Eunsu Kang +4
We explore the intersection of human and machine creativity by generating sculptural objects through machine learning. This research raises questions about both the technical detai…
Learning Robust Global Representations by Penalizing Local Predictive Power
Haohan Wang, Songwei Ge, Eric P. Xing +1
Despite their renowned predictive power on i.i.d. data, convolutional neural networks are known to rely more on high-frequency patterns that humans deem superficial than on low-fre…
Hallucinating Point Cloud into 3D Sculptural Object
Chun-Liang Li, Eunsu Kang, Songwei Ge +4
Our team of artists and machine learning researchers designed a creative algorithm that can generate authentic sculptural artworks. These artworks do not mimic any given forms and…