1 code implementation • 18 Apr 2024 • Songwei Ge, Aniruddha Mahapatra, Gaurav Parmar, Jun-Yan Zhu, Jia-Bin Huang
We show that FVD with features extracted from the recent large-scale self-supervised video models is less biased toward image quality.
no code implementations • 8 Jun 2023 • 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.
no code implementations • ICCV 2023 • Songwei Ge, Seungjun Nah, Guilin Liu, Tyler Poon, Andrew Tao, Bryan Catanzaro, David Jacobs, Jia-Bin Huang, Ming-Yu Liu, Yogesh Balaji
Despite tremendous progress in generating high-quality images using diffusion models, synthesizing a sequence of animated frames that are both photorealistic and temporally coherent is still in its infancy.
Ranked #8 on Text-to-Video Generation on UCF-101
no code implementations • ICCV 2023 • Songwei Ge, Taesung Park, Jun-Yan Zhu, Jia-Bin Huang
For each region, we enforce its text attributes by creating region-specific detailed prompts and applying region-specific guidance, and maintain its fidelity against plain-text generation through region-based injections.
no code implementations • 16 Feb 2023 • Ting-Hsuan Liao, Songwei Ge, Yiran Xu, Yao-Chih Lee, Badour AlBahar, Jia-Bin Huang
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 texts, image editing, and customized generation.
1 code implementation • CVPR 2023 • Songwei Ge, Shlok Mishra, Simon Kornblith, Chun-Liang Li, David Jacobs
To exploit such a structure, we propose a contrastive learning framework where a Euclidean loss is used to learn object representations and a hyperbolic loss is used to encourage representations of scenes to lie close to representations of their constituent objects in a hyperbolic space.
2 code implementations • 17 Apr 2022 • Thomas Hayes, Songyang Zhang, Xi Yin, Guan Pang, Sasha Sheng, Harry Yang, Songwei Ge, Qiyuan Hu, Devi Parikh
Altogether, MUGEN can help progress research in many tasks in multimodal understanding and generation.
1 code implementation • 7 Apr 2022 • Songwei Ge, Thomas Hayes, Harry Yang, Xi Yin, Guan Pang, David Jacobs, Jia-Bin Huang, Devi Parikh
Videos are created to express emotion, exchange information, and share experiences.
Ranked #15 on Video Generation on UCF-101
1 code implementation • NeurIPS 2021 • Songwei Ge, Shlok Mishra, Haohan Wang, Chun-Liang Li, David Jacobs
We also show that model bias favors texture and shape features differently under different test settings.
no code implementations • 27 Jun 2021 • Songwei Ge, Devi Parikh
We ask the question: to what extent can recent large-scale language and image generation models blend visual concepts?
1 code implementation • NeurIPS 2021 • Songwei Ge, Vasu Singla, Ronen Basri, David Jacobs
Using this, we prove that shift invariance in neural networks produces adversarial examples for the simple case of two classes, each consisting of a single image with a black or white dot on a gray background.
1 code implementation • ICLR 2021 • Songwei Ge, Vedanuj Goswami, C. Lawrence Zitnick, Devi Parikh
Sketching or doodling is a popular creative activity that people engage in.
no code implementations • ICLR 2020 • Haohan Wang, Xindi Wu, Songwei Ge, Zachary C. Lipton, Eric P. Xing
Recent research has shown that CNNs are often overly sensitive to high-frequency textural patterns.
no code implementations • 8 Dec 2019 • Austin Dill, Songwei Ge, Eunsu Kang, Chun-Liang Li, Barnabas Poczos
The typical approach for incorporating this creative process is to interpolate in a learned latent space so as to avoid the problem of generating unrealistic instances by exploiting the model's learned structure.
no code implementations • 8 Dec 2019 • Austin Dill, Chun-Liang Li, Songwei Ge, Eunsu Kang
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, a discretized mesh, and a set of points sampled from the surface.
no code implementations • 20 Aug 2019 • Songwei Ge, Austin Dill, Eunsu Kang, Chun-Liang Li, Lingyao Zhang, Manzil Zaheer, Barnabas Poczos
We explore the intersection of human and machine creativity by generating sculptural objects through machine learning.
no code implementations • 20 Aug 2019 • Songwei Ge, Curtis Xuan, Ruihua Song, Chao Zou, Wei Liu, Jin Zhou
In this paper, we address the problem of automatically adding sound effects to radio stories with a retrieval-based model.
no code implementations • 20 Aug 2019 • Songwei Ge, Zhicheng Dou, Zhengbao Jiang, Jian-Yun Nie, Ji-Rong Wen
Our analysis reveals that the attention model is able to attribute higher weights to more related past sessions after fine training.
4 code implementations • NeurIPS 2019 • Haohan Wang, Songwei Ge, Eric P. Xing, Zachary C. Lipton
Despite their renowned predictive power on i. i. d.
Ranked #104 on Domain Generalization on PACS
no code implementations • 13 Nov 2018 • Chun-Liang Li, Eunsu Kang, Songwei Ge, Lingyao Zhang, Austin Dill, Manzil Zaheer, Barnabas Poczos
Our approach extends DeepDream from images to 3D point clouds.