161 citations · 387 across the 61 of their papers we have counts for
7 papers · 1 filter
GLeaD: Improving GANs with A Generator-Leading Task
Qingyan Bai, Ceyuan Yang, Yinghao Xu +3
Generative adversarial network (GAN) is formulated as a two-player game between a generator (G) and a discriminator (D), where D is asked to differentiate whether an image comes fr…
Shape-Guided Diffusion with Inside-Outside Attention
Dong Huk Park, Grace Luo, Clayton Toste +5
We introduce precise object silhouette as a new form of user control in text-to-image diffusion models, which we dub Shape-Guided Diffusion. Our training-free method uses an Inside…
Learning Transferable Spatiotemporal Representations from Natural Script Knowledge
Ziyun Zeng, Yuying Ge, Xihui Liu +4
Pre-training on large-scale video data has become a common recipe for learning transferable spatiotemporal representations in recent years. Despite some progress, existing methods…
Back to the Source: Diffusion-Driven Test-Time Adaptation
Jin Gao, Jialing Zhang, Xihui Liu +3
Test-time adaptation harnesses test inputs to improve the accuracy of a model trained on source data when tested on shifted target data. Existing methods update the source model by…
The ArtBench Dataset: Benchmarking Generative Models with Artworks
Peiyuan Liao, Xiuyu Li, Xihui Liu +1
We introduce ArtBench-10, the first class-balanced, high-quality, cleanly annotated, and standardized dataset for benchmarking artwork generation. It comprises 60,000 images of art…
MILES: Visual BERT Pre-training with Injected Language Semantics for Video-text Retrieval
Yuying Ge, Yixiao Ge, Xihui Liu +5
Dominant pre-training work for video-text retrieval mainly adopt the "dual-encoder" architectures to enable efficient retrieval, where two separate encoders are used to contrast gl…
Bridging Video-text Retrieval with Multiple Choice Questions
Yuying Ge, Yixiao Ge, Xihui Liu +4
Pre-training a model to learn transferable video-text representation for retrieval has attracted a lot of attention in recent years. Previous dominant works mainly adopt two separa…