Joonseok Lee

8

Papers

36

Total Citations

Papers (8)

V2Meow: Meowing to the Visual Beat via Video-to-Music Generation

Finding NeMo: Negative-mined Mosaic Augmentation for Referring Image Segmentation

Latent Diffusion Models with Masked AutoEncoders

Towards Scalable Human-aligned Benchmark for Text-guided Image Editing

Latent Expression Generation for Referring Image Segmentation and Grounding

SummDiff: Generative Modeling of Video Summarization with Diffusion

Dictionary Contrastive Learning for Efficient Local Supervision without Auxiliary Networks

Isometric Representation Learning for Disentangled Latent Space of Diffusion Models