-
@naver-ai lab
- Seoul, Korea
- http://sanghyukchun.github.io/home
- @SanghyukChun
Stars
[ECCV 2024] Official PyTorch implementation of "HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Texts"
Toward Interactive Regional Understanding in Vision-Large Language Models (NAACL 2024)
Official PyTorch implementation of ReWaS (AAAI'25) "Read, Watch and Scream! Sound Generation from Text and Video"
Collection of Composed Image Retrieval (CIR) papers.
[ECCV2024] Official implementation of paper, "DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs".
Official Pytorch implementation of LinCIR: Language-only Training of Zero-shot Composed Image Retrieval (CVPR 2024)
[ICCV 2023] Few shot font generation via transferring similarity guided global and quantization local styles
Uncertainty-aware representation learning (URL) benchmark
Official Pytorch implementation of "Graphit: A Unified Framework for Diverse Image Editing Tasks"
Official Pytorch implementation of "Improved Probabilistic Image-Text Representations" (ICLR 2024)
Official Pytorch implementation of "CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion" (TMLR 2024)
Robust Benchmark MS-COCO to Stress-test Robustness of Image-Text Matching Models
[ECCV2024][ICCV2023] Official PyTorch implementation of SeiT++ and SeiT
[NeurIPS 2023] Code for the paper "Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Models"
Benchmark your model on out-of-distribution datasets with carefully collected human comparison data (NeurIPS 2021 Oral)
Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022
Official Pytorch implementation of C3-GAN (Spotlight at ICLR 2022)
Extended COCO Validation (ECCV) Caption dataset (ECCV 2022)