# CLOVA AI LAB @ CVPR 2022 ![](/files/VX66ZxoYvUjo00n4fr7x) ## Presentation Schedule #### \[Workshop] #### [AI4CC 2022](https://ai4cc.net/): June 19. @ Room 208-210 (11:45 - 12:45) Yoonsik Kim (NAVER CLOVA), Junyeop Lee(Upstage), Seonghyeon Kim (NAVER CLOVA), Moonbin Yim (NAVER CLOVA), Seung Shin (NAVER CLOVA), Gayoung Lee (NAVER AI Lab), Sungrae Park(Upstage). [RewriteNet: Reliable Scene Text Editing with Implicit Decomposition of Text Contents and Styles.](https://arxiv.org/abs/2107.11041v2) (17:00 - 18:00) Sihyun Yu (KAIST), Jihoon Tack (KAIST), Sangwoo Mo (KAIST), Hyunsu Kim (NAVER AI Lab), Junho Kim (NAVER AI Lab), Jung-Woo Ha (NAVER AI Lab), Jinwoo Shin (KAIST). [Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks](https://arxiv.org/abs/2202.10571). [**FGVC9 Workshop**](https://sites.google.com/view/fgvc9/home)**: June 19.** (10:30 - 12:00) Yunji Kim(NAVER AI LAB), Jung-Woo Ha(NAVER AI LAB) [Contrastive Fine-grained Class Clustering via Generative Adversarial Networks](https://drive.google.com/file/d/1UNu0aYOE0Zt07bRTXWGnOryPZ0oyKlCL/view). #### \[Poster 1.1] June. 21. 10:00\~12:30 Jongin Lim (SNU), Sangdoo Yun (NAVER AI LAB), Seulki Park (SNU & NAVER AI Lab intern), Jin Young Choi (SNU). [Hypergraph-Induced Semantic Tuplet Loss for Deep Metric Learning.](https://openaccess.thecvf.com/content/CVPR2022/papers/Lim_Hypergraph-Induced_Semantic_Tuplet_Loss_for_Deep_Metric_Learning_CVPR_2022_paper.pdf) #### \[Poster 1.2] June. 21. 14:30\~17:00 Beomyoung Kim (NAVER CLOVA), Youngjoon Yoo (NAVER CLOVA), Chaeun Rhee (Inha Univ.), Junmo Kim (KAIST). [Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-Refinement](https://arxiv.org/abs/2109.09477). Jin Kim(Yonsei Univ.), Jiyoung Lee (NAVER AI Lab), JungIn Park (Yonsei Univ.), Dongbo Min (Ewha Univ.), Kwanghoon Sohn (Yonsei Univ.). [Pin the Memory: Learning to Generalize Semantic Segmentation. ](https://arxiv.org/abs/2204.03609) #### \[Poster 2.1] June. 22. 10:00\~12:30 Jun-Hyuk Kim (Yonsei Univ. & NAVER AI Lab intern), Byeongho Heo (NAVER AI Lab), Jong-Seok Lee (Yonsei Univ.). [Joint Global and Local Hierarchical Priors for Learned Image Compression](https://arxiv.org/abs/2112.04487). Seulki Park (SNU & NAVER AI Lab intern) , Youngkyu Hong (NAVER AI Lab), Byeongho Heo (NAVER AI Lab), Sangdoo Yun (NAVER AI Lab), Jin Young Choi (SNU). [The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classification. ](https://arxiv.org/abs/2112.00412#:~:text=version%2C%20v3\)%5D-,The%20Majority%20Can%20Help%20The%20Minority%3A%20Context-rich%20Minority,Oversampling%20for%20Long-tailed%20Classification\&text=The%20problem%20of%20class%20imbalanced,of%20data%20from%20minority%20classes.) YeongWoo Nam (GIST & NAVER AI Lab intern), Mohammad Mostafavi (Lunit), Kuk-Jin Yoon (KAIST), Jonghyun Choi (Yonsei Univ. & NAVER AI Lab). [Stereo Depth from Events Cameras: Concentrate and Focus on the Future. ](https://openaccess.thecvf.com/content/CVPR2022/papers/Nam_Stereo_Depth_From_Events_Cameras_Concentrate_and_Focus_on_the_CVPR_2022_paper.pdf) #### \[Oral 2.2.3] June 22. 13:30\~15:00 Kanghyun Choi (Yonsei Univ.), Hye Yoon Lee (Yonsei Univ.), Deokki Hong (Yonsei Univ.),Joonsang Yu (NAVER CLOVA),Noseong Park (Yonsei Univ.), Youngsok Kim (Yonsei Univ.),Jinho Lee (Yonsei Univ.). It's All In the Teacher: Zero-Shot Quantization Brought Closer to the Teacher. **\[Poster 2.2] June. 22. 14:30\~17:00** Jihwan Bang (NAVER CLOVA),Hyunseo Koh (GIST & NAVER AI Lab intern),Seulki Park (SNU & NAVER AI Lab intern),Hwanjun Song (NAVER AI Lab),Jung-Woo Ha (NAVER AI Lab), Jonghyun Choi (Yonsei U.). [Online Continual Learning on a Contaminated Data Stream with Blurry Task Boundaries. ](https://arxiv.org/abs/2203.15355) Dahyun Kim (GIST & NAVER AI Lab intern), Jonghyun Choi (Yonsei Univ. & NAVER AI Lab). [Unsupervised Representation Learning for Binary Networks by Joint Classifier Learning](https://arxiv.org/abs/2110.08851#:~:text=Unsupervised%20Representation%20Learning%20for%20Binary%20Networks%20by%20Joint%20Classifier%20Learning,-Dahyun%20Kim%2C%20Jonghyun\&text=Self-supervised%20learning%20is%20a,readily%20deployable%20to%20edge%20devices.) Sangwon Jung (SNU & NAVER AI Lab intern), Sanghyuk Chun (NAVER AI Lab), Taesup Moon (SNU). [Learning Fair Classifiers with Partially Annotated Group Labels](https://arxiv.org/abs/2111.14581). **\[Poster 3.1] June. 23. 10:00\~12:30** Junho Kim (NAVER AI Lab) , Yunjey Choi (NAVER AI Lab), Youngjung Uh (Yonsei Univ.). [Feature Statistics Mixing Regularization for Generative Adversarial Networks](https://arxiv.org/abs/2112.04120). Jisoo Mok (SNU & NAVER AI Lab intern), Byunggook Na (SNU), Ji-Hoon Kim (NAVER CLOVA), Dongyoon Han (NAVER AI Lab), Sungroh Yoon (SNU). [Demystifying the Neural Tangent Kernel from a Practical Perspective: Can it be trusted for Neural Architecture Search without training?.](https://openaccess.thecvf.com/content/CVPR2022/papers/Mok_Demystifying_the_Neural_Tangent_Kernel_From_a_Practical_Perspective_Can_CVPR_2022_paper.pdf) **\[Poster 3.2] June. 23. 14:00\~17:00** Jungin Park (Yonsei Univ.), Jiyoung Lee (NAVER AI Lab), Ig-Jae Kim (KIST), Kwanghoon Sohn (Yonsei Univ.). [Probabilistic Representations for Video Contrastive Learning. ](https://arxiv.org/abs/2204.03946) **\[Poster 4.1] June. 24. 10:00\~12:30** Jungbeom Lee (SNU), Seong Joon Oh (NAVER AI Lab), Sangdoo Yun (NAVER AI LAB), Junsuk Choe (Sogang Univ.), Eunji Kim (SNU), Sungroh Yoon (SNU). [Weakly Supervised Semantic Segmentation using Out-of-Distribution Data](https://arxiv.org/abs/2203.03860). ## NAVER NIGHT \[1st Event] June 20. 18:30\~21:30 **Closed** \[2nd Event] June 23. 18:30\~21:30 **Closed** --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://naver-career.gitbook.io/en/teams/clova-cic/events/clova-ai-lab-cvpr-2022.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.