[NeurIPS 2022] Geometric order learning

Our paper on order learning will be presented in Neurips 2022.

Seon-Ho Lee, Nyeong Ho Shin, and Chang-Su Kim, “Geometric order learning for rank estimation,” in Proc. NeurIPS, New Orleans, Louisiana, Nov. 2022.


Order learning is a new concept that we proposed in a series of papers:

1. Kyungsun Lim, Nyeong-Ho Shin, Young-Yoon Lee, and Chang-Su Kim, “Order learning and its application to age estimation,” ICLR 2020.

2. Seon-Ho Lee and Chang-Su Kim, “Deep repulsive clustering of ordered data based on order-identity decomposition” ICLR 2021.

3. Nyeong Ho Shin, Seon-Ho Lee, and Chang-Su Kim, “Moving window regression: A novel approach to ordinal regression,” CVPR 2022.

4. Seon-Ho Lee and Chang-Su Kim, “Order learning using partially ordered data via chainization,” ECCV 2022.

5. Seon-Ho Lee, Nyeong Ho Shin, and Chang-Su Kim, “Geometric order learning for rank estimation,” NeurIPS 2022.


It has been a productive year for Ho brothers. Congratulations!

[ECCV 2022] Order learning and depth estimation

We will present our technologies on order learning and depth estimation in ECCV 2022, which will be in Tel Aviv, Israel this October.

Seon-Ho Lee and Chang-Su Kim, “Order Learning Using Partially Ordered Data via Chainization
Jinyoung Jun, Jae-Han Lee, Chul Lee, and Chang-Su Kim, “Depth Map Decomposition for Monocular Depth Estimation

Congratulations to Seon-Ho and Jinyoung for these achievements !
Many thanks to Dr. Jae-Han Lee and Prof. Chul Lee for excellent supervision !

[ICIP 2022] Video frame extrapolation

We are pleased to announce that our paper on video frame extrapolation (not interpolation) will be presented in ICIP 2022, which will be held in Bordeaux, France this October.

Seunggyun Woo, Junheum Park, and Chang-Su Kim, “Future frame extrapolation using future cost volume,” in Proc. ICIP, Bordeaux, France, Oct. 2022.

Congratulations to Seunggyun and Junheum!

[CVPR 2022] Three orals and one poster

We will present four papers on image compression, object descriptors, and order learning in CVPR 2022. Three of them are orals. Well done, Jae-Han and Seungmin, Dongkwon and Wonhui, Wonhui and Dongkwon, and Nyeong-Ho and Seon-Ho!

  • Jae-Han Lee, Seungmin Jeon, Kwang Pyo Choi, Youngo Park, and Chang-Su Kim, “DPICT: Deep Progressive Image Compression Using Trit-Planes” (Oral)
  • Dongkwon Jin, Wonhui Park, Seong-Gyun Jeong, Heeyeon Kwon, and Chang-Su Kim, “Eigenlanes: Data-Driven Lane Descriptors for Structurally Diverse Lanes” (Poster)
  • Wonhui Park, Dongkwon Jin, and Chang-Su Kim, “Eigencontours: Novel Contour Descriptors Based on Low-Rank Approximation” (Oral)
  • Nyeong Ho Shin, Seon-Ho Lee, and Chang-Su Kim, “Moving Window Regression: A Novel Approach to Ordinal Regression” (Oral)

Congratulations to Jae-Han and Seungmin.

Congratulations to Dongkown and Wonhui, aka eigenbrothers.

Congratulations to Nyeong Ho and Seon-Ho.

Also many thanks to our colleagues Kwang Pyo Choi, Youngo Park, Seong-Gyun Jeong, and Heeyeon Kwon!

[2022] Dr. Lee’s JVCI paper

This February MCL produced 17th Ph.D., Dr. Jae-Han Lee, who published his 2nd journal paper today.

Jae-Han Lee and Chang-Su Kim, “Single-image depth estimation using relative depths,” J. Vis. Commun. Image Represent., vol. 84, no. 103459, Apr. 2022.