Seong Joon Oh

8.5k total citations · 2 hit papers
24 papers, 3.8k citations indexed

About

Seong Joon Oh is a scholar working on Computer Vision and Pattern Recognition, Artificial Intelligence and Sociology and Political Science. According to data from OpenAlex, Seong Joon Oh has authored 24 papers receiving a total of 3.8k indexed citations (citations by other indexed papers that have themselves been cited), including 20 papers in Computer Vision and Pattern Recognition, 18 papers in Artificial Intelligence and 1 paper in Sociology and Political Science. Recurrent topics in Seong Joon Oh's work include Domain Adaptation and Few-Shot Learning (10 papers), Advanced Neural Network Applications (9 papers) and Advanced Image and Video Retrieval Techniques (7 papers). Seong Joon Oh is often cited by papers focused on Domain Adaptation and Few-Shot Learning (10 papers), Advanced Neural Network Applications (9 papers) and Advanced Image and Video Retrieval Techniques (7 papers). Seong Joon Oh collaborates with scholars based in Germany, South Korea and United States. Seong Joon Oh's co-authors include Sangdoo Yun, Sanghyuk Chun, Dongyoon Han, Junsuk Choe, Youngjoon Yoo, Bernt Schiele, Mario Fritz, Sungrae Park, Jeonghun Baek and Rodrigo Benenson and has published in prestigious journals such as IEEE Transactions on Pattern Analysis and Machine Intelligence, Pattern Recognition and 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

In The Last Decade

Seong Joon Oh

23 papers receiving 3.7k citations

Hit Papers

align trajectories

What are hit papers?

Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the same subfield and year (this is the minimum needed to enter the top 1%, not the average within it), or reaches the top citation threshold in at least one of its specific research topics.

CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features

2019 2.6k citations Sangdoo Yun, Dongyoon Han et al. profile →
What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis

2019 296 citations Jeonghun Baek, Geewook Kim et al. profile →

Peers

Countries citing papers authored by Seong Joon Oh

Since Specialization

Citations

This map shows the geographic impact of Seong Joon Oh's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Seong Joon Oh with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Seong Joon Oh more than expected).

Fields of papers citing papers by Seong Joon Oh

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Seong Joon Oh. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Seong Joon Oh. The network helps show where Seong Joon Oh may publish in the future.

Co-authorship network of co-authors of Seong Joon Oh

This figure shows the co-authorship network connecting the top 25 collaborators of Seong Joon Oh. A scholar is included among the top collaborators of Seong Joon Oh based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Seong Joon Oh. Seong Joon Oh is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

Sort: Min cites: Since: Top N: Style:

20 of 20 papers shown

#	Work	Indexed citations
1	Calibrating Large Language Models Using Their Generations Only 2024 ·(unknown), (unknown), Hwaran Lee, Sangdoo Yun, Seong Joon Oh	2
2	TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification 2024 ·(unknown), (unknown), Hwaran Lee, Sangdoo Yun, Seong Joon Oh	0
3	Evaluation for Weakly Supervised Object Localization: Protocol, Metrics, and Datasets 2022 ·IEEE Transactions on Pattern Analysis and Machine Intelligence ·Junsuk Choe, Seong Joon Oh, Sanghyuk Chun, Seungho Lee, Zeynep Akata, Hyunjung Shim	11
4	AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights 2021 ·International Conference on Learning Representations ·Byeongho Heo, Sanghyuk Chun, Seong Joon Oh, Dongyoon Han, Sangdoo Yun, (unknown), Youngjung Uh, Jung-Woo Ha	7
5	Rethinking Spatial Dimensions of Vision Transformers 2021 ·2021 IEEE/CVF International Conference on Computer Vision (ICCV) ·Byeongho Heo, Sangdoo Yun, Dongyoon Han, Sanghyuk Chun, Junsuk Choe, Seong Joon Oh	2
6	Region-based dropout with attention prior for weakly supervised object localization 2021 ·Pattern Recognition ·Junsuk Choe, Dongyoon Han, Sangdoo Yun, Jung-Woo Ha, Seong Joon Oh, Hyunjung Shim	17
7	Probabilistic Embeddings for Cross-Modal Retrieval 2021 ·Sanghyuk Chun, Seong Joon Oh, Rafael Sampaio de Rezende, Yannis Kalantidis, Diane Larlus	145
8	Slowing Down the Weight Norm Increase in Momentum-based Optimizers 2020 ·arXiv (Cornell University) ·Byeongho Heo, Sanghyuk Chun, Seong Joon Oh, Dongyoon Han, Sangdoo Yun, Youngjung Uh, Jung-Woo Ha	9
9	What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis breakdown → 2019 ·Jeonghun Baek, Geewook Kim, Junyeop Lee, Sungrae Park, Dongyoon Han, Sangdoo Yun, Seong Joon Oh, Hwalsuk Lee	296
10	CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features breakdown → 2019 ·Sangdoo Yun, Dongyoon Han, Sanghyuk Chun, Seong Joon Oh, Youngjoon Yoo, Junsuk Choe	2641
11	Learning De-biased Representations with Biased Representations 2019 ·arXiv (Cornell University) ·Hyojin Bahng, Sanghyuk Chun, Sangdoo Yun, Jaegul Choo, Seong Joon Oh	56
12	Understanding and Controlling User Linkability in Decentralized Learning. 2018 ·Max Planck Digital Library ·Tribhuvanesh Orekondy, Seong Joon Oh, Bernt Schiele, Mario Fritz	7
13	Modeling Uncertainty with Hedged Instance Embedding 2018 ·KAIST Institutional Repository (KAIST) ·Seong Joon Oh, Kevin Murphy, (unknown), Joseph Roth, Florian Schroff, Andrew Gallagher	10
14	Person Recognition in Personal Photo Collections 2018 ·IEEE Transactions on Pattern Analysis and Machine Intelligence ·Seong Joon Oh, Rodrigo Benenson, Mario Fritz, Bernt Schiele	10
15	Natural and Effective Obfuscation by Head Inpainting 2018 ·Qianru Sun, Liqian Ma, Seong Joon Oh, Luc Van Gool, Bernt Schiele, Mario Fritz	128
16	Adversarial Image Perturbation for Privacy Protection A Game Theory Perspective 2017 ·Seong Joon Oh, Mario Fritz, Bernt Schiele	68
17	Exploiting Saliency for Object Segmentation from Image Level Labels 2017 ·UvA-DARE (University of Amsterdam) ·Seong Joon Oh, Rodrigo Benenson, Anna Khoreva, Zeynep Akata, Mario Fritz, Bernt Schiele	126
18	Generating Descriptions with Grounded and Co-referenced People 2017 ·Anna Rohrbach, Marcus Rohrbach, Siyu Tang, Seong Joon Oh, Bernt Schiele	28
19	I-Pic 2016 ·Paarijaat Aditya, Rijurekha Sen, Peter Druschel, Seong Joon Oh, Rodrigo Benenson, Mario Fritz, Bernt Schiele, Bobby Bhattacharjee, Tong Wu	72
20	Person Recognition in Personal Photo Collections 2015 ·Seong Joon Oh, Rodrigo Benenson, Mario Fritz, Bernt Schiele	23

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact