연구 성과

Recommendation in Offline Stores: A Gamification Approach for Learning the Spatiotemporal Representation of Indoor Shopping (KDD 22), Prof.Chiehyeon Lim

Recommendation in Offline Stores Title Recommendation in Offline Stores Author Shin, Jongkyung; Lee, Changhun; Lim, Chiehyeon; Shin, Yunmo; Lim, Junseok Issue Date 2022-08-18 Publisher ACM Citation International Conference on Knowledge Discovery and Data Mining Abstract With the current advancements in mobile and sensing technologies used to collect real-time data...

Robust combination of distributed gradients under adversarial perturbations (CVPR 22), Prof.Kwang In Kim

Robust Combination of Distributed Gradients Under Adversarial Perturbations Abstract: We consider distributed (gradient descent-based) learning scenarios where the server combines the gradients of learning objectives gathered from local clients. As individual data collection and learning environments can vary, some clients could transfer erroneous gradients e.g. due to...

Robust Imitation Learning against Variations in Environment Dynamics (ICML22), Prof.Seungyul Han

Robust Imitation Learning against Variations in Environment Dynamics Jongseong Chae, Seungyul Han, Whiyoung Jung, Myungsik Cho, Sungho Choi, Youngchul Sung In this paper, we propose a robust imitation learning (IL) framework that improves the robustness of IL when environment dynamics are perturbed. The existing IL framework trained in a single environment can...

Robust tests in online decision-making(AAAI 22), Prof. Gi-Soo Kim

Robust Tests in Online Decision-Making Gi-Soo Kim Ulsan National Institute of Science and Technology (UNIST) Jane P Kim Stanford University School of Medicine Hyun-Joon Yang Stanford University School of Medicine   DOI: https://doi.org/10.1609/aaai.v36i9.21240 Keywords: Reasoning Under Uncertainty (RU)   Abstract Bandit algorithms are widely used in sequential decision problems to maximize the cumulative reward. One potential...

3rd place in HANDS challenge: Motion reconstruction held in ICCV’23

LAIT’s (Prof. Jaejun Yoo) paper accepted to NeurIPS 2023

TopP&R: Robust Support Estimation Approach for Evaluating Fidelity and Diversity in Generative Models Pumjun Kim, Yoojin Jang, Jisu Kim, and Jaejun Yoo* We propose a robust and reliable evaluation metric for generative models called Topological Precision and Recall (TopP&R, pronounced “topper”), which systematically estimates supports by retaining only topologically and statistically significant features with...

RVI Lab’s (Prof. Kyungdon Joo) papers accepted to ICCV 2021!

One paper of Robotics and Visual Intelligence (RVI) lab is accepted to IEEE International Conference on Computer Vision (ICCV), 2021, which is one of the top conferences in computer vision! Existing vanishing point (VP) estimation methods rely on pre-extracted image lines and/or prior knowledge of...

RVI Lab’s (Prof. Kyungdon Joo) papers accepted to TPAMI!

One paper of Robotics and Visual Intelligence (RVI) lab is accepted to IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), which is one of the top journals in AI/CS/EE (IF:16.389)! We propose a new linear RGB-D simultaneous localization and mapping (L-SLAM) formulation by utilizing planar...

UNIST Service & Knowledge Lab’s (Prof. Chiehyeon Lim) paper accepted to NeurIPS 2021

UNIST AIGS/IE Service Engineering & Knowledge Discovery Lab (Prof. Chiehyeon Lim)’s paper has been accepted to the Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track 2021: “MIND dataset for diet planning and dietary healthcare with machine learning: Dataset creation using combinatorial optimization and controllable generation...

UVL Lab’s (Prof. Seungryul Baek) paper accepted to ICCV 2021

A paper of UNIST Vision & Learning Lab (UVLL) is accepted to IEEE International Conference on Computer Vision (ICCV) 2021, which is one of top conferences in computer vision field. We present a new algorithm that accurately estimates interacting hand poses in such a challenging scenario....