923 citations · 1.2k across the 21 of their papers we have counts for
21 papers
Robust and Interpretable Adaptation of Equivariant Materials Foundation Models via Sparsity-promoting Fine-tuning
Youngwoo Cho, Seunghoon Yi, Wooil Yang +6
Pre-trained materials foundation models, or machine learning interatomic potentials, leverage general physicochemical knowledge to effectively approximate potential energy surfaces…
VisAlign: Dataset for Measuring the Degree of Alignment between AI and Humans in Visual Perception
Jiyoung Lee, Seungho Kim, Seunghyun Won +6
AI alignment refers to models acting towards human-intended goals, preferences, or ethical principles. Given that most large-scale deep learning models act as black boxes and canno…
V2Meow: Meowing to the Visual Beat via Video-to-Music Generation
Kun Su, Judith Yue Li, Qingqing Huang +8
Video-to-music generation demands both a temporally localized high-quality listening experience and globally aligned video-acoustic signatures. While recent music generation models…
Towards Efficient Neural Scene Graphs by Learning Consistency Fields
Yeji Song, Chaerin Kong, Seoyoung Lee +2
Neural Radiance Fields (NeRF) achieves photo-realistic image rendering from novel views, and the Neural Scene Graphs (NSG) \cite{ost2021neural} extends it to dynamic scenes (video)…
MuLan: A Joint Embedding of Music Audio and Natural Language
Qingqing Huang, Aren Jansen, Joonseok Lee +3
Music tagging and content-based retrieval systems have traditionally been constructed using pre-defined ontologies covering a rigid set of music attributes or text queries. This pa…
Bilateral Self-unbiased Learning from Biased Implicit Feedback
Jae-woong Lee, Seongmin Park, Joonseok Lee +1
Implicit feedback has been widely used to build commercial recommender systems. Because observed feedback represents users' click logs, there is a semantic gap between true relevan…
Boundary-aware Self-supervised Learning for Video Scene Segmentation
Jonghwan Mun, Minchul Shin, Gunsoo Han +4
Self-supervised learning has drawn attention through its effectiveness in learning in-domain representations with no ground-truth annotations; in particular, it is shown that prope…
S-Walk: Accurate and Scalable Session-based Recommendationwith Random Walks
Minjin Choi, Jinhong Kim, Joonsek Lee +2
Session-based recommendation (SR) predicts the next items from a sequence of previous items consumed by an anonymous user. Most existing SR models focus only on modeling intra-sess…
Continuous-Time Video Generation via Learning Motion Dynamics with Neural ODE
Kangyeol Kim, Sunghyun Park, Junsoo Lee +4
In order to perform unconditional video generation, we must learn the distribution of the real-world videos. In an effort to synthesize high-quality videos, various studies attempt…
Exploration into Translation-Equivariant Image Quantization
Woncheol Shin, Gyubok Lee, Jiyoung Lee +3
This is an exploratory study that discovers the current image quantization (vector quantization) do not satisfy translation equivariance in the quantized space due to aliasing. Ins…
Local Collaborative Autoencoders
Minjin Choi, Yoonki Jeong, Joonseok Lee +1
Top-N recommendation is a challenging problem because complex and sparse user-item interactions should be adequately addressed to achieve high-quality recommendation results. The l…
Session-aware Linear Item-Item Models for Session-based Recommendation
Minjin Choi, jinhong Kim, Joonseok Lee +2
Session-based recommendation aims at predicting the next item given a sequence of previous items consumed in the session, e.g., on e-commerce or multimedia streaming services. Spec…
A Hierarchical Multi-Modal Encoder for Moment Localization in Video Corpus
Bowen Zhang, Hexiang Hu, Joonseok Lee +5
Identifying a short segment in a long video that semantically matches a text query is a challenging task that has important application potentials in language-based video search, b…
Vid-ODE: Continuous-Time Video Generation with Neural Ordinary Differential Equation
Sunghyun Park, Kangyeol Kim, Junsoo Lee +4
Video generation models often operate under the assumption of fixed frame rates, which leads to suboptimal performance when it comes to handling flexible frame rates (e.g., increas…
Saving Face: Investigating the Ethical Concerns of Facial Recognition Auditing
Inioluwa Deborah Raji, Timnit Gebru, Margaret Mitchell +3
Although essential to revealing biased performance, well intentioned attempts at algorithmic auditing can have effects that may harm the very populations these measures are meant t…
N-GCN: Multi-scale Graph Convolution for Semi-supervised Node Classification
Sami Abu-El-Haija, Amol Kapoor, Bryan Perozzi +1
Graph Convolutional Networks (GCNs) have shown significant improvements in semi-supervised learning on graph-structured data. Concurrently, unsupervised learning of graph embedding…
YouTube-8M: A Large-Scale Video Classification Benchmark
Sami Abu-El-Haija, Nisarg Kothari, Joonseok Lee +4
Many recent advancements in Computer Vision are attributed to large datasets. Open-source software packages for Machine Learning and inexpensive commodity hardware have reduced the…
Optimizing a Personalized Multigram Cellphone Keypad
Joonseok Lee, R. I., McKay
Current layouts for alphabetic input on mobile phone keypads are very inefficient. We propose a genetic algorithm (GA) to find a suitable keypad layout for each user, based on thei…
Personalized Academic Research Paper Recommendation System
Joonseok Lee, Kisung Lee, Jennifer G. Kim
A huge number of academic papers are coming out from a lot of conferences and journals these days. In these circumstances, most researchers rely on key-based search or browsing thr…
Matrix Approximation under Local Low-Rank Assumption
Joonseok Lee, Seungyeon Kim, Guy Lebanon +1
Matrix approximation is a common tool in machine learning for building accurate prediction models for recommendation systems, text mining, and computer vision. A prevalent assumpti…
A Comparative Study of Collaborative Filtering Algorithms
Joonseok Lee, Mingxuan Sun, Guy Lebanon
Collaborative filtering is a rapidly advancing research area. Every year several new techniques are proposed and yet it is not clear which of the techniques work best and under wha…