36 citations · 90 across the 21 of their papers we have counts for
21 papers
GeoDANO: Geometric VLM with Domain Agnostic Vision Encoder
Seunghyuk Cho, Zhenyue Qin, Yang Liu +3
We introduce GeoDANO, a geometric vision-language model (VLM) with a domain-agnostic vision encoder, for solving plane geometry problems. Although VLMs have been employed for solvi…
EPIC: Graph Augmentation with Edit Path Interpolation via Learnable Cost
Jaeseung Heo, Seungbeom Lee, Sungsoo Ahn +1
Data augmentation plays a critical role in improving model performance across various domains, but it becomes challenging with graph data due to their complex and irregular structu…
Feature Unlearning for Pre-trained GANs and VAEs
Saemi Moon, Seunghyuk Cho, Dongwoo Kim
We tackle the problem of feature unlearning from a pre-trained image generative model: GANs and VAEs. Unlike a common unlearning task where an unlearning target is a subset of the…
Item-based Variational Auto-encoder for Fair Music Recommendation
Jinhyeok Park, Dain Kim, Dongwoo Kim
We present our solution for the EvalRS DataChallenge. The EvalRS DataChallenge aims to build a more realistic recommender system considering accuracy, fairness, and diversity in ev…
Substructure-Atom Cross Attention for Molecular Representation Learning
Jiye Kim, Seungbeom Lee, Dongwoo Kim +2
Designing a neural network architecture for molecular representation is crucial for AI-driven drug discovery and molecule design. In this work, we propose a new framework for molec…
Hyperbolic VAE via Latent Gaussian Distributions
Seunghyuk Cho, Juyong Lee, Dongwoo Kim
We propose a Gaussian manifold variational auto-encoder (GM-VAE) whose latent space consists of a set of Gaussian distributions. It is known that the set of the univariate Gaussian…
MetaSSD: Meta-Learned Self-Supervised Detection
Moon Jeong Park, Jungseul Ok, Yo-Seb Jeon +1
Deep learning-based symbol detector gains increasing attention due to the simple algorithm design than the traditional model-based algorithms such as Viterbi and BCJR. The supervis…
Few-Shot Unlearning by Model Inversion
Youngsik Yoon, Jinhwan Nam, Hyojeong Yun +3
We consider a practical scenario of machine unlearning to erase a target dataset, which causes unexpected behavior from the trained model. The target dataset is often assumed to be…
Strengthening Skeletal Action Recognizers via Leveraging Temporal Patterns
Zhenyue Qin, Pan Ji, Dongwoo Kim +3
Skeleton sequences are compact and lightweight. Numerous skeleton-based action recognizers have been proposed to classify human behaviors. In this work, we aim to incorporate compo…
A Rotated Hyperbolic Wrapped Normal Distribution for Hierarchical Representation Learning
Seunghyuk Cho, Juyong Lee, Jaesik Park +1
We present a rotated hyperbolic wrapped normal distribution (RoWN), a simple yet effective alteration of a hyperbolic wrapped normal distribution (HWN). The HWN expands the domain…
Representation-Centric Survey of Supervised Skeletal Action Recognition and the New Benchmark
Yang Liu, Jiyao Yang, Madhawa Perera +8
3D skeletal action recognition has emerged as a powerful alternative to traditional RGB and depth-based approaches, offering robustness to environmental variations, computational e…
Anonymization for Skeleton Action Recognition
Saemi Moon, Myeonghyeon Kim, Zhenyue Qin +2
Skeleton-based action recognition attracts practitioners and researchers due to the lightweight, compact nature of datasets. Compared with RGB-video-based action recognition, skele…
Robust Deep Learning from Crowds with Belief Propagation
Hoyoung Kim, Seunghyuk Cho, Dongwoo Kim +1
Crowdsourcing systems enable us to collect large-scale dataset, but inherently suffer from noisy labels of low-paid workers. We address the inference and learning problems using su…
Informative Class Activation Maps
Zhenyue Qin, Dongwoo Kim, Tom Gedeon
We study how to evaluate the quantitative information content of a region within an image for a particular label. To this end, we bridge class activation maps with information theo…
Neural Network Classifier as Mutual Information Evaluator
Zhenyue Qin, Dongwoo Kim, Tom Gedeon
Cross-entropy loss with softmax output is a standard choice to train neural network classifiers. We give a new view of neural network classifiers with softmax and cross-entropy as…
Position-Sensing Graph Neural Networks: Proactively Learning Nodes Relative Positions
Zhenyue Qin, Yiqun Zhang Saeed Anwar, Dongwoo Kim +3
Most existing graph neural networks (GNNs) learn node embeddings using the framework of message passing and aggregation. Such GNNs are incapable of learning relative positions betw…
Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition
Zhenyue Qin, Yang Liu, Pan Ji +5
Skeleton sequences are lightweight and compact, and thus are ideal candidates for action recognition on edge devices. Recent skeleton-based action recognition methods extract featu…
Invertible Denoising Network: A Light Solution for Real Noise Removal
Yang Liu, Zhenyue Qin, Saeed Anwar +4
Invertible networks have various benefits for image denoising since they are lightweight, information-lossless, and memory-saving during back-propagation. However, applying inverti…
Roughly Collected Dataset for Contact Force Sensing Catheter
Seunghyuk Cho, Minsoo Koo, Dongwoo Kim +4
With rise of interventional cardiology, Catheter Ablation Therapy (CAT) has established itself as a first-line solution to treat cardiac arrhythmia. Although CAT is a promising tec…
Rethinking Softmax with Cross-Entropy: Neural Network Classifier as Mutual Information Estimator
Zhenyue Qin, Dongwoo Kim, Tom Gedeon
Mutual information is widely applied to learn latent representations of observations, whilst its implication in classification neural networks remain to be better explained. We sho…
Softmax Is Not an Artificial Trick: An Information-Theoretic View of Softmax in Neural Networks
Zhenyue Qin, Dongwoo Kim
Despite great popularity of applying softmax to map the non-normalised outputs of a neural network to a probability distribution over predicting classes, this normalised exponentia…