20 citations · 26 across the 17 of their papers we have counts for
19 papers
Anatomy-Structured Hierarchical MIL for Weakly-Supervised Thoracic Disease Detection in Chest X-rays
Jeongin Kim, Sohyun Ahn, Seo Young Kang +6
Weakly-supervised thoracic disease detection in chest X-rays (CXR) is challenging due to subtle appearances and complex anatomical overlap, motivating anatomy-aware modeling for im…
What You Ask is What You Ground: Bridging Question Intent to Temporal Evidence for Grounded VideoQA
Jinhwan Seo, Kyubeom Han, Jumin Lee +2
We study a critical yet overlooked failure mode in Grounded Video Question Answering: question-invariant grounding, where models predict nearly identical temporal segments for diff…
JointHOI: Jointly Generating Contact Maps Enhances Hand Object Interaction Generation
Mingyeong Song, Jungbin Cho, Jisoo Kim +5
Text driven hand object interaction (HOI) generation is gaining attention for immersive applications and robotics, yet producing physically plausible interactions remains challengi…
Ordering Matters: Rank-Aware Selective Fusion for Blended Emotion Recognition
Junghyun Lee, Hyunseo Kim, Hanna Jang +1
Blended emotion recognition is challenging because emotions are often expressed as mixtures of subtle and overlapping multimodal cues rather than a single dominant signal. We propo…
Explicit Time-Frequency Dynamics for Skeleton-Based Gait Recognition
Seoyeon Ko, Yeojin Song, Egene Chung +3
Skeleton-based gait recognizers excel at modeling spatial configurations but often underuse explicit motion dynamics that are crucial under appearance changes. We introduce a plug-…
Random Is Hard to Beat: Active Selection in online DPO with Modern LLMs
Giyeong Oh, Junghyun Lee, Jaehyun Park +3
Modern LLMs inherit strong priors from web-scale pretraining, which can limit the headroom of post-training data-selection strategies. While Active Preference Learning (APL) seeks…
SIREN: Spatially-Informed Reconstruction of Binaural Audio with Vision
Mingyeong Song, Seoyeon Ko, Junhyug Noh
Binaural audio delivers spatial cues essential for immersion, yet most consumer videos are monaural due to capture constraints. We introduce SIREN, a visually guided mono to binaur…
Vicinity-Guided Discriminative Latent Diffusion for Privacy-Preserving Domain Adaptation
Jing Wang, Wonho Bae, Jiahong Chen +2
Recent work on latent diffusion models (LDMs) has focused almost exclusively on generative tasks, leaving their potential for discriminative transfer largely unexplored. We introdu…
Beyond Softmax: Dual-Branch Sigmoid Architecture for Accurate Class Activation Maps
Yoojin Oh, Junhyug Noh
Class Activation Mapping (CAM) and its extensions have become indispensable tools for visualizing the evidence behind deep network predictions. However, by relying on a final softm…
Pinpointing Trigger Moment for Grounded Video QA: Enhancing Spatio-temporal Grounding in Multimodal Large Language Models
Jinhwan Seo, Yoonki Cho, Junhyug Noh +1
In this technical report, we introduce a framework to address Grounded Video Question Answering (GVQA) task for the ICCV 2025 Perception Test Challenge. The GVQA task demands robus…
Diffusion-Driven Two-Stage Active Learning for Low-Budget Semantic Segmentation
Jeongin Kim, Wonho Bae, YouLee Han +4
Semantic segmentation demands dense pixel-level annotations, which can be prohibitively expensive - especially under extremely constrained labeling budgets. In this paper, we addre…
SteeringTTA: Guiding Diffusion Trajectories for Robust Test-Time-Adaptation
Jihyun Yu, Yoojin Oh, Wonho Bae +2
Test-time adaptation (TTA) aims to correct performance degradation of deep models under distribution shifts by updating models or inputs using unlabeled test data. Input-only diffu…
Generalized Coverage for More Robust Low-Budget Active Learning
Wonho Bae, Junhyug Noh, Danica J. Sutherland
The ProbCover method of Yehuda et al. is a well-motivated algorithm for active learning in low-budget regimes, which attempts to "cover" the data distribution with balls of a given…
Scalp Diagnostic System With Label-Free Segmentation and Training-Free Image Translation
Youngmin Kim, Saejin Kim, Hoyeon Moon +2
Scalp disorders are highly prevalent worldwide, yet remain underdiagnosed due to limited access to expert evaluation and the high cost of annotation. Although AI-based approaches h…
Object Discovery via Contrastive Learning for Weakly Supervised Object Detection
Jinhwan Seo, Wonho Bae, Danica J. Sutherland +2
Weakly Supervised Object Detection (WSOD) is a task that detects objects in an image using a model trained only on image-level annotations. Current state-of-the-art models benefit…
One Weird Trick to Improve Your Semi-Weakly Supervised Semantic Segmentation Model
Wonho Bae, Junhyug Noh, Milad Jalali Asadabadi +1
Semi-weakly supervised semantic segmentation (SWSSS) aims to train a model to identify objects in images based on a small number of images with pixel-level labels, and many more im…
What and When to Look?: Temporal Span Proposal Network for Video Relation Detection
Sangmin Woo, Junhyug Noh, Kangil Kim
Identifying relations between objects is central to understanding the scene. While several works have been proposed for relation modeling in the image domain, there have been many…
Tackling the Challenges in Scene Graph Generation with Local-to-Global Interactions
Sangmin Woo, Junhyug Noh, Kangil Kim
In this work, we seek new insights into the underlying challenges of the Scene Graph Generation (SGG) task. Quantitative and qualitative analysis of the Visual Genome dataset impli…
LID 2020: The Learning from Imperfect Data Challenge Results
Yunchao Wei, Shuai Zheng, Ming-Ming Cheng +32
Learning from imperfect data becomes an issue in many industrial applications after the research community has made profound progress in supervised learning from perfectly annotate…