Suha Kwak

Pohang University of Science and Technology — South Korea

Computer Science · Physical Sciences

32h-index5.5kcitations149works1.22yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Human Pose and Action Recognition(42), Domain Adaptation and Few-Shot Learning(40), Multimodal Machine Learning Applications(31), Advanced Neural Network Applications(25), Advanced Image and Video Retrieval Techniques(25)

Publications149 total

MEGA-GUI: Multi-stage Enhanced Grounding Agents for GUI Elements
arXiv (Cornell University)·2025Open Access
Part-Aware Bottom-Up Group Reasoning for Fine-Grained Social Interaction Detection
arXiv (Cornell University)·2025Open Access
GroupCoOp: Group-robust Fine-tuning via Group Prompt Learning
arXiv (Cornell University)·2025Open Access
Improving Sound Source Localization with Joint Slot Attention on Image and Audio
2025
Learning Audio-guided Video Representation with Gated Attention for Video-Text Retrieval
2025· 1 cited
GENIUS: A Generative Framework for Universal Multimodal Search
2025
GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation
arXiv (Cornell University)·2025Open Access
SYNAuG: Exploiting synthetic data for data imbalance problems
Pattern Recognition Letters·2025· 4 cited
TestDG: Test-time Domain Generalization for Continual Test-time Adaptation
arXiv (Cornell University)·2025Open Access
Learning Audio-guided Video Representation with Gated Attention for Video-Text Retrieval
arXiv (Cornell University)·2025Open Access
Learning Unified Distance Metric Across Diverse Data Distributions with Parameter-Efficient Transfer Learning
2025
Boosting Semi-Supervised Video Action Detection with Temporal Context
2025
Enhancing Cost Efficiency in Active Learning with Candidate Set Query
arXiv (Cornell University)·2025Open Access
Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens
arXiv (Cornell University)·2025· 1 citedOpen Access
Improving Text-based Person Search via Part-level Cross-modal Correspondence
arXiv (Cornell University)·2024Open Access
ActFusion: a Unified Diffusion Model for Action Segmentation and Anticipation
arXiv (Cornell University)·2024· 1 citedOpen Access
Online Temporal Action Localization with Memory-Augmented Transformer
Lecture notes in computer science·2024
Classification Matters: Improving Video Action Detection with Class-Specific Attention
Lecture notes in computer science·2024· 1 cited
Towards More Practical Group Activity Detection: A New Benchmark and Model
Lecture notes in computer science·2024· 3 cited
Efficient and Versatile Robust Fine-Tuning of Zero-Shot Models
Lecture notes in computer science·2024· 3 cited
page 1 of 8Next →

Frequent Co-authors

Bohyung Han(15), Minsu Cho(8), Seunghoon Hong(7), Minsu Cho(6), Sung‐Yeon Kim(5), Dong-Won Kim(5), Namyup Kim(5), Jiwoon Ahn(4), Sunghyun Cho(4), Cordelia Schmid(4), Jean Ponce(4), Ivan Laptev(4), Joon Hee Han(4), Tackgeun You(3), Heeseung Kwon(3), Manjin Kim(3), SoHyun Lee(3), Minkyo Seo(3), Taeyoung Son(3), Boseung Jeong(3)