Publication

Backpropagation-Free Test-Time Adaptation via Probabilistic Gaussian Alignment

Youjia Zhang, Youngeun Kim, Young-Geun Choi, Hongyeob Kim, Huiling Liu, and Sungeun Hong,  Conference on Neural Information Processing Systems (NeurIPS 2025), December 2025

Test-Time Adaptation   Domain Shift   Backpropagation-Free   Gaussian Discriminant Analysis 

PRIMT: Preference-based Reinforcement Learning with Multimodal Feedback and Trajectory Synthesis from Foundation Models

Ruiqi Wang, Dezhong Zhao, Ziqin Yuan, Tianyu Shao, Guohua Chen, Dominic Kao, Sungeun Hong, and Byung-Cheol Min, Conference on Neural Information Processing Systems (NeurIPS 2025) Oral🎤, December 2025 

Multimodal Learning   Robot Manipulation    Preference-based Reinforcement Learning   Causal Inference

RA-Touch: Retrieval-Augmented Touch Understanding with Enriched Visual Data

Yoorhim Cho*, Hongyeob Kim*, Semin Kim, Youjia Zhang, YunSeok Choi, and Sungeun Hong, ACM Multimedia (MM 2025), October 2025 

Multimodal Learning   Tactile Perception   Retrieval-Augmented Methods

Task Vector Quantization for Memory-Efficient Model Merging

Youngeun Kim*, Seunghwan Lee*, Aecheon Jung*, Bogon Ryu, and Sungeun Hong, IEEE/CVF International Conference on Computer Vision (ICCV 2025), October 2025

Model Merging   Multi-task Learning   Task Vector Quantization

DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding

Jungbin Cho*, Junwan Kim*, Jisoo Kim, Minseo Kim, Mingu Kang, Sungeun Hong, Tae-Hyun Oh, and Youngjae Yu, IEEE/CVF International Conference on Computer Vision (ICCV 2025) Highlight🌟, October 2025 

3D Human   Human Motion Generation   Flow Matching

Question-Aware Gaussian Experts for Audio-Visual Question Answering

Hongyeob Kim*, Inyoung Jung*, Dayoon Suh, Youjia Zhang, Sangmin Lee and Sungeun Hong, Proc. IEEE/CVF Conference on Computer Vision and Patter Recognition (CVPR 2025) Highlight🌟, June 2025.  

Multimodal Learning   Audio-Vision-Language  Question Answering

IAM: Enhancing RGB-D Instance Segmentation with New Benchmarks

Aecheon Jung, Soyun Choi, Junhong Min, and Sungeun Hong, Arxiv, January 2025.

RGB-D Instance Segmentation   Dataset Construction   Attention

FVTTS: Face based voice synthesis for text-to-speech

Minyoung Lee, Eunil Park and Sungeun Hong, Proc. Annual Conference of the International Speech Communication Association (INTERSPEECH 2024), September 2024.

Text-to-Speech (TTS)   Face   Synthesis

Intra-inter modal attention blocks for RGB-D semantic segmentation

Soyun Choi, Youjia Zhang and Sungeun Hong, Proc. ACM International Conference on Multimedia Retrieval (ICMR 2023), June 2023. 

Multimodal Learning   Sensor Fusion   RGB-D   Semantic Segmentation

IFQA: Interpretable face quality assessment

Byungho Jo, Donghyeon Cho, In Kyu Park, and Sungeun Hong, Proc. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2023), pp.3444-3453, January 2023

Face   Image Quality Assessment   Image Restoration

Spatio-channel attention blocks for cross-modal crowd counting

Youjia Zhang, Soyun Choi, and Sungeun Hong, Proc. Asian Conference on Computer Vision (ACCV 2022) Oral🎤, December 2022.

Multimodal Learning    Sensor Fusion   RGB-D/T Crowd Counting

Re-Aging GAN: Toward personalized face age transformation

Farkhod Makhmudkhujaev, Sungeun Hong, and In Kyu Park, Proc. IEEE/CVF International Conference on Computer Vision (ICCV 2021), October 2021.

Face    Age Estimation   Generative Models

VisDrone-DET2019: The vision meets drone object detection in image challenge results

Sungeun Hong and VisDrone Challenge Participants, VisDrone Workshops at International Conference on Computer Vision (ICCVW 2019), Ranked at 3rd, October 2019.

Object Detection   Drone     Small Object

Patch-level augmentation for object detection in aerial images

Sungeun Hong, Sungil Kang, Donghyeon Cho, VisDrone Workshops at International Conference on Computer Vision (ICCVW 2019), Ranked 3rd, October 2019

Object Detection   Drone   Text-driven Augmentation

Key instance selection for unsupervised video object segmentation

Sungeun Hong, Donghyeon Cho, Sungil Kang, and Jiwon Kim, DAVIS Challenge Workshops at Computer Vision and Pattern Recognition (CVPRW 2019), Ranked 3rd, June 2019

Video Object Segmentation   Instance Selection

Scale-varying triplet ranking with classification loss for facial age estimation

Woobin Im, Sungeun Hong , Sung-Eui Yoon, and Hyun S. Yang, Proc. Asian Conference on Computer Vision (ACCV 2018), December 2018.

Face   Age Estimation   Ranking Loss

Cascaded pyramid network for 3D human pose estimation challenge

Sungeun Hong , Wonjin Jung, Ilsang Woo, and Seung Wook Kim, PoseTrack Workshops at European Conference on Computer Vision (ECCVW 2018), September 2018.

Human Pose Estimation   Pyramid Network   3D Pose

Bilinear attention networks for VizWiz challenge

Jin-Hwa Kim, Yongseok Choi, Sungeun Hong, Jaehyun Jun, and Byoung-Tak Zhang, Vizwiz Workshops at European Conference on Computer Vision (ECCVW 2018), Ranked 2nd, September 2018.

Visual Question Answering   Attention   Visually Impaired

CBVMR: Content-based video–music retrieval using soft intra-modal structure constraint

Sungeun Hong , Woobin Im, and Hyun S. Yang, Proc. ACM International Conference on Multimedia Retrieval (ICMR 2018) (spotlight), June 2018.

Multimodal Learning   Cross-modal Retrieval   Video Object Segmentation   Music

SSPP-DAN: Deep domain adaptation network for face recognition with single sample per person

Sungeun Hong, Woobin Im, Jongbin Ryu, and Hyun S. Yang, IEEE International Conference on Image Processing (ICIP 2017) (Oral), September 2017.

Domain Adaptation   Face Recognition