International Journal/Conference

2026

[C016] Frequency-Aware Object Detection for Drone Imagery

Jinseong Kim, Soonhyung Kwon, and Chanho Eom

IEIE International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC) (Oral), Jul. , 2026

[C015] Occlusion-Aware Real-Time Soccer Player Tracking and Team Classification in Broadcast Videos

Hayun Lee and Chanho Eom

IEIE International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC) (Oral), Jul. , 2026

[C014] FLAIR: Frequency- and Locality-Aware Implicit Neural Representations [arXiv] [Paper] [Project page]

Sukhun Ko, SeokHyun Youn, Dahyeon Kye, Kyle Min, Chanho Eom, and Jihyong Oh

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) - Findings, June 06, 2026 (CV Top-tier Conference, h5-index = 440)

[J010] Generalizable Large Language Model Based Human Keypoint Localization for Emotion Recognition [Paper]

Jianing Li, Xiaobin Liu, Chanho Eom, Shuang Yang, Jianzhong He, Hantao Yao, Jing Yuan

Pattern Recognition, vol. 174, pp. 112978-112988, Jun. 01, 2026 (ISSN: 0031-3203) (SCI Top 10%, Impact Factor = 7.6)

• Collaboration : Peking University, University of Science and Technology of China, Hong Kong Polytechnic University, Nankai University

[J009] AceVFI: A Comprehensive Survey of Advances in Video Frame Interpolation [arXiv] [Paper] [Project page]

Dahyeon Kye, Changhyun Roh, Sukhun Ko, Chanho Eom, and Jihyong Oh

IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), Mar. 09, 2026 (ISSN: 1051-8215) (SCI Top 5%, Impact Factor = 11.1)

[J008] MoCHA-former: Moir´e-Conditioned Hybrid Adaptive Transformer for Video Demoir´eing [arXiv] [Paper] [Project page] [Code] [Demo]

Jeahun Seong, Changhyun Roh, Chanho Eom, and Jihyong Oh

NeuroComputing, vol. 669, pp. 132477-132499, Mar. 07, 2026 (ISSN: 0925-2312) (SCI Top 20%, Impact Factor = 6.5)

[C013] COVA: Text-guided Composed Retrieval for Audio-Visual Content [arXiv] [Paper] [Project page]  [Code]

Gyuwon Han*, Young Kyun Jang*, and Chanho Eom (*equal contribution)

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 05, 2026 (Audio&Speech Top-tier Conference, h5-index = 291)

• Collaboration : Google DeepMind

[J007] FAST-GOAL⚽: Fast and Efficient Global-local Object Alignment Learning [arXiv] [Paper] [Code]

Hyungyu Choi*, Young Kyun Jang*, and Chanho Eom (*equal contribution)

IEEE Transactions on Image Processing (TIP), vol. 35, pp. 5181-5195, Apr. 29, 2026 (ISSN: 1057-7149) (SCI Top 2%, Impact Factor = 13.7)

• Collaboration : Google DeepMind

[J006] DiCo: Disentangled Concept Representation for Text-to-image Person Re-identification [arXiv] [Paper]

Giyeol Kim and Chanho Eom

NeuroComputing, vol. 675, pp. 132885-132895, Apr. 28, 2026 (ISSN: 0925-2312) (SCI Top 20%, Impact Factor = 6.5)

[C012] VIRAL: Visual Representation Alignment for Multimodal Large Language Models [arXiv] [Paper] [Project page] [Code]

Heeji Yoon, Jaewoo Jung, Junwan Kim, Hyungyu Choi, Heeseong Shin, Sangbeom Lim, Honggyu An, Chaehyun Kim, Jisang Han, Donghyun Kim, Chanho Eom, Sunghwan Hong, and Seungryong Kim

International Conference on Learning Representations (ICLR) Workshop, Apr. 26, 2026 (AI Top-tier Conference, h5-index = 362)

• Collaboration : ETH Zurich, New York University

[J005] Modality-Specific Expert Guiding for Visible-Infrared Person Re-Identification [Paper]

Xinyu Guo, Xiaobin Liu, Zishao Qiao, Nan Hu, Jianing Li, Chanho Eom, and Jing Yuan

Journal of Visual Communication and Image Representation (JVCI), vol. 117, pp.104783-104794, Apr. 01, 2026 (ISSN: 1047-3203) (SCI Top 40%, Impact Factor = 3.1)

• Collaboration : Hong Kong Polytechnic University, Nankai University

2025

[C011] DiffPS: Leveraging Prior Knowledge of Diffusion Model for Person Search [arXiv] [Paper] [Project page] [Code]

Giyeol Kim*, Sooyoung Yang*, Jihyong Oh, Myungjoo Kang, and Chanho Eom (*equal contribution)

IEEE/CVF International Conference on Computer Vision (ICCV), Oct. 23, 2025 (CV Top-tier Conference, h5-index = 291)

•  🏆 Highlight Paper (263/11152 = Top 2.35%)

[J004] Domain Generalization for Person Re-identification: A Survey Towards Domain-Agnostic Person Matching [arXiv] [Paper] [Project page]

Hyunseo Lee, Juhyun Park, Jihyong Oh, and Chanho Eom

NeuroComputing, vol. 649, pp. 130763-130782, Oct. 07, 2025 (ISSN: 0925-2312) (SCI Top 20%, Impact Factor = 6.5)

[C010] Visible-Infrared Person Re-Identification with Modality-Specific Expert [Paper]

Zishao Qiao, Xiaobin Liu, Xinyu Guo, Jianing Li, Chanho Eom, and Jing Yuan

International Conference on Image, Vision and Computing (ICIVC), Jul. 17, 2025

• Collaboration : Hong Kong Polytechnic University, Nankai University

[C009] Unifying Detection and Explanation for Domain-Aware Anomaly Detection

Juhyun Park, Jihyong Oh, and Chanho Eom

IEIE International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC)(Oral), Jul. 08, 2025

[C008] Frozen Yet Powerful: Frozen Pre-trained Models for Person Detection and Retrieval

Giyeol Kim, Jianing Li, Xiaobin Liu, Jihyong Oh, and Chanho Eom

IEIE International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC) (Oral), Jul. 08, 2025

• Collaboration : Hong Kong Polytechnic University, Nankai University

[C007] GOAL⚽: Global-local Object Alignment Learning [arXiv] [Paper]  [Project page] [Code]

Hyungyu Choi*, Young Kyun Jang*, and Chanho Eom (*equal contribution)

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 13, 2025 (CV Top-tier Conference, h5-index = 440)

• Collaboration : Google DeepMind

[C006] Subnet-Aware Dynamic Supernet Training for Neural Architecture Search [arXiv] [Paper]  [Project page] [Code]

Jeimin Jeon, Youngmin Oh, Junghyup Lee, Donghyeon Baek, Dohyung Kim, Chanho Eom, and Bumsub Ham

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 13, 2025 (CV Top-tier Conference, h5-index = 440)

[C005] Composed Video Retrieval Beyond Vision with Audio Reasoning

Gyuwon Han and Chanho Eom

International Conference on Electronics, Information, and Communication (ICEIC), Jan. 20, 2025

[C004] Learning Disentangled Concept Representations for Fine-Grained Text-to-Image Person Re-Identification

Giyeol Kim, Jianing Li, Xiaobin Liu, and Chanho Eom

International Conference on Electronics, Information, and Communication (ICEIC) (Oral), Jan. 20, 2025

• Collaboration : Hong Kong Polytechnic University, Nankai University

[J003] Cerberus🐕: Attribute-based Person Re-identification Using Semantic IDs [arXiv] [Paper]

Chanho Eom, Geon Lee, Kyunghwan Cho, Hyeonseok Jung, Moonsub Jin, and Bumsub Ham

Expert Systems with Applications (ESWA), vol. 259, no. 1, pp. 125320-125333, Jan. 01, 2025 (ISSN: 0957-4174) (SCI Top 7%, Impact Factor = 7.5)

• Collaboration : Hyundai Motors

~2024

[J002] Disentangled Representations for Short-Term and Long-Term Re-Identification [arXiv] [Paper]  [Project page]

Chanho Eom, Wonkyung Lee, Geon Lee, and Bumsub Ham

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 44, no. 12, pp. 8975-8991, Dec. 01, 2022 (ISSN: 0162-8828) (SCI Top 1%, Impact Factor = 24.314)

[C003] Bi-directional Contrastive Learning for Domain Adaptive Semantic Segmentation [arXiv] [Paper] [Project page] [Code]

Geon Lee, Chanho Eom, Wonkyung Lee, Hyekang Park, and Bumsub Ham

European Conference on Computer Vision (ECCV), Oct. 25, 2022 (CV Top-tier Conference, h5-index = 186)

[C002] Video-based Person Re-identification with Spatial and Temporal Memory Networks [arXiv] [Paper] [Project page] [Code] [Video]

Chanho Eom, Geon Lee, Junghyup Lee, and Bumsub Ham

IEEE/CVF International Conference on Computer Vision (ICCV), Oct. 13, 2021 (CV Top-tier Conference, h5-index = 184)

[J001] Temporally Consistent Depth Prediction with Flow-Guided Memory Units [arXiv] [Paper] [Project page] [Code] [Demo]

Chanho Eom, Hyunjong Park, and Bumsub Ham

IEEE Transactions on Intelligent Transportation Systems (TITS), vol. 21, no. 11, pp. 4626-4636, Nov. 01, 2020 (ISSN: 1524-9050) (SCI Top 3%, Impact Factor = 6.492)

[C001] Learning Disentangled Representation for Robust Person Re-identification [arXiv] [Paper] [Project page] [Code]

Chanho Eom and Bumsub Ham

Neural Information Processing Systems (NeurIPS), Dec. 12, 2019 (AI Top-tier Conference, h5-index = 198)

• 🏆 NeurIPS Travel Award

• [NAVER AI Tech Talk]