📝 Publications

20 entries in total. You can also find them on Google Scholar, or download the full CV (PDF). ← Back to selected publications

International Conference Papers 8

Bounding-Box Trajectories Matter for Video Anomaly Detection

Inpyo Song, Jangwon Lee

ECCV'26 | [arXiv] |

@inproceedings{song2026bbox,
  title     = {Bounding-Box Trajectories Matter for Video Anomaly Detection},
  author    = {Song, Inpyo and Lee, Jangwon},
  booktitle = {European Conference on Computer Vision (ECCV)},
  year      = {2026}
}

Real-Time Traffic Accident Anticipation with Feature Reuse

Inpyo Song, Jangwon Lee

@inproceedings{song2025rare,
  title     = {Real-Time Traffic Accident Anticipation with Feature Reuse},
  author    = {Song, Inpyo and Lee, Jangwon},
  booktitle = {IEEE International Conference on Image Processing (ICIP)},
  year      = {2025}
}

PawPrint: Whose Footprints Are These? Identifying Animal Individuals by Their Footprints

Inpyo Song, Hyemin Hwang, Jangwon Lee

@inproceedings{song2025pawprint,
  title     = {PawPrint: Whose Footprints Are These? Identifying Animal Individuals by Their Footprints},
  author    = {Song, Inpyo and Hwang, Hyemin and Lee, Jangwon},
  booktitle = {IEEE International Conference on Image Processing (ICIP)},
  year      = {2025}
}

Anomaly Detection for People with Visual Impairments Using an Egocentric 360-Degree Camera

Inpyo Song, Sanghyeon Lee, Minjun Joo, Jangwon Lee

@inproceedings{song2025view360,
  title     = {Anomaly Detection for People with Visual Impairments Using an Egocentric 360-Degree Camera},
  author    = {Song, Inpyo and Lee, Sanghyeon and Joo, Minjun and Lee, Jangwon},
  booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
  year      = {2025}
}

SFTrack: A Robust Scale and Motion Adaptive Algorithm for Tracking Small and Fast Moving Objects

Inpyo Song, Jangwon Lee

@inproceedings{song2024sftrack,
  title     = {SFTrack: A Robust Scale and Motion Adaptive Algorithm for Tracking Small and Fast Moving Objects},
  author    = {Song, Inpyo and Lee, Jangwon},
  booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  year      = {2024}
}

Motion-Aware Heatmap Regression for Human Pose Estimation in Videos

Inpyo Song, Jongmin Lee, Moonwook Ryu, Jangwon Lee

IJCAI'24 (14.0% acceptance rate) | [Paper] |

@inproceedings{song2024motionaware,
  title     = {Motion-Aware Heatmap Regression for Human Pose Estimation in Videos},
  author    = {Song, Inpyo and Lee, Jongmin and Ryu, Moonwook and Lee, Jangwon},
  booktitle = {International Joint Conference on Artificial Intelligence (IJCAI)},
  year      = {2024}
}

Video Question Answering for People with Visual Impairments Using an Egocentric 360-Degree Camera

Inpyo Song, Minjun Joo, Joonhyung Kwon, Jangwon Lee

CVPRW'24 (First Joint Egocentric Vision (EgoVis) Workshop) | [arXiv] |

@inproceedings{song2024vqa360,
  title     = {Video Question Answering for People with Visual Impairments Using an Egocentric 360-Degree Camera},
  author    = {Song, Inpyo and Joo, Minjun and Kwon, Joonhyung and Lee, Jangwon},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  year      = {2024}
}

Scale and Motion Adaptive Multi-Object Tracking Algorithm for Unmanned Aerial Vehicles

Inpyo Song, Jangwon Lee

RO-MAN'23 (Late-Breaking Report) |

@inproceedings{song2023uav,
  title     = {Scale and Motion Adaptive Multi-Object Tracking Algorithm for Unmanned Aerial Vehicles},
  author    = {Song, Inpyo and Lee, Jangwon},
  booktitle = {IEEE International Conference on Robot \& Human Interactive Communication (RO-MAN), Late-Breaking Reports},
  year      = {2023}
}

International Journal Papers 1

Action-Conditioned Contrastive Learning for 3D Human Pose and Shape Estimation in Videos

Inpyo Song, Moonwook Ryu, Jangwon Lee

CVIU'24 (IF 4.3, Q1) | [Paper] | [Code] |

@article{song2024acmr,
  title   = {Action-Conditioned Contrastive Learning for 3D Human Pose and Shape Estimation in Videos},
  author  = {Song, Inpyo and Ryu, Moonwook and Lee, Jangwon},
  journal = {Computer Vision and Image Understanding (CVIU)},
  year    = {2024}
}

Domestic Conference Papers 4

Probing H.264 Compressed-Domain Signals for Video Anomaly Detection

Inpyo Song, Eunji Jeon, Jangwon Lee

KIBME Summer Conference 2026
A Study on Synthetic Data Generation and Evaluation for Pose Estimation in Surveillance Videos

Moonwook Ryu, Jongwoo Choi, Inpyo Song, Jangwon Lee

KIBME Summer Conference 2026 Outstanding Poster Award
Smooth and Consistent Pose Estimation with Intersections Module

Jongmin Lee*, Inpyo Song*, Moonwook Ryu, Jangwon Lee

KIBME Summer Conference 2024 (* Equal contribution)
Multi-Task Learning in Facial Kinship Verification

Inpyo Song, Jangwon Lee

KIBME Summer Conference 2023

Domestic Journal Papers 2

Teacher Response Entropy Based Adaptive Knowledge Distillation

Inpyo Song, Jangwon Lee

KIIS 2024
Rule-Based Zero-Shot Video Anomaly Detection Using Object Detection and Semantic Segmentation

Inpyo Song, Jangwon Lee

JBE 2024 (Vol. 29, No. 6)

Preprints & Manuscripts Under Review 5

Rethinking Open-World Video Anomaly Detection: Diagnosing Definition Blindness

Inpyo Song, Jangwon Lee

Under review | [arXiv]
Instance-Aligned Captions for Explainable Video Anomaly Detection

Inpyo Song, Joonhyung Kwon, Eunji Jeon, Minjun Ju, Jangwon Lee

Under review | [arXiv]
PCEval: A Benchmark for Evaluating Physical Computing Capabilities of Large Language Models

Inpyo Song, Eunji Jeon, Jangwon Lee

Under review | [arXiv]
A VLM Answer is Not an Anomaly Score: Rank Compression in Training-Free Video Anomaly Detection

Inpyo Song, Jangwon Lee

Under review
Frame-Level Evaluation in Weakly Supervised Video Anomaly Detection Mostly Measures Video-Level Ranking

Inpyo Song, Jangwon Lee

Under review

Inpyo Song

📝 Publications

International Conference Papers 8

Bounding-Box Trajectories Matter for Video Anomaly Detection

Real-Time Traffic Accident Anticipation with Feature Reuse

PawPrint: Whose Footprints Are These? Identifying Animal Individuals by Their Footprints

Anomaly Detection for People with Visual Impairments Using an Egocentric 360-Degree Camera

SFTrack: A Robust Scale and Motion Adaptive Algorithm for Tracking Small and Fast Moving Objects

Motion-Aware Heatmap Regression for Human Pose Estimation in Videos

Video Question Answering for People with Visual Impairments Using an Egocentric 360-Degree Camera

Scale and Motion Adaptive Multi-Object Tracking Algorithm for Unmanned Aerial Vehicles

International Journal Papers 1

Action-Conditioned Contrastive Learning for 3D Human Pose and Shape Estimation in Videos

Domestic Conference Papers 4

Probing H.264 Compressed-Domain Signals for Video Anomaly Detection

A Study on Synthetic Data Generation and Evaluation for Pose Estimation in Surveillance Videos

Smooth and Consistent Pose Estimation with Intersections Module

Multi-Task Learning in Facial Kinship Verification

Domestic Journal Papers 2

Teacher Response Entropy Based Adaptive Knowledge Distillation

Rule-Based Zero-Shot Video Anomaly Detection Using Object Detection and Semantic Segmentation

Preprints & Manuscripts Under Review 5

Rethinking Open-World Video Anomaly Detection: Diagnosing Definition Blindness

Instance-Aligned Captions for Explainable Video Anomaly Detection

PCEval: A Benchmark for Evaluating Physical Computing Capabilities of Large Language Models

A VLM Answer is Not an Anomaly Score: Rank Compression in Training-Free Video Anomaly Detection

Frame-Level Evaluation in Weakly Supervised Video Anomaly Detection Mostly Measures Video-Level Ranking