← Search

Hyung-Il Kim

7 accepted papers

2026

DeepProtect: Proactive Face-Swapping Defense using Identity Blending and Attribute Distortion

CVPR 2026

Face-swapping deepfakes allow realistic identity transfer, which can serve creative purposes but increases the risk of identity abuse. A proactive defense aims to prevent deepfake creation by obstructing identity feature extraction from input images, essential for identity-driven face-swapping. Exis

Cited by 0SourcecodeScholar
2026

Latent-RAG: Identity Retrieval-Guided Latent Augmentation for Privacy-Preserving Person Re-Identification

ICRA 2026poster

Person re-identification (re-ID) is crucial for security applications, including autonomous robots that monitor individuals via continuous image acquisition. Such data are transmitted to a database; however, if stored without adequate protection, they can be intercepted, posing privacy risks. In res…

Cited by 0codeScholar
2026

Task Prototype-Based Knowledge Retrieval for Multi-Task Learning from Partially Annotated Data

AAAI 2026technical

Multi-task learning (MTL) is critical in real-world applications such as autonomous driving and robotics, enabling simultaneous handling of diverse tasks. However, obtaining fully annotated data for all tasks is impractical due to labeling costs. Existing methods for partially labeled MTL typically

Cited by 0SourcePDFScholar
2024

Improving Open Set Recognition via Visual Prompts Distilled from Common-Sense Knowledge

AAAI 2024technical

Open Set Recognition (OSR) poses significant challenges in distinguishing known from unknown classes. In OSR, the overconfidence problem has become a persistent obstacle, where visual recognition models often misclassify unknown objects as known objects with high confidence. This issue stems from th…

Cited by 9SourcePDFScholar
2024

MonoWAD: Weather-Adaptive Diffusion Model for Robust Monocular 3D Object Detection

ECCV 2024poster

"Monocular 3D object detection is an important challenging task in autonomous driving. Existing methods mainly focus on performing 3D detection in ideal weather conditions, characterized by scenarios with clear and optimal visibility. However, the challenge of autonomous driving requires the ability…

2022

Weakly Paired Associative Learning for Sound and Image Representations via Bimodal Associative Memory

CVPR 2022poster

Data representation learning without labels has attracted increasing attention due to its nature that does not require human annotation. Recently, representation learning has been extended to bimodal data, especially sound and image which are closely related to basic human senses. Existing sound and…

Cited by 7PDFScholar
2021

Video Prediction Recalling Long-Term Motion Context via Memory Alignment Learning

CVPR 2021poster

Our work addresses long-term motion context issues for predicting future frames. To predict the future precisely, it is required to capture which long-term motion context (e.g., walking or running) the input motion (e.g., leg movement) belongs to. The bottlenecks arising when dealing with the long-t…

Cited by 146PDFcodeScholar