Junho Kim

23

Papers

15

Total Citations

Papers (23)

Fully Geometric Panoramic Localization

SALOVA: Segment-Augmented Long Video Assistant for Targeted Retrieval and Routing in Long-Form Video Analysis

StyleKeeper: Prevent Content Leakage using Negative Visual Query Guidance

CapeLLM: Support-Free Category-Agnostic Pose Estimation with Multimodal Large Language Models

Learning 3D Scene Analogies with Neural Contextual Scene Maps

Masking Adversarial Damage: Finding Adversarial Saliency for Robust and Sparse Network

Diffusion Video Autoencoders: Toward Temporally Consistent Face Video Editing via Disentangled Video Encoding

PICCOLO: Point Cloud-Centric Omnidirectional Localization

N-ImageNet: Towards Robust, Fine-Grained Object Recognition With Event Cameras

CTRL-C: Camera Calibration TRansformer With Line-Classification

LDL: Line Distance Functions for Panoramic Localization

Calibrating Panoramic Depth Estimation for Practical Localization and Mapping

Mitigating Adversarial Vulnerability through Causal Parameter Estimation by Adversarial Double Machine Learning

Neural Geometric Parser for Single Image Camera Calibration

CPO: Change Robust Panorama to Point Cloud Localization

Generator Knows What Discriminator Should Learn in Unconditional GANs

MoDA: Map Style Transfer for Self-Supervised Domain Adaptation of Embodied Agents

Demystifying Causal Features on Adversarial Examples and Causal Inoculation for Robust Network by Adversarial Instrumental Variable Regression

Enhancing Creative Generation on Stable Diffusion-based Models

Exploiting Spatial Dimensions of Latent in GAN for Real-Time Image Editing

Ev-TTA: Test-Time Adaptation for Event-Based Object Recognition

Feature Statistics Mixing Regularization for Generative Adversarial Networks

Distilling Robust and Non-Robust Features in Adversarial Examples by Information Bottleneck