Jae-Pil Heo

papers

786

total citations

papers (29)

Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer

CVPR 2024arXiv

225

citations

Query-Dependent Video Representation for Moment Retrieval and Highlight Detection

CVPR 2023arXiv

191

citations

Ambiguity-Restrained Text-Video Representation Learning for Partially Relevant Video Retrieval

AAAI 2025arXiv

citations

Foreground-Covering Prototype Generation and Matching for SAM-Aided Few-Shot Segmentation

AAAI 2025arXiv

citations

Prototypes are Balanced Units for Efficient and Effective Partially Relevant Video Retrieval

ICCV 2025arXiv

citations

Selective Contrastive Learning for Weakly Supervised Affordance Grounding

ICCV 2025arXiv

citations

Auto-Encoded Supervision for Perceptual Image Super-Resolution

CVPR 2025arXiv

citations

Disentangled Representation Learning for Unsupervised Neural Quantization

CVPR 2023

citations

Collaborative Learning With Disentangled Features for Zero-Shot Domain Adaptation

ICCV 2021

citations

Translation of Text Embedding via Delta Vector to Suppress Strongly Entangled Content in Text-to-Image Diffusion Models

ICCV 2025arXiv

citations

Bridging the Semantic Granularity Gap Between Text and Frame Representations for Partially Relevant Video Retrieval

AAAI 2025

citations

VarSR: Variational Super-Resolution Network for Very Low Resolution Images

ECCV 2020

citations

Self-Supervised Video GANs: Learning for Appearance Consistency and Motion Coherency

CVPR 2021

citations

Product Quantizer Aware Inverted Index for Scalable Nearest Neighbor Search

ICCV 2021

citations

Local Attention Pyramid for Scene Image Generation

CVPR 2022

citations

Jae-Pil Heo

papers (29)

Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer

Query-Dependent Video Representation for Moment Retrieval and Highlight Detection

Task Discrepancy Maximization for Fine-Grained Few-Shot Classification

VLCounter: Text-Aware Visual Representation for Zero-Shot Object Counting

Leveraging Hidden Positives for Unsupervised Semantic Segmentation

Difficulty-Aware Simulator for Open Set Recognition

Self-Feedback DETR for Temporal Action Detection

Towards Squeezing-Averse Virtual Try-On via Sequential Deformation

Tailoring Self-Supervision for Supervised Learning

Task-Disruptive Background Suppression for Few-Shot Segmentation

Mitigating Background Shift in Class-Incremental Semantic Segmentation

Fine-Tuning Visual Autogressive Models for Subject-Driven Generation

Noise-Free Optimization in Early Training Steps for Image Super-resolution

Diversity-aware Channel Pruning for StyleGAN Compression

Temporal Alignment-Free Video Matching for Few-shot Action Recognition

Prediction-Feedback DETR for Temporal Action Detection

Ambiguity-Restrained Text-Video Representation Learning for Partially Relevant Video Retrieval

Foreground-Covering Prototype Generation and Matching for SAM-Aided Few-Shot Segmentation

Prototypes are Balanced Units for Efficient and Effective Partially Relevant Video Retrieval

Selective Contrastive Learning for Weakly Supervised Affordance Grounding

Auto-Encoded Supervision for Perceptual Image Super-Resolution

Disentangled Representation Learning for Unsupervised Neural Quantization

Collaborative Learning With Disentangled Features for Zero-Shot Domain Adaptation

Translation of Text Embedding via Delta Vector to Suppress Strongly Entangled Content in Text-to-Image Diffusion Models

Bridging the Semantic Granularity Gap Between Text and Frame Representations for Partially Relevant Video Retrieval

VarSR: Variational Super-Resolution Network for Very Low Resolution Images

Self-Supervised Video GANs: Learning for Appearance Consistency and Motion Coherency

Product Quantizer Aware Inverted Index for Scalable Nearest Neighbor Search

Local Attention Pyramid for Scene Image Generation

papers (29)

Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer

Query-Dependent Video Representation for Moment Retrieval and Highlight Detection

Task Discrepancy Maximization for Fine-Grained Few-Shot Classification

VLCounter: Text-Aware Visual Representation for Zero-Shot Object Counting

Leveraging Hidden Positives for Unsupervised Semantic Segmentation

Difficulty-Aware Simulator for Open Set Recognition

Self-Feedback DETR for Temporal Action Detection

Towards Squeezing-Averse Virtual Try-On via Sequential Deformation

Tailoring Self-Supervision for Supervised Learning

Task-Disruptive Background Suppression for Few-Shot Segmentation

Mitigating Background Shift in Class-Incremental Semantic Segmentation

Fine-Tuning Visual Autogressive Models for Subject-Driven Generation

Noise-Free Optimization in Early Training Steps for Image Super-resolution

Diversity-aware Channel Pruning for StyleGAN Compression

Temporal Alignment-Free Video Matching for Few-shot Action Recognition

Prediction-Feedback DETR for Temporal Action Detection

Ambiguity-Restrained Text-Video Representation Learning for Partially Relevant Video Retrieval

Foreground-Covering Prototype Generation and Matching for SAM-Aided Few-Shot Segmentation

Prototypes are Balanced Units for Efficient and Effective Partially Relevant Video Retrieval

Selective Contrastive Learning for Weakly Supervised Affordance Grounding

Auto-Encoded Supervision for Perceptual Image Super-Resolution

Disentangled Representation Learning for Unsupervised Neural Quantization

Collaborative Learning With Disentangled Features for Zero-Shot Domain Adaptation

Translation of Text Embedding via Delta Vector to Suppress Strongly Entangled Content in Text-to-Image Diffusion Models

Bridging the Semantic Granularity Gap Between Text and Frame Representations for Partially Relevant Video Retrieval

VarSR: Variational Super-Resolution Network for Very Low Resolution Images

Self-Supervised Video GANs: Learning for Appearance Consistency and Motion Coherency

Product Quantizer Aware Inverted Index for Scalable Nearest Neighbor Search

Local Attention Pyramid for Scene Image Generation