JH
Jae-Pil Heo
cs.CVcs.AIcs.LGbounding box proposalcontent-based image matchingeess.IVobject trackingplenoptic imaging technique
On Valency
published · living versionsW_wtndta8x·v1 · currentpublished
Unified Loss-Aware Density Control for 3D Gaussian Splatting
with Tae-Young Kim, Jiwoo Chung
1 version
Preprints & journals
51 papers in the corpus · 2015–2026Intrinsic Temporal Adaptation of CLIP for Partially Relevant Video Retrieval2609.04800v1 · Hyun Seok Seong, Woojin Jun, SuBeen Lee et al.2026 · 0 citationsarXiv
Per-View Gaussian Predictions Enable Training-Free Distractor Filtering in Feed-Forward 3DGS2608.26951v1 · Kangmin Seo, Jae-Pil Heo2026 · 0 citationsarXiv
Mitigating Modality and Language-Style Gaps for Zero-Shot Video Moment Retrieval2607.19027v1 · Jihyun Lee, Cheol-Ho Cho, Woojin Jun et al.2026 · 0 citationsarXiv
Improving Sparse-View 3DGS Generalization via Flat Minima Optimization2607.00885v1 · Kangmin Seo, Sangeek Hyun, MinKyu Lee et al.2026 · 0 citationsarXiv
Selective Synergistic Learning for Video Object-Centric Learning2606.15527v1 · WonJun Moon, Jae-Pil Heo2026 · 0 citationsarXiv
Cross-scale Aligned Supervision for Training GANs2605.26449v1 · Sangeek Hyun, MinKyu Lee, Jae-Pil Heo2026 · 0 citationsarXiv
Temporally Consistent Long-Term Memory for 3D Single Object Tracking2604.13789v1 · Jaejoon Yoo, SuBeen Lee, Yerim Jeon et al.2026 · 0 citationsarXiv
PDF-GS: Progressive Distractor Filtering for Robust 3D Gaussian Splatting2604.12580v2 · Kangmin Seo, MinKyu Lee, Tae-Young Kim et al.2026 · 0 citationsarXiv
Reconstruction-Guided Slot Curriculum: Addressing Object Over-Fragmentation in Video Object-Centric Learning2603.22758v1 · WonJun Moon, Hyun Seok Seong, Jae-Pil Heo2026 · 0 citationsarXiv
Looking Beyond the Window: Global-Local Aligned CLIP for Training-free Open-Vocabulary Semantic Segmentation2603.23030v1 · ByeongCheol Lee, Hyun Seok Seong, Sangeek Hyun et al.2026 · 0 citationsarXiv
SeaCache: Spectral-Evolution-Aware Cache for Accelerating Diffusion Models2602.18993v2 · Jiwoo Chung, Sangeek Hyun, MinKyu Lee et al.2026 · 0 citationsarXiv
From Vicious to Virtuous Cycles: Synergistic Representation Learning for Unsupervised Video Object-Centric Learning2602.03390v1 · Hyun Seok Seong, WonJun Moon, Jae-Pil Heo2026 · 0 citationsarXiv
Auxiliary Descriptive Knowledge for Few-Shot Adaptation of Vision-Language Model2512.17313v1 · SuBeen Lee, GilHan Park, WonJun Moon et al.2025 · 0 citationsarXiv
Masking Matters: Unlocking the Spatial Reasoning Capabilities of LLMs for 3D Scene-Language Understanding2512.02487v2 · Yerim Jeon, Miso Lee, WonJun Moon et al.2025 · 0 citationsarXiv
Mitigating Semantic Collapse in Partially Relevant Video Retrieval2510.27432v1 · WonJun Moon, MinSeok Jung, Gilhan Park et al.2025 · 0 citationsarXiv
Scalable GANs with Transformers2509.24935v3 · Sangeek Hyun, MinKyu Lee, Jae-Pil Heo2025 · 0 citationsarXiv
White Aggregation and Restoration for Few-shot 3D Point Cloud Semantic Segmentation2509.13907v3 · Jiyun Im, SuBeen Lee, Miso Lee et al.2025 · 0 citationsarXiv
Translation of Text Embedding via Delta Vector to Suppress Strongly Entangled Content in Text-to-Image Diffusion Models2508.10407v2 · Eunseo Koh, Seunghoo Hong, Tae-Young Kim et al.2025 · 0 citationsarXiv
Selective Contrastive Learning for Weakly Supervised Affordance Grounding2508.07877v1 · WonJun Moon, Hyun Seok Seong, Jae-Pil Heo2025 · 1 citationarXiv
Prototypes are Balanced Units for Efficient and Effective Partially Relevant Video Retrieval2504.13035v1 · WonJun Moon, Cheol-Ho Cho, Woojin Jun et al.2025 · 3 citationsarXiv
Analyzing the Training Dynamics of Image Restoration Transformers: A Revisit to Layer Normalization2504.06629v3 · MinKyu Lee, Sangeek Hyun, Woojin Jun et al.2025 · 0 citationsarXiv
Temporal Alignment-Free Video Matching for Few-shot Action Recognition2504.05956v1 · SuBeen Lee, WonJun Moon, Hyun Seok Seong et al.2025 · 10 citationsarXiv
Fine-Tuning Visual Autoregressive Models for Subject-Driven Generation2504.02612v2 · Jiwoo Chung, Sangeek Hyun, Hyunjun Kim et al.2025 · 2 citationsarXiv
Foreground-Covering Prototype Generation and Matching for SAM-Aided Few-Shot Segmentation2501.00752v1 · Suho Park, SuBeen Lee, Hyun Seok Seong et al.2025 · 15 citationsarXiv
Auto-Encoded Supervision for Perceptual Image Super-Resolution2412.00124v2 · MinKyu Lee, Sangeek Hyun, Woojin Jun et al.2024 · 6 citationsarXiv
Task-Oriented Channel Attention for Fine-Grained Few-Shot Classification.40030286 · Lee, SuBeen, Moon, WonJun, Seong, Hyun Seok et al.2025 · 14 citationsIEEE transactions on pattern analysis and machine intelligence. 2024;PP
Prediction-Feedback DETR for Temporal Action Detection2408.16729v3 · Jihwan Kim, Miso Lee, Cheol-Ho Cho et al.2024 · 7 citationsarXiv
Long-term Pre-training for Temporal Action Detection with Transformers2408.13152v2 · Jihwan Kim, Miso Lee, Jae-Pil Heo2024 · 5 citationsarXiv
Mutually-Aware Feature Learning for Few-Shot Object Counting2408.09734v2 · Yerim Jeon, Subeen Lee, Jihwan Kim et al.2024 · 11 citationsarXiv
Boundary-Recovering Network for Temporal Action Detection2408.09354v1 · Jihwan Kim, Jaehyun Choi, Yerim Jeon et al.2024 · 2 citationsarXiv
Progressive Proxy Anchor Propagation for Unsupervised Semantic Segmentation2407.12463v1 · Hyun Seok Seong, WonJun Moon, SuBeen Lee et al.2024 · 1 citationarXiv
Mitigating Background Shift in Class-Incremental Semantic Segmentation2407.11859v1 · Gilhan Park, WonJun Moon, SuBeen Lee et al.2024 · 13 citationsarXiv
GSGAN: Adversarial Learning for Hierarchical Generation of 3D Gaussian Splats2406.02968v2 · Sangeek Hyun, Jae-Pil Heo2024 · 4 citationsarXiv
Diversity-aware Channel Pruning for StyleGAN Compression2403.13548v1 · Jiwoo Chung, Sangeek Hyun, Sang-Heon Shim et al.2024 · 12 citationsarXiv
Noise-free Optimization in Early Training Steps for Image Super-Resolution2312.17526v1 · MinKyu Lee, Jae-Pil Heo2023 · 8 citationsarXiv
VLCounter: Text-aware Visual Representation for Zero-Shot Object Counting2312.16580v2 · Seunggu Kang, WonJun Moon, Euiyeon Kim et al.2023 · 44 citationsarXiv
Towards Squeezing-Averse Virtual Try-On via Sequential Deformation2312.15861v1 · Sang-Heon Shim, Jiwoo Chung, Jae-Pil Heo2023 · 24 citationsarXiv
Task-Disruptive Background Suppression for Few-Shot Segmentation2312.15894v1 · Suho Park, SuBeen Lee, Sangeek Hyun et al.2023 · 15 citationsarXiv
Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer2312.09008v2 · Jiwoo Chung, Sangeek Hyun, Jae-Pil Heo2023 · 232 citationsarXiv
Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding2311.08835v4 · WonJun Moon, Sangeek Hyun, SuBeen Lee et al.2023 · 8 citationsarXiv
Self-Feedback DETR for Temporal Action Detection2308.10570v1 · Jihwan Kim, Miso Lee, Jae-Pil Heo2023 · 32 citationsarXiv
Leveraging Hidden Positives for Unsupervised Semantic Segmentation2303.15014v1 · Hyun Seok Seong, WonJun Moon, SuBeen Lee et al.2023 · 50 citationsarXiv
Query-Dependent Video Representation for Moment Retrieval and Highlight Detection2303.13874v1 · WonJun Moon, Sangeek Hyun, SangUk Park et al.2023 · 169 citationsarXiv
Frequency-Based Motion Representation for Video Generative Adversarial Networks.37440396 · Hyun, Sangeek, Lew, Jaihyun, Chung, Jiwoo et al.2025 · 3 citationsIEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 2023;32:3949-3963
Minority-Oriented Vicinity Expansion with Attentive Aggregation for Video Long-Tailed Recognition2211.13471v1 · WonJun Moon, Hyun Seok Seong, Jae-Pil Heo2022 · 3 citationsarXiv
Tailoring Self-Supervision for Supervised Learning2207.10023v1 · WonJun Moon, Ji-Hwan Kim, Jae-Pil Heo2022 · 12 citationsarXiv
Difficulty-Aware Simulator for Open Set Recognition2207.10024v1 · WonJun Moon, Junho Park, Hyun Seok Seong et al.2022 · 62 citationsarXiv
Task Discrepancy Maximization for Fine-grained Few-Shot Classification2207.01376v1 · SuBeen Lee, WonJun Moon, Jae-Pil Heo2022 · 101 citationsIEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2022
Content-Aware Focal Plane Selection and Proposals for Object Tracking on Plenoptic Image Sequences.30583559 · Bae, Dae Hyun, Kim, Jae Woo, Heo, Jae-Pil2019 · 5 citationsSensors (Basel, Switzerland). 2018;19(1)
Distance Encoded Product Quantization for Approximate K-Nearest Neighbor Search in High-Dimensional Space.29994392 · Heo, Jae-Pil, Lin, Zhe, Yoon, Sung-Eui2019 · 30 citationsIEEE transactions on pattern analysis and machine intelligence. 2019;41(9):2084-2097
Career total: 104 works. 51 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.