WM
WonJun Moon
cs.CVcs.AIcs.LGcs.CL
On Valency
published · living versionsW_h2mepfcs·v1 · currentpublished
Repurposing Video Diffusion Transformers for Cross-View Temporal Object Correspondence
with Siyoon Jin, Dahyun Chung, Honggyu An, Sangbeom Lim +3
1 version
Preprints & journals
23 papers in the corpus · 2022–2026PLAYGROUND: Progressive Layout Generation with Render-Grounded Planning2610.18865v1 · Jaeho Lee, Junhwan Heo, Junghyun Park et al.2026 · 0 citationsarXiv
Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering2609.38177v1 · Jaewoo Jung, Hyeonseo Yu, Honggyu An et al.2026 · 0 citationsarXiv
Selective Synergistic Learning for Video Object-Centric Learning2606.15527v1 · WonJun Moon, Jae-Pil Heo2026 · 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
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
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
Temporal Alignment-Free Video Matching for Few-shot Action Recognition2504.05956v1 · SuBeen Lee, WonJun Moon, Hyun Seok Seong et al.2025 · 10 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
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
VLCounter: Text-aware Visual Representation for Zero-Shot Object Counting2312.16580v2 · Seunggu Kang, WonJun Moon, Euiyeon Kim et al.2023 · 44 citationsarXiv
Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding2311.08835v4 · WonJun Moon, Sangeek Hyun, SuBeen Lee et al.2023 · 8 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
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
Career total: 30 works. 23 are in this corpus.
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.