Lune

Profiles2019-2026

Junsong Yuan

State University of New York at Buffalo

44Papers
24Last author
120Unique co-authors
0First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers44

  1. From Infusion to Assimilation Distillation for Medical Image SegmentationAuthor 4 of 4CVPR 2026
  2. Textured Geometry Evaluation: Perceptual 3D Textured Shape Metric via 3D Latent-Geometry NetworkAuthor 9 of 9AAAI 2026
  3. GeoRemover: Removing Objects and Their Causal Visual ArtifactsAuthor 6 of 6NeurIPS 2025 · 11 citations
  4. UST-SSM: Unified Spatio-Temporal State Space Models for Point Cloud Video ModelingAuthor 6 of 7ICCV 2025 · 3 citations
  5. PP-Motion: Physical-Perceptual Fidelity Evaluation for Human Motion GenerationAuthor 7 of 8ACM MM 2025 · 1 citation
  6. Recognizing Actions From Robotic View for Natural Human-Robot InteractionAuthor 7 of 8ICCV 2025 · 1 citation
  7. CompSlider: Compositional Slider for Disentangled Multiple-Attribute Image GenerationAuthor 6 of 6ICCV 2025
  8. Motion Consistency Model: Accelerating Video Diffusion with Disentangled Motion-Appearance DistillationAuthor 8 of 9NeurIPS 2024 · 41 citations
  9. FSC: Few-Point Shape CompletionAuthor 6 of 6CVPR 2024 · 10 citations
  10. NeuRBF: A Neural Fields Representation with Adaptive Radial Basis FunctionsAuthor 6 of 7ICCV 2023 · 80 citations
  11. Towards Generic Image Manipulation Detection with Weakly-Supervised Self-Consistency LearningAuthor 4 of 4ICCV 2023 · 35 citations
  12. Uncertainty-aware State Space Transformer for Egocentric 3D Hand Trajectory ForecastingAuthor 6 of 7ICCV 2023 · 34 citations
  13. Relit-NeuLF: Efficient Relighting and Novel View Synthesis via Neural 4D Light FieldAuthor 6 of 9ACM MM 2023 · 17 citations
  14. Progressive Multi-View Human Mesh Recovery with Self-SupervisionAuthor 6 of 8AAAI 2023 · 16 citations
  15. SOAR: Scene-debiasing Open-set Action RecognitionAuthor 7 of 8ICCV 2023 · 15 citations
  16. Language-guided Human Motion Synthesis with Atomic ActionsAuthor 8 of 8ACM MM 2023 · 12 citations
  17. Open Set Video HOI detection from Action-centric Chain-of-Look PromptingAuthor 3 of 3ICCV 2023 · 10 citations
  18. High Fidelity 3D Hand Shape Reconstruction via Scalable Graph Frequency DecompositionAuthor 7 of 7CVPR 2023
  19. MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in VideoAuthor 5 of 5CVPR 2022 · 356 citations
  20. Learning Transferable Human-Object Interaction Detector with Natural Language SupervisionAuthor 6 of 6CVPR 2022 · 66 citations
  21. OVIS: Open-Vocabulary Visual Instance Search via Visual-Semantic Aligned Representation LearningAuthor 4 of 5AAAI 2022 · 3 citations
  22. Rethinking Soft Labels for Knowledge Distillation: A Bias-Variance Tradeoff PerspectiveAuthor 6 of 7ICLR 2021 · 209 citations
  23. ACSNet: Action-Context Separation Network for Weakly Supervised Temporal Action LocalizationAuthor 5 of 7AAAI 2021 · 83 citations
  24. Stacked Homography Transformations for Multi-View Pedestrian DetectionAuthor 6 of 6ICCV 2021 · 66 citations
  25. Discovering Human Interactions with Large-Vocabulary Objects via Query and Multi-Scale DetectionAuthor 5 of 6ICCV 2021 · 35 citations
  26. Weakly Supervised Temporal Action Localization Through Learning Explicit Subspaces for Action and ContextAuthor 4 of 6AAAI 2021 · 28 citations
  27. Handling Difficult Labels for Multi-label Image Classification via Uncertainty DistillationAuthor 6 of 6ACM MM 2021 · 15 citations
  28. Robust Knowledge Transfer via Hybrid Forward on the Teacher-Student ModelAuthor 6 of 6AAAI 2021 · 13 citations
  29. Model-Based 3D Hand Reconstruction via Self-Supervised LearningAuthor 8 of 8CVPR 2021
  30. ConsNet: Learning Consistency Graph for Zero-Shot Human-Object Interaction DetectionAuthor 2 of 3ACM MM 2020 · 83 citations

Showing the 30 most recent indexed papers.

Dusk over the sea between two cliffs drawn in fine vertical lines