Lune

Profiles2019-2026ORCID 0000-0002-9444-3763

Jianfei Cai

Monash University

35Papers
18Last author
77Unique co-authors
0First author
0Solo

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

Recent papers35

  1. PCGS: Progressive Compression of 3D Gaussian SplattingAuthor 6 of 6AAAI 2026 · 15 citations
  2. Marginalized Generalized IoU (MGIoU): A Unified Objective Function for Optimizing Convex Parametric ShapesAuthor 3 of 4AAAI 2026 · 2 citations
  3. PanFlow: Decoupled Motion Control for Panoramic Video GenerationAuthor 7 of 7AAAI 2026 · 1 citation
  4. Fast Feedforward 3D Gaussian Splatting CompressionAuthor 6 of 6ICLR 2025 · 1 citation
  5. Relightable and Dynamic Gaussian Avatar Reconstruction from Monocular VideoAuthor 5 of 7ACM MM 2025 · 1 citation
  6. DrVideo: Document Retrieval Based Long Video UnderstandingAuthor 7 of 7CVPR 2025
  7. PaRa: Personalizing Text-to-Image Diffusion via Parameter Rank ReductionAuthor 3 of 4ICLR 2025
  8. Point-Cache: Test-time Dynamic and Hierarchical Cache for Robust and Generalizable Point Cloud AnalysisAuthor 7 of 7CVPR 2025
  9. Normal-GS: 3D Gaussian Splatting with Normal-Involved RenderingAuthor 5 of 5NeurIPS 2024 · 17 citations
  10. Point-PRC: A Prompt Learning Based Regulation Framework for Generalizable Point Cloud AnalysisAuthor 7 of 7NeurIPS 2024 · 9 citations
  11. How Far can we Compress Instant-NGP-Based NeRF?Author 4 of 4CVPR 2024
  12. JRDB-PanoTrack: An Open-World Panoptic Segmentation and Tracking Robotic Dataset in Crowded Human EnvironmentsAuthor 6 of 7CVPR 2024
  13. ObjectSDF++: Improved Object-Compositional Neural Implicit SurfacesAuthor 5 of 5ICCV 2023 · 44 citations
  14. Open-Vocabulary Object Detection via Scene Graph DiscoveryAuthor 3 of 3ACM MM 2023 · 20 citations
  15. JRDB-Pose: A Large-Scale Dataset for Multi-Person Pose Estimation and TrackingAuthor 4 of 5CVPR 2023
  16. MARLIN: Masked Autoencoder for facial video Representation LearnINgAuthor 5 of 8CVPR 2023
  17. Transformer Scale Gate for Semantic SegmentationAuthor 3 of 3CVPR 2023
  18. GMFlow: Learning Optical Flow via Global MatchingAuthor 3 of 5CVPR 2022 · 353 citations
  19. MoVQ: Modulating Quantized Vectors for High-Fidelity Image GenerationAuthor 3 of 4NeurIPS 2022 · 156 citations
  20. Bridging Global Context Interactions for High-Fidelity Image CompletionAuthor 3 of 4CVPR 2022 · 114 citations
  21. ProposalCLIP: Unsupervised Open-Category Object Proposal Generation via Exploiting CLIP CuesAuthor 4 of 4CVPR 2022 · 59 citations
  22. Towards Unbiased Visual Emotion Recognition via Causal InterventionAuthor 3 of 3ACM MM 2022 · 27 citations
  23. Learning Meta-class Memory for Few-Shot Semantic SegmentationAuthor 4 of 4ICCV 2021 · 128 citations
  24. High-Resolution Optical Flow from 1D Attention and CorrelationAuthor 3 of 5ICCV 2021 · 92 citations
  25. A Unified 3D Human Motion Synthesis Model via Conditional Variational Auto-Encoder∗Author 5 of 13ICCV 2021 · 83 citations
  26. CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape ParsingAuthor 3 of 11ICCV 2021 · 71 citations
  27. Auto-Parsing Network for Image Captioning and Visual Question AnsweringAuthor 4 of 4ICCV 2021 · 45 citations
  28. Causal Attention for Vision-Language TasksAuthor 4 of 4CVPR 2021
  29. RSG: A Simple but Effective Module for Learning Imbalanced DatasetsAuthor 4 of 5CVPR 2021
  30. The Spatially-Correlative Loss for Various Image Translation TasksAuthor 3 of 3CVPR 2021

Showing the 30 most recent indexed papers.

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