PPaperPicks

Yanyun Qu

34 papers at tracked venues · 32 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. BeyondSparse: Facilitating Mamba to Enhance Cross-Domain 3D Semantic Segmentation in Adverse Weather
  2. Diffusion Once and Done: Degradation-Aware LoRA for All-in-One Image Restoration
  3. PC-CrossDiff: Point-Cluster Dual-Level Cross-Modal Differential Attention for Unified 3D Referring and Segmentation
  4. SpikingIR: A Novel Converted Spiking Neural Network for Efficient Image Restoration
  5. Target Refocusing via Attention Redistribution for Open-Vocabulary Semantic Segmentation: An Explainability Perspective
  6. xMHashSeg: Cross-modal Hash Learning for Training-free Unsupervised LiDAR Semantic Segmentation
  7. Large Continual Instruction Assistant
  8. MaskViM: Domain Generalized Semantic Segmentation with State Space Models
  9. Multi-Schema Proximity Network for Composed Image Retrieval
  10. Novel Category Discovery with X-Agent Attention for Open-Vocabulary Semantic Segmentation
  11. Omni-Query Active Learning for Source-Free Domain Adaptive Cross-Modality 3D Semantic Segmentation
  12. One-for-More: Continual Diffusion Model for Anomaly Detection
  13. PLATO-TTA: Prototype-Guided Pseudo-Labeling and Adaptive Tuning for Multi-Modal Test-Time Adaptation of 3D Segmentation
  14. SeqVLM: Proposal-Guided Multi-View Sequences Reasoning via VLM for Zero-Shot 3D Visual Grounding
  15. Task-Aware Prompt Gradient Projection for Parameter-Efficient Tuning Federated Class-Incremental Learning
  16. AdaFormer: Efficient Transformer with Adaptive Token Sparsification for Image Super-resolution
  17. Beyond the Label Itself: Latent Labels Enhance Semi-supervised Point Cloud Panoptic Segmentation
  18. Building a Strong Pre-Training Baseline for Universal 3D Large-Scale Perception
  19. CLIP-FSAC: Boosting CLIP for Few-Shot Anomaly Classification with Synthetic Anomalies
  20. CLIP-Guided Federated Learning on Heterogeneity and Long-Tailed Data
  21. CLIP2UDA: Making Frozen CLIP Reward Unsupervised Domain Adaptation in 3D Semantic Segmentation
  22. COTR: Compact Occupancy TRansformer for Vision-Based 3D Occupancy Prediction
  23. Cross-Modal Match for Language Conditioned 3D Object Grounding
  24. Efficient Lightweight Image Denoising with Triple Attention Transformer
  25. Learning Commonality, Divergence and Variety for Unsupervised Visible-Infrared Person Re-identification
  26. Learning Task-Aware Language-Image Representation for Class-Incremental Object Detection
  27. Multi-memory Matching for Unsupervised Visible-Infrared Person Re-identification
  28. Prompt Gradient Projection for Continual Learning
  29. PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection
  30. Relationship Prompt Learning is Enough for Open-Vocabulary Semantic Segmentation
  31. Robust Pseudo-label Learning with Neighbor Relation for Unsupervised Visible-Infrared Person Re-Identification
  32. SkipDiff: Adaptive Skip Diffusion Model for High-Fidelity Perceptual Image Super-resolution
  33. SkipVSR: Adaptive Patch Routing for Video Super-Resolution with Inter-Frame Mask
  34. UniDSeg: Unified Cross-Domain 3D Semantic Segmentation via Visual Foundation Models Prior