PPaperPicks

Huadong Ma

34 papers at tracked venues · 30 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. HDRMovieformer: A Transformer Framework and Benchmark for Cinematic SDR-to-HDR Conversion
  2. Improving Batch Normalization with Test-Time Adaptation for Robust Object Detection in Self-Driving
  3. Regression over Classification: Assessing Image Aesthetics via Multimodal Large Language Models
  4. Selective Diffusion Distillation for Real-World High-Scale Image Super-Resolution
  5. A Dynamic Service Offloading Algorithm Based on Lyapunov Optimization in Edge Computing
  6. EvRAW: Event-guided Structural and Color Modeling for RAW-to-sRGB Image Reconstruction
  7. From Abyssal Darkness to Blinding Glare: a Benchmark on Extreme Exposure Correction in Real World
  8. Global-Local Tree Search in VLMs for 3D Indoor Scene Generation
  9. NTIRE 2025 Challenge on Image Super-Resolution (x4): Methods and Results
  10. Rethinking Personalized Aesthetics Assessment: Employing Physique Aesthetics Assessment as An Exemplification
  11. SafeDriveRAG: Towards Safe Autonomous Driving with Knowledge Graph-based Retrieval-Augmented Generation
  12. Severe Light, Textureless Sight: A Benchmark for Extreme Exposure Correction
  13. Synergistic Tensor and Pipeline Parallelism
  14. T2SG: Traffic Topology Scene Graph for Topology Reasoning in Autonomous Driving
  15. Towards Efficient Object Re-Identification with a Novel Cloud-Edge Collaborative Framework
  16. VIoTGPT: Learning to Schedule Vision Tools Towards Intelligent Video Internet of Things
  17. Venus: Generating Large-scale mmWave Radar Data via Few 2D Videos for Gesture Recognition While Lying Down
  18. "Special Relativity" of Image Aesthetics Assessment: a Preliminary Empirical Perspective
  19. AIGC Image Quality Assessment via Image-Prompt Correspondence
  20. AraLive: Automatic Reward Adaption for Learning-based Live Video Streaming
  21. CSAdv: Class-Specific Adversarial Patches for DETR-Style Object Detection
  22. Continuous Optical Zooming: A Benchmark for Arbitrary-Scale Image Super-Resolution in Real World
  23. Decomposed Vector-Quantized Variational Autoencoder for Human Grasp Generation
  24. ELTA: An Enhancer against Long-Tail for Aesthetics-oriented Models
  25. Exploring in Extremely Dark: Low-Light Video Enhancement with Real Events
  26. Learning Exposure Correction in Dynamic Scenes
  27. NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Results
  28. NTIRE 2024 Quality Assessment of AI-Generated Content Challenge
  29. Region-Aware Exposure Consistency Network for Mixed Exposure Correction
  30. Rethinking No-reference Image Exposure Assessment from Holism to Pixel: Models, Datasets and Benchmarks
  31. SGFormer: Semantic Graph Transformer for Point Cloud-Based 3D Scene Graph Generation
  32. SM4Depth: Seamless Monocular Metric Depth Estimation across Multiple Cameras and Scenes by One Model
  33. Semi-supervised Teacher-Reference-Student Architecture for Action Quality Assessment
  34. Weakly-Supervised Temporal Action Localization by Inferring Salient Snippet-Feature