Peeping the Research

Following are some research notes.

• Candidate Topics

  • Cloud-Device Collaborative Learning via small and large lanauge models for mobile health
  • Efficient Cloth Try-on Image Synthesis via Denoising Diffusion Model
  • Brain-inspired computing by assemblies of neurons
  • Breath Tracking using a Depth Camera for XV Scanner
  • Images to Text for Museum Collection
  • Model Reprogramming for Low-Level Image Processing

• Computer Graphics

  • Guided Image Filtering
  • Motion Magnification

• Computer Vision

  • PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

• Human-Computer Interaction

• Motion Magnification

  • Bilateral Video Magnification Filter
  • Eulerian Video Magnification for Revealing Subtle Changes in the World
  • Learning-based Axial Video Motion Magnification

• Remote Photo Plethysmography (rPPG)

  • Ballistocardiogram signal processing: a review
  • EVM-CNN: Real-Time Contactless Heart Rate Estimation from Facial Video
  • Feasibility of Heart Rate and Respiratory Rate Estimation by Inertial Sensors Embedded in a Virtual Reality Headset
  • PhysFormer++: Facial Video-based Physiological Measurement with SlowFast Temporal Difference Transformer
  • RhythmMamba: Fast, Lightweight, and Accurate Remote Physiological Measurement
  • rPPG-Toolbox: Deep Remote PPG Toolbox

• Respiratory Monitoring

  • An Unobtrusive and Non-Contact Method for Respiratory Measurement With Respiratory Region Detecting Algorithm Based on Depth Images
  • DeepBreath: Breathing Exercise Assessment with a Depth Camera
  • Markerless Active Trunk Shape Modelling for Motion Tolerant Remote Respiratory Assessment
  • Sensing Systems for Respiration Monitoring: A Technical Systematic Review
  • Soleimani's Dataset
  • Video-Based Respiratory Rate Estimation for Infants in the NICU

• Semantic Segmentation

  • BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
  • ICNet for Real-Time Semantic Segmentation on High-Resolution Images
  • Indoor Semantic Segmentation using depth information
  • SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory
  • Segment Anything