Area of research
Computer Vision and Pattern Recognition
Research interest
Research interests include Computer science, Artificial intelligence, Computer vision, Encoding (memory), Texture (cosmology), and Image (mathematics).
LSE-NeRF: Learning Sensor Modeling Errors for Deblured Neural Radiance Fields with RGB-Event Stereo
Comparing Deep Neural Network Architectures as Models of Human Lightness and Illusion Perception.
Revisiting Image Fusion for Multi-Illuminant White-Balance Correction
Position, Padding and Predictions: A Deeper Look at Position Information in CNNs
Watch Your Steps: Local Image and Scene Editing by Text Instructions
Understanding Video Transformers via Universal Concept Discovery
Visual Concept Connectome (VCC): Open World Concept Discovery and Their Interlayer Connections in Deep Models
PolyOculus: Simultaneous Multi-view Image-Based Novel View Synthesis
Quantifying and Learning Static vs. Dynamic Information in Deep Spatiotemporal Networks
Lightness Illusions Through AI Eyes: Assessing ConvNet and ViT Concordance with Human Perception
SPIn-NeRF: Multiview Segmentation and Perceptual Inpainting with Neural Radiance Fields
Reference-guided Controllable Inpainting of Neural Radiance Fields
Long-Term Photometric Consistent Novel View Synthesis with Diffusion Models
StepFormer: Self-Supervised Step Discovery and Localization in Instructional Videos
GePSAn: Generative Procedure Step Anticipation in Cooking Videos
P<sup>3</sup>IV: Probabilistic Procedure Planning from Instructional Videos with Weak Supervision
A Deeper Dive Into What Deep Spatiotemporal Networks Encode: Quantifying Static vs. Dynamic Information
SegMix: Co-occurrence Driven Mixup for Semantic Segmentation and Adversarial Robustness
Global Pooling, More than Meets the Eye: Position Information is Encoded Channel-Wise in CNNs
Shape or Texture: Understanding Discriminative Features in CNNs
Learning Multi-Scale Photo Exposure Correction
Boundary Effects in CNNs: Feature or Bug?
2021cited by 3position: middle
Global Pooling, More than Meets the Eye: Position Information is Encoded Channel-Wise in CNNs
Wavelet Flow: Fast Training of High Resolution Normalizing Flows
Wavelet Flow: Fast Training of High Resolution Normalizing Flows
York University Digital Library (York University) 2020cited by 6position: middle
Convolutional Photomosaic Generation via Multi-scale Perceptual Losses
Two-Stream Convolutional Networks for Dynamic Texture Synthesis
Two-Stream Convolutional Networks for Dynamic Texture Synthesis
Dynamic scene understanding: The role of orientation features in space and time in scene classification
Action Spotting and Recognition Based on a Spatiotemporal Orientation Analysis