Roberto Cipolla
University of Cambridge · 518 works · 53,567 citations · h-index 82
Top works
- SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
- Semantic texton forests for image categorization and segmentation
- Semantic object classes in video: A high-definition ground truth database
- Robust structure from motion using motion parallax
- Segmentation and Recognition Using Structure from Motion Point Clouds
- Multi-task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
- Feature-based human face detection
- PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization
- Contour-based learning for object detection
- Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding
- Determining the gaze of faces in images
- Deep Roots: Improving CNN Efficiency with Hierarchical Filter Groups
- Shape context and chamfer matching in cluttered scenes
- Surface orientation and time to contact from image divergence and deformation
- Unsupervised Bayesian Detection of Independent Motion in Crowds
- The dynamic analysis of apparent contours
- Real-time visual tracking of complex structures
- Learning Motion Categories using both Semantic and Structural Information
- Multi-View Stereo via Volumetric Graph-Cuts
- Extracting Spatiotemporal Interest Points using Global Information