The Centre for Vision, Speech and Signal Processing (CVSSP) is one of the major research centres of the Faculty of Electronics and Physical Sciences of the University of Surrey. Its aim is to advance the state of the art in multimedia signal processing and computer vision, with a focus on image, video and audio applications.
This server hosts the CVSSP internal Wiki, project pages and datasets for CVSSP. Our main website is available on the University's server
Dataset Pages Hosted Here
- CVSSP3D publications and Datasets
- 3DCars Dataset
- 3DMM - 3D Morphable face Models
- i3Dpost 3D Video Action Dataset
- DIPLECS Autonomous Driving Datasets
- Flickr25K - 25K images echoing the TU-Berlin sketch dataset
- Hollywood3d
- Kinect Sign Recognition
- Multiple View and 3D Video
- S3A Datasets
- POSZ RIR Dataset
- Surrey Mobile Dataset
- YouTube Long Term Tracking Sequences
Project Pages Hosted Here
- 4D Vision
- ACASVA - Adaptive Cognition for Automated Sports Video Annotation
- BRIDGET
- Comprehensible Video Thumbnails
- DynaVis - Learning to recognise Dynamic Visual content from broadcast footage
- ExTOL
- Face analysis
- G3 - Galvanising Guildford Games
- MacSeNet
- Making Sense of Sounds
- MARUSS
- S3A - Spatial Audio
- SpaRTaN