John Collomosse

Principal Scientist

London

Prof. John Collomosse is a principal scientist in Adobe’s Creative Intelligence Lab, based in the London (UK) office.

John has over 15 years experience in Computer Vision and AI, completing his PhD on Image and Video Stylization at the University of Bath in 2004. His research fuses Computer Vision, Graphics and AI to tackle big data problems in visual media, with emphasis on post-production/vfx and intelligent algorithms for searching and rendering large visual media repositories.

John’s work on visual search and content discovery focuses on sketch technologies, and models of visual style for aesthetic search.  This work has been demoed over Stock and Behance at Adobe MAX.  He has worked on volumetric video and performance capture for immersive AR/VR content production and video-realistic character animation, and on technologies for visual content provenance.

John serves on the advisory board of the UK Science Council EPSRC for Computer Science and for the Digital Economy theme.

My Publications

An Internal Learning Approach to Video Inpainting

Zhang, H., Mai, L., Xu, N., Wang, Z., Collomosse, J., Jin, H. (Oct. 28, 2019)
International Conference on Computer Vision (ICCV) 2019

Robust Synthesis of Adversarial Visual Examples Using a Deep Image Prior

Gittings, T., Schneider, S., Collomosse, J. (Sep. 11, 2019)
British Machine Vision Conference (BMVC) 2019

LiveSketch: Query Perturbation for Guided Sketch-based Visual Search

Collomosse, J., Bui, T., Jin, H. (Jun. 18, 2019)
Conference on Computer Vision and Pattern Recognition (CVPR) 2019

ARCHANGEL: Tamper-proofing Video Archives using Temporal Content Hashes on the Blockchain

Bui, T., Cooper, D., Collomosse, J., Bell, M., Green, A., Sheridan, J., Higgins, J., Das, A., Keller, J., Thereaux, O., Brown, A. (Jun. 17, 2019)
Computer Vision and Pattern Recognition (CVPR) Workshops 2019. Computer Vision, AI and Blockchain.

Fusing Visual and Inertial Sensors with Semantics for 3D Human Pose Estimation

Gilbert, A., Trumble, M., Malleson, C., Hilton, A., Collomosse, J. (Apr. 1, 2019)
International Journal of Computer Vision (IJCV)

In-painting of Wide-baseline Multiple Viewpoint Video

Gilbert, A., Trumble, M., Hilton, A., Collomosse, J., Collomosse, J. (Dec. 24, 2018)
IEEE Transactions on Visualization and Computer Graphics (TVCG)

Deep Manifold Alignment for Mid-grain Sketch based Image Retrieval

Bui, T., Ribeiro, L., Ponti, M., Collomosse, J. (Dec. 2, 2018)
Asian Conference on Computer Vision (ACCV). 2018.

TAPESTRY: Visualizing Interwoven Identities for Trust Provenance

Yang, Y., Collomosse, J., Manohar, A., Briggs, J., Steane, J. (Oct. 22, 2018)
IEEE Symposium on Visualization for Cyber Security (VizSec)

Volumetric performance capture from minimal camera viewpoints

Trumble, M., Gilbert, A., Hilton, A., Collomosse, J. (Sep. 9, 2018)
European Conference on Computer Vision (ECCV). 2018.

Deep Autoencoder for Combined Human Pose Estimation and Body Model Upscaling

Trumble, M., Gilbert, A., Hilton, A., Collomosse, J. (Sep. 8, 2018)
European Conference on Computer Vision (ECCV). 2018.

ARCHANGEL: Trusted Archives of Digital Public Documents

Collomosse, J., Bui, T., Brown, A., Sheridan, J., Green, A., Bell, M., Fawcett, J., Higgins, J., Thereaux, O. (Aug. 29, 2018)
ACM Conference on Document Engineering (DocEng). 2018.

Disentangling Structure and Aesthetics for Content-aware Image Completion

Gilbert, A., Collomosse, J., Jin, H., Price, B. (Jun. 18, 2018)
Conference on Computer Vision and Pattern Recognition (CVPR) 2018

Sketching out the Details: Sketch-based Image Retrieval using Convolutional Neural Networks with Multi-stage Regression

Bui, T., Ribeiro, L., Ponti, M., Collomosse, J. (Apr. 1, 2018)
Elsevier Journal on Computers & Graphics (C&G)

Compact descriptors for sketch-based image retrieval using a triplet loss convolutional neural network

Bui, T., Ribeiro, L., Ponti, M., Collomosse, J. (Nov. 1, 2017)
Journal on Computer Vision and Image Understanding (CVIU)

BAM! The Behance Artistic Media Dataset for Recognition Beyond Photography

Wilber, M., Fang, C., Jin, H., Hertzmann, A., Collomosse, J., Belongie, S. (Oct. 22, 2017)
International Conference on Computer Vision (ICCV). 2017.

Sketching with Style: Visual Search with Sketches and Aesthetic Context

Collomosse, J., Bui, T., Wilber, M., Fang, C., Jin, H. (Oct. 22, 2017)
International Conference on Computer Vision (ICCV). 2017.

Real-time Full-Body Motion Capture from Video and IMUs

Malleson, C., Gilbert, A., Trumble, M., Collomosse, J., Hilton, A., Volino, M. (Oct. 10, 2017)
International Conference on 3D Vision (3DV). 2017.

Total Capture: 3D Human Pose Estimation Fusing Video and Inertial Sensors

Trumble, M., Gilbert, A., Malleson, C., Hilton, A., Collomosse, J. (Sep. 4, 2017)
British Machine Vision Conference (BMVC). 2017.

Comprehensible Video Thumbnails

Kim, J., Gray, C., Asente, P., Collomosse, J. (May. 1, 2015)
Computer Graphics Forum (Proc. Eurographics 2015)

A Particle Filtering Approach to Salient Video Object Localization

Gray, C., James, S., Collomosse, J., Asente, P. (Oct. 1, 2014)
IEEE International Conference on Image Processing (ICIP). 2014.