Projects
LRM: Large Reconstruction Model for Single Image to 3D (2024): Website
PiC: A Phrase-in-Context Dataset for Phrase Understanding and Semantic Search (2023): Website
gScoreCAM: What is CLIP looking at? (2022): Code
Double Trouble: How to not explain a text classifier's decisions using counterfactuals synthesized by masked language models (2022): Code
Learning by Planning: Language-Guided Global Image Editing (2021): Website
GIER: Grounded Image Editing Request (2020): Website
PhraseCut: Language-based Image Segmentation in the Wild (2018-2020): Paper, Dataset
Expressing Visual Relationships via Language (2019): Data and Code
Voice-based Photo Editing (2016 - 2019). Demo: Youtube. Press coverage: Engadget, The Verge, PopPhoto, TechCrunch, PetaPixel. Here is the list of full coverage
Speech Driven Book Technology (2013-2017). Code: Github
Bot Colony (2010-2012). Demo: E3-2010 MIGS Tech Demo 2012
CALO - Cognitive Agent that Learns and Organizes (Funded by DARPA, 2009-2010)
SEMAINE - Sustained Emotionally coloured Machine-human Interaction using Nonverbal Expression (European Project, 2008-2009)
Interactive Collaborative Information System (Funded by Dutch Government, 2004-2008)
Multimodal Dialog Management (Funded by Swiss NSF, 2003-2004)
Inspire Smart Home (European Project, 2002-2004)
STING - Evaluation of Scientific & Technological Innovation and Progress in Europe through Pattents (European project, 2002)