Yannis Kalantidis

Binding

Research Interests
Summary Representation learning in constrained environments & multi-modal learning.
Learning with limited computation, data and other resources, edge computing
Representation learning for image and video.
[ECCV 2016, ECCV 2018, NeurIPS 2018, CVPR 2019a, ICCV 2019]
Vision and language, multi-modal search.
[IJCV 2017, WSDM 2017, AAAI 2019, CVPR 2019b, TPAMI 2019]
Video understanding.
Description and grounding [CVPR 2019b, Arxiv 2019], summarization [CVPR 2019c], motion [CVPR
2019d]
Web-scale nearest neighbor search, clustering and classification.
[ECCV 2012, CVPR 2014, ICCV 2015, NeurIPSw 2016]