84 citations
- University of SurreyGB6 papers
- Samsung (South Korea)KR4 papers
- National Technical University of AthensGR3 papers
- University of CambridgeGB3 papers
- University of OxfordGB3 papers
- Ericsson (Sweden)SE2 papers
- Huawei Technologies (Germany)DE2 papers
- Imperial College LondonGB2 papers
- Intel (Germany)DE2 papers
- Laboratoire Informatique d'AvignonFR2 papers
- Nokia (Finland)FI2 papers
- Orange (France)FR2 papers
11 papers · 1 filter
A Modular System for Enhanced Robustness of Multimedia Understanding Networks via Deep Parametric Estimation
Francesco Barbato, Umberto Michieli, Mehmet Kerim Yucel +2
In multimedia understanding tasks, corrupted samples pose a critical challenge, because when fed to machine learning models they lead to performance degradation. In the past, three…
Relevance-based Margin for Contrastively-trained Video Retrieval Models
Alex Falcon, Swathikiran Sudhakaran, Giuseppe Serra +2
Video retrieval using natural language queries has attracted increasing interest due to its relevance in real-world applications, from intelligent access in private media galleries…
Fast Hybrid Image Retargeting
Daniel Valdez-Balderas, Oleg Muraveynyk, Timothy Smith
Image retargeting changes the aspect ratio of images while aiming to preserve content and minimise noticeable distortion. Fast and high-quality methods are particularly relevant at…
Improving memory banks for unsupervised learning with large mini-batch, consistency and hard negative mining
Adrian Bulat, Enrique Sánchez-Lozano, Georgios Tzimiropoulos
An important component of unsupervised learning by instance-based discrimination is a memory bank for storing a feature representation for each training sample in the dataset. In t…
Towards Uncovering the Intrinsic Data Structures for Unsupervised Domain Adaptation using Structurally Regularized Deep Clustering
Hui Tang, Xiatian Zhu, Ke Chen +2
Unsupervised domain adaptation (UDA) is to learn classification models that make predictions for unlabeled data on a target domain, given labeled data on a source domain whose dist…
A Transfer Learning approach to Heatmap Regression for Action Unit intensity estimation
Ioanna Ntinou, Enrique Sanchez, Adrian Bulat +2
Action Units (AUs) are geometrically-based atomic facial muscle movements known to produce appearance changes at specific facial locations. Motivated by this observation we propose…