H
Hakan Bilen
Researcher at University of Edinburgh
Publications - 108
Citations - 5630
Hakan Bilen is an academic researcher from University of Edinburgh. The author has contributed to research in topics: Computer science & Artificial neural network. The author has an hindex of 23, co-authored 86 publications receiving 3906 citations. Previous affiliations of Hakan Bilen include Katholieke Universiteit Leuven & University of Oxford.
Papers
More filters
Proceedings ArticleDOI
Weakly Supervised Deep Detection Networks
Hakan Bilen,Andrea Vedaldi +1 more
TL;DR: This paper proposes a weakly supervised deep detection architecture that modifies one such network to operate at the level of image regions, performing simultaneously region selection and classification.
Proceedings ArticleDOI
Dynamic Image Networks for Action Recognition
TL;DR: The new approximate rank pooling CNN layer allows the use of existing CNN models directly on video data with fine-tuning to generalize dynamic images to dynamic feature maps and the power of the new representations on standard benchmarks in action recognition achieving state-of-the-art performance.
Proceedings ArticleDOI
Self-Supervised Video Representation Learning with Odd-One-Out Networks
TL;DR: A new self-supervised CNN pre-training technique based on a novel auxiliary task called odd-one-out learning, which learns temporal representations for videos that generalizes to other related tasks such as action recognition.
Proceedings Article
Learning multiple visual domains with residual adapters
TL;DR: In this paper, a tunable deep network architecture that, by means of adapter residual modules, can be steered on the fly to diverse visual domains is proposed. But it does not address the task of learning a single visual representation that can be successfully utilized in the analysis of very different types of images, from dog breeds to stop signs.
Posted Content
Learning multiple visual domains with residual adapters
TL;DR: This paper develops a tunable deep network architecture that, by means of adapter residual modules, can be steered on the fly to diverse visual domains and introduces the Visual Decathlon Challenge, a benchmark that evaluates the ability of representations to capture simultaneously ten very differentVisual domains and measures their ability to recognize well uniformly.