Adrian Hilton

SEM-POS: Grammatically and Semantically Correct Video Captioning

Apr 04, 2023
Asmar Nadeem, Adrian Hilton, Robert Dawes, Graham Thomas, Armin Mustafa

Figure 2 for SEM-POS: Grammatically and Semantically Correct Video Captioning

Figure 3 for SEM-POS: Grammatically and Semantically Correct Video Captioning

Figure 4 for SEM-POS: Grammatically and Semantically Correct Video Captioning

Access Paper or Ask Questions

Super-resolution 3D Human Shape from a Single Low-Resolution Image

Aug 23, 2022
Marco Pesavento, Marco Volino, Adrian Hilton

Figure 2 for Super-resolution 3D Human Shape from a Single Low-Resolution Image

Figure 3 for Super-resolution 3D Human Shape from a Single Low-Resolution Image

Figure 4 for Super-resolution 3D Human Shape from a Single Low-Resolution Image

Access Paper or Ask Questions

Visually Supervised Speaker Detection and Localization via Microphone Array

Mar 07, 2022
Davide Berghi, Adrian Hilton, Philip J. B. Jackson

Figure 2 for Visually Supervised Speaker Detection and Localization via Microphone Array

Figure 3 for Visually Supervised Speaker Detection and Localization via Microphone Array

Figure 4 for Visually Supervised Speaker Detection and Localization via Microphone Array

* IEEE 23rd International Workshop on Multimedia Signal Processing (MMSP), 2021
* Erratum: Due to a bug in the evaluation script, the correct average distance (aD) metric is here reported in yellow. The analysis remains unchanged from the original paper as the trend between the old and new measures are perfectly monotonic. The bug was caused by an incorrect normalization factor

Access Paper or Ask Questions

Super-Resolution Appearance Transfer for 4D Human Performances

Aug 31, 2021
Marco Pesavento, Marco Volino, Adrian Hilton

Figure 2 for Super-Resolution Appearance Transfer for 4D Human Performances

Figure 3 for Super-Resolution Appearance Transfer for 4D Human Performances

Figure 4 for Super-Resolution Appearance Transfer for 4D Human Performances

Access Paper or Ask Questions

Attention-based Multi-Reference Learning for Image Super-Resolution

Aug 31, 2021
Marco Pesavento, Marco Volino, Adrian Hilton

Figure 2 for Attention-based Multi-Reference Learning for Image Super-Resolution

Figure 3 for Attention-based Multi-Reference Learning for Image Super-Resolution

Figure 4 for Attention-based Multi-Reference Learning for Image Super-Resolution

Access Paper or Ask Questions

SyDog: A Synthetic Dog Dataset for Improved 2D Pose Estimation

Jul 31, 2021
Moira Shooter, Charles Malleson, Adrian Hilton

Figure 2 for SyDog: A Synthetic Dog Dataset for Improved 2D Pose Estimation

Figure 3 for SyDog: A Synthetic Dog Dataset for Improved 2D Pose Estimation

Figure 4 for SyDog: A Synthetic Dog Dataset for Improved 2D Pose Estimation

* 5 pages, 1 figure, Poster presentation at the Computer Vision for Animal Behavior Tracking and Modeling (CV4Animals:) Workshop in conjunction with CVPR 2021

Access Paper or Ask Questions