Výsledky vyhledávání - "Frank M. Hafner"

Cross-modal distillation for RGB-depth person re-identification

Autor: Frank M. Hafner, Amran Bhuyian, Julian F.P. Kooij, Eric Granger

Publikováno v: Computer Vision and Image Understanding, 216

Person re-identification is a key challenge for surveillance across multiple sensors. Prompted by the advent of powerful deep learning models for visual recognition, and inexpensive RGB-D cameras and sensor-rich mobile robotic platforms, e.g. self-dr

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0c251fa2616b70e5ec5b0c896f558eb3
http://resolver.tudelft.nl/uuid:23ce667a-600d-454d-97c3-a22fca9a3625

Zobrazit plný text záznamu

BackboneAnalysis: Structured Insights into Compute Platforms from CNN Inference Latency

Autor: Frank M. Hafner, Matthias Zeller, Mark Schutera, Jochen Abhau, Julian F.P. Kooij

Publikováno v: Proceedings of the 2022 IEEE Intelligent Vehicles Symposium (IV)

Customization of a convolutional neural network (CNN) to a specific compute platform involves finding an optimal pareto state between computational complexity of the CNN and resulting throughput in operations per second on the compute platform. Howev

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0395484bece43dce4f3efbd405573574
http://resolver.tudelft.nl/uuid:2f6fbb7a-b6ba-49b4-9740-c7306c994c48

Zobrazit plný text záznamu

Domain is of the Essence: Data Deployment for City-Scale Multi-Camera Vehicle Re-Identification

Autor: Jochen Abhau, Mark Schutera, Frank M. Hafner, Hendrik Vogt, Markus Reischl

Publikováno v: AVSS

In deep learning applications large annotated datasets are considered necessary for application development and improved model performance. This work aims to investigate the validity of this assumption when enlarging a given dataset, by secondary dat

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::4236aeb39c9d861373a89278ef776244
https://doi.org/10.1109/avss.2019.8909858

Zobrazit plný text záznamu

RGB-Depth cross-modal person re-identification

Autor: Frank M. Hafner, Julian F. P. Kooij, Eric Granger, Amran Bhuiyan

Publikováno v: Proceedings of the 16th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS 2019)
AVSS

Person re-identification is a key challenge for surveillance across multiple sensors. Prompted by the advent of powerful deep learning models for visual recognition, and inexpensive RGBD cameras and sensor-rich mobile robotic platforms, e.g. self-dri

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::45c093d5b6e2dd3303e1ffdce5722998
http://resolver.tudelft.nl/uuid:261bdf5c-4e9c-4d37-bc55-ecb93181a4be

Zobrazit plný text záznamu

Cuepervision: self-supervised learning for continuous domain adaptation without catastrophic forgetting

Autor: Ralf Mikut, Veit Hagenmeyer, Frank M. Hafner, Mark Schutera, Markus Reischl, Jochen Abhau

Publikováno v: Image and Vision Computing. 106:104079

Perception systems, to a large extent, rely on neural networks. Commonly, the training of neural networks uses a finite amount of data. The usual assumption is that an appropriate training dataset is available, which covers all relevant domains. This

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::986dd786aa31299792273fcf904d917c
https://doi.org/10.1016/j.imavis.2020.104079

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání