Non-Separable Multi-Dimensional Network Flows for Visual Computing
| dc.contributor.author | Ehm, Viktoria | en_US |
| dc.contributor.author | Cremers, Daniel | en_US |
| dc.contributor.author | Bernard, Florian | en_US |
| dc.contributor.editor | Singh, Gurprit | en_US |
| dc.contributor.editor | Chu, Mengyu (Rachel) | en_US |
| dc.date.accessioned | 2023-05-03T06:05:54Z | |
| dc.date.available | 2023-05-03T06:05:54Z | |
| dc.date.issued | 2023 | |
| dc.description.abstract | Flows in networks (or graphs) play a significant role in numerous computer vision tasks. The scalar-valued edges in these graphs often lead to a loss of information and thereby to limitations in terms of expressiveness. For example, oftentimes highdimensional data (e.g. feature descriptors) are mapped to a single scalar value (e.g. the similarity between two feature descriptors). To overcome this limitation, we propose a novel formalism for non-separable multi-dimensional network flows. By doing so, we enable an automatic and adaptive feature selection strategy - since the flow is defined on a per-dimension basis, the maximizing flow automatically chooses the best matching feature dimensions. As a proof of concept, we apply our formalism to the multi-object tracking problem and demonstrate that our approach outperforms scalar formulations on the MOT16 benchmark in terms of robustness to noise. | en_US |
| dc.description.sectionheaders | Posters | |
| dc.description.seriesinformation | Eurographics 2023 - Posters | |
| dc.identifier.doi | 10.2312/egp.20231028 | |
| dc.identifier.isbn | 978-3-03868-211-0 | |
| dc.identifier.issn | 1017-4656 | |
| dc.identifier.pages | 15-16 | |
| dc.identifier.pages | 2 pages | |
| dc.identifier.uri | https://doi.org/10.2312/egp.20231028 | |
| dc.identifier.uri | https://diglib.eg.org:443/handle/10.2312/egp20231028 | |
| dc.publisher | The Eurographics Association | en_US |
| dc.rights | Attribution 4.0 International License | |
| dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | |
| dc.subject | CCS Concepts: Theory of computation -> Design and analysis of algorithms; Theory and algorithms for application domains | |
| dc.subject | Theory of computation | |
| dc.subject | Design and analysis of algorithms | |
| dc.subject | Theory and algorithms for application domains | |
| dc.title | Non-Separable Multi-Dimensional Network Flows for Visual Computing | en_US |