Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308481509> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4308481509 abstract "In many applications of computer vision it is important to accurately estimate the trajectory of an object over time by fusing data from a number of sources, of which 2D and 3D imagery is only one. In this paper, we show how to use a deep feature encoding in conjunction with generative densities over the features in a factor-graph based, probabilistic tracking framework. We present a likelihood model that combines a learned feature encoder with generative densities over them, both trained in a supervised manner. We also experiment with directly inferring probability through the use of image classification models that feed into the likelihood formulation. These models are used to implement deep factors that are added to the factor graph to complement other factors that represent domain-specific knowledge such as motion models and/or other prior information. Factors are then optimized together in a non-linear least-squares tracking framework that takes the form of an Extended Kalman Smoother with a Gaussian prior. A key feature of our likelihood model is that it leverages the Lie group properties of the tracked target's pose to apply the feature encoding on an image patch, extracted through a differentiable warp function inspired by spatial transformer networks. To illustrate the proposed approach we evaluate it on a challenging social insect behavior dataset, and show that using deep features does outperform these earlier linear appearance models used in this setting." @default.
- W4308481509 created "2022-11-12" @default.
- W4308481509 creator A5016467437 @default.
- W4308481509 creator A5073438293 @default.
- W4308481509 creator A5079677096 @default.
- W4308481509 creator A5082717441 @default.
- W4308481509 creator A5087336025 @default.
- W4308481509 date "2021-12-02" @default.
- W4308481509 modified "2023-09-26" @default.
- W4308481509 title "Probabilistic Tracking with Deep Factors" @default.
- W4308481509 doi "https://doi.org/10.48550/arxiv.2112.01609" @default.
- W4308481509 hasPublicationYear "2021" @default.
- W4308481509 type Work @default.
- W4308481509 citedByCount "0" @default.
- W4308481509 crossrefType "posted-content" @default.
- W4308481509 hasAuthorship W4308481509A5016467437 @default.
- W4308481509 hasAuthorship W4308481509A5073438293 @default.
- W4308481509 hasAuthorship W4308481509A5079677096 @default.
- W4308481509 hasAuthorship W4308481509A5082717441 @default.
- W4308481509 hasAuthorship W4308481509A5087336025 @default.
- W4308481509 hasBestOaLocation W43084815091 @default.
- W4308481509 hasConcept C11413529 @default.
- W4308481509 hasConcept C119857082 @default.
- W4308481509 hasConcept C132525143 @default.
- W4308481509 hasConcept C138885662 @default.
- W4308481509 hasConcept C153180895 @default.
- W4308481509 hasConcept C154945302 @default.
- W4308481509 hasConcept C159246509 @default.
- W4308481509 hasConcept C167966045 @default.
- W4308481509 hasConcept C2776401178 @default.
- W4308481509 hasConcept C31972630 @default.
- W4308481509 hasConcept C39890363 @default.
- W4308481509 hasConcept C41008148 @default.
- W4308481509 hasConcept C41895202 @default.
- W4308481509 hasConcept C49937458 @default.
- W4308481509 hasConcept C57273362 @default.
- W4308481509 hasConcept C80444323 @default.
- W4308481509 hasConcept C83665646 @default.
- W4308481509 hasConceptScore W4308481509C11413529 @default.
- W4308481509 hasConceptScore W4308481509C119857082 @default.
- W4308481509 hasConceptScore W4308481509C132525143 @default.
- W4308481509 hasConceptScore W4308481509C138885662 @default.
- W4308481509 hasConceptScore W4308481509C153180895 @default.
- W4308481509 hasConceptScore W4308481509C154945302 @default.
- W4308481509 hasConceptScore W4308481509C159246509 @default.
- W4308481509 hasConceptScore W4308481509C167966045 @default.
- W4308481509 hasConceptScore W4308481509C2776401178 @default.
- W4308481509 hasConceptScore W4308481509C31972630 @default.
- W4308481509 hasConceptScore W4308481509C39890363 @default.
- W4308481509 hasConceptScore W4308481509C41008148 @default.
- W4308481509 hasConceptScore W4308481509C41895202 @default.
- W4308481509 hasConceptScore W4308481509C49937458 @default.
- W4308481509 hasConceptScore W4308481509C57273362 @default.
- W4308481509 hasConceptScore W4308481509C80444323 @default.
- W4308481509 hasConceptScore W4308481509C83665646 @default.
- W4308481509 hasLocation W43084815091 @default.
- W4308481509 hasOpenAccess W4308481509 @default.
- W4308481509 hasPrimaryLocation W43084815091 @default.
- W4308481509 hasRelatedWork W1504288058 @default.
- W4308481509 hasRelatedWork W2017205855 @default.
- W4308481509 hasRelatedWork W2031347084 @default.
- W4308481509 hasRelatedWork W2048505601 @default.
- W4308481509 hasRelatedWork W2167293474 @default.
- W4308481509 hasRelatedWork W2331674254 @default.
- W4308481509 hasRelatedWork W2358403311 @default.
- W4308481509 hasRelatedWork W2922188210 @default.
- W4308481509 hasRelatedWork W2979079341 @default.
- W4308481509 hasRelatedWork W3042897387 @default.
- W4308481509 isParatext "false" @default.
- W4308481509 isRetracted "false" @default.
- W4308481509 workType "article" @default.