Polynomial Neural Fields for Subband Decomposition and Manipulation

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt

Standard

Polynomial Neural Fields for Subband Decomposition and Manipulation. / Bender, Thoranna ; Sørensen, Simon Moe ; Kashani, Alireza; Hjorleifsson, K. Eldjarn; Hyldig, Grethe; Hauberg, Søren; Belongie, Serge; Warburg, Frederik .

Advances in Neural Information Processing Systems 36 - 37th Conference on Neural Information Processing Systems, NeurIPS 2023. Neural Information Processing Systems Foundation, 2023. (Advances in Neural Information Processing Systems, Bind 36).

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt

Harvard

Bender, T, Sørensen, SM, Kashani, A, Hjorleifsson, KE, Hyldig, G, Hauberg, S, Belongie, S & Warburg, F 2023, Polynomial Neural Fields for Subband Decomposition and Manipulation. i Advances in Neural Information Processing Systems 36 - 37th Conference on Neural Information Processing Systems, NeurIPS 2023. Neural Information Processing Systems Foundation, Advances in Neural Information Processing Systems, bind 36, 36th Conference on Neural Information Processing Systems, NeurIPS 2022, New Orleans, USA, 28/11/2022.

APA

Bender, T., Sørensen, S. M., Kashani, A., Hjorleifsson, K. E., Hyldig, G., Hauberg, S., Belongie, S., & Warburg, F. (2023). Polynomial Neural Fields for Subband Decomposition and Manipulation. I Advances in Neural Information Processing Systems 36 - 37th Conference on Neural Information Processing Systems, NeurIPS 2023 Neural Information Processing Systems Foundation. Advances in Neural Information Processing Systems Bind 36

Vancouver

Bender T, Sørensen SM, Kashani A, Hjorleifsson KE, Hyldig G, Hauberg S o.a. Polynomial Neural Fields for Subband Decomposition and Manipulation. I Advances in Neural Information Processing Systems 36 - 37th Conference on Neural Information Processing Systems, NeurIPS 2023. Neural Information Processing Systems Foundation. 2023. (Advances in Neural Information Processing Systems, Bind 36).

Author

Bender, Thoranna ; Sørensen, Simon Moe ; Kashani, Alireza ; Hjorleifsson, K. Eldjarn ; Hyldig, Grethe ; Hauberg, Søren ; Belongie, Serge ; Warburg, Frederik . / Polynomial Neural Fields for Subband Decomposition and Manipulation. Advances in Neural Information Processing Systems 36 - 37th Conference on Neural Information Processing Systems, NeurIPS 2023. Neural Information Processing Systems Foundation, 2023. (Advances in Neural Information Processing Systems, Bind 36).

Bibtex

@inproceedings{60213480624242a78fa59079a22ae124,
title = "Polynomial Neural Fields for Subband Decomposition and Manipulation",
abstract = "We present WineSensed, a large multimodal wine dataset for studying the relations between visual perception, language, and flavor. The dataset encompasses 897k images of wine labels and 824k reviews of wines curated from the Vivino platform. It has over 350k unique vintages, annotated with year, region, rating, alcohol percentage, price, and grape composition. We obtained fine-grained flavor annotations on a subset by conducting a wine-tasting experiment with 256 participants who were asked to rank wines based on their similarity in flavor, resulting in more than 5k pairwise flavor distances. We propose a low-dimensional concept embedding algorithm that combines human experience with automatic machine similarity kernels. We demonstrate that this shared concept embedding space improves upon separate embedding spaces for coarse flavor classification (alcohol percentage, country, grape, price, rating) and representing human perception of flavor.",
author = "Thoranna Bender and S{\o}rensen, {Simon Moe} and Alireza Kashani and Hjorleifsson, {K. Eldjarn} and Grethe Hyldig and S{\o}ren Hauberg and Serge Belongie and Frederik Warburg",
note = "Publisher Copyright: {\textcopyright} 2022 Neural information processing systems foundation. All rights reserved.; 36th Conference on Neural Information Processing Systems, NeurIPS 2022 ; Conference date: 28-11-2022 Through 09-12-2022",
year = "2023",
language = "English",
series = "Advances in Neural Information Processing Systems",
publisher = "Neural Information Processing Systems Foundation",
booktitle = "Advances in Neural Information Processing Systems 36 - 37th Conference on Neural Information Processing Systems, NeurIPS 2023",

}

RIS

TY - GEN

T1 - Polynomial Neural Fields for Subband Decomposition and Manipulation

AU - Bender, Thoranna

AU - Sørensen, Simon Moe

AU - Kashani, Alireza

AU - Hjorleifsson, K. Eldjarn

AU - Hyldig, Grethe

AU - Hauberg, Søren

AU - Belongie, Serge

AU - Warburg, Frederik

N1 - Publisher Copyright: © 2022 Neural information processing systems foundation. All rights reserved.

PY - 2023

Y1 - 2023

N2 - We present WineSensed, a large multimodal wine dataset for studying the relations between visual perception, language, and flavor. The dataset encompasses 897k images of wine labels and 824k reviews of wines curated from the Vivino platform. It has over 350k unique vintages, annotated with year, region, rating, alcohol percentage, price, and grape composition. We obtained fine-grained flavor annotations on a subset by conducting a wine-tasting experiment with 256 participants who were asked to rank wines based on their similarity in flavor, resulting in more than 5k pairwise flavor distances. We propose a low-dimensional concept embedding algorithm that combines human experience with automatic machine similarity kernels. We demonstrate that this shared concept embedding space improves upon separate embedding spaces for coarse flavor classification (alcohol percentage, country, grape, price, rating) and representing human perception of flavor.

AB - We present WineSensed, a large multimodal wine dataset for studying the relations between visual perception, language, and flavor. The dataset encompasses 897k images of wine labels and 824k reviews of wines curated from the Vivino platform. It has over 350k unique vintages, annotated with year, region, rating, alcohol percentage, price, and grape composition. We obtained fine-grained flavor annotations on a subset by conducting a wine-tasting experiment with 256 participants who were asked to rank wines based on their similarity in flavor, resulting in more than 5k pairwise flavor distances. We propose a low-dimensional concept embedding algorithm that combines human experience with automatic machine similarity kernels. We demonstrate that this shared concept embedding space improves upon separate embedding spaces for coarse flavor classification (alcohol percentage, country, grape, price, rating) and representing human perception of flavor.

M3 - Article in proceedings

T3 - Advances in Neural Information Processing Systems

BT - Advances in Neural Information Processing Systems 36 - 37th Conference on Neural Information Processing Systems, NeurIPS 2023

PB - Neural Information Processing Systems Foundation

T2 - 36th Conference on Neural Information Processing Systems, NeurIPS 2022

Y2 - 28 November 2022 through 9 December 2022

ER -

ID: 384576085