One-Shot Learning for Human Affordance Detection

Abel Pacheco-Ortega; Walterio Mayol-Cuervas

doi:10.1007/978-3-031-25066-8_46

One-Shot Learning for Human Affordance Detection

Abel Pacheco-Ortega^*
, Walterio Mayol-Cuervas

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

1 Citation (Scopus)

15 Downloads (Pure)

Abstract

The diversity of action possibilities offered by an environment, a.k.a affordances, cannot be addressed in a scalable manner simply from object categories or semantics, which are limitless. To this end, we present a one-shot learning approach that trains on one or a handful of human-scene interaction samples. Then, given a previously unseen scene, we can predict human affordances and generate the associated articulated 3D bodies. Our experiments show that our approach generates physically plausible interactions that are perceived as more natural in 60–70% of the comparisons with other methods.

Original language	English
Title of host publication	Computer Vision – ECCV 2022 Workshops, Proceedings
Editors	Leonid Karlinsky, Tomer Michaeli, Ko Nishino
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	758-766
Number of pages	9
ISBN (Electronic)	978-3-031-25066-8
ISBN (Print)	9783031250651
DOIs	https://doi.org/10.1007/978-3-031-25066-8_46
Publication status	Published - 18 Feb 2023
Event	17th European Conference on Computer Vision, ECCV 2022 - Tel Aviv, Israel Duration: 23 Oct 2022 → 27 Oct 2022 https://eccv2022.ecva.net/

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer Cham
Volume	13803 LNCS
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	17th European Conference on Computer Vision, ECCV 2022
Country/Territory	Israel
City	Tel Aviv
Period	23/10/22 → 27/10/22
Internet address	https://eccv2022.ecva.net/

Bibliographical note

Publisher Copyright:
© 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Keywords

Affordances
Affordances detection
Human interactions
Scene understanding
Visual perception

Access to Document

10.1007/978-3-031-25066-8_46

Full-text PDF (accepted manuscript)
This is the accepted author manuscript (AAM). The final published version (Version of Record) can be found on the publisher's website. The copyright of any third-party content, such as images, remains with the copyright holder.
Accepted author manuscript, 7.59 MB

Handle.net

Persistent link

Cite this

@inproceedings{dc838d01d976450180b7a4542842775c,

title = "One-Shot Learning for Human Affordance Detection",

abstract = "The diversity of action possibilities offered by an environment, a.k.a affordances, cannot be addressed in a scalable manner simply from object categories or semantics, which are limitless. To this end, we present a one-shot learning approach that trains on one or a handful of human-scene interaction samples. Then, given a previously unseen scene, we can predict human affordances and generate the associated articulated 3D bodies. Our experiments show that our approach generates physically plausible interactions that are perceived as more natural in 60–70\% of the comparisons with other methods.",

keywords = "Affordances, Affordances detection, Human interactions, Scene understanding, Visual perception",

author = "Abel Pacheco-Ortega and Walterio Mayol-Cuervas",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.; 17th European Conference on Computer Vision, ECCV 2022 ; Conference date: 23-10-2022 Through 27-10-2022",

year = "2023",

month = feb,

day = "18",

doi = "10.1007/978-3-031-25066-8\_46",

language = "English",

isbn = "9783031250651",

series = "Lecture Notes in Computer Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "758--766",

editor = "Leonid Karlinsky and Tomer Michaeli and Ko Nishino",

booktitle = "Computer Vision – ECCV 2022 Workshops, Proceedings",

address = "Germany",

url = "https://eccv2022.ecva.net/",

}

Pacheco-Ortega, A & Mayol-Cuervas, W 2023, One-Shot Learning for Human Affordance Detection. in L Karlinsky, T Michaeli & K Nishino (eds), Computer Vision – ECCV 2022 Workshops, Proceedings. Lecture Notes in Computer Science, vol. 13803 LNCS, Springer Science and Business Media Deutschland GmbH, pp. 758-766, 17th European Conference on Computer Vision, ECCV 2022, Tel Aviv, Israel, 23/10/22. https://doi.org/10.1007/978-3-031-25066-8_46

One-Shot Learning for Human Affordance Detection. / Pacheco-Ortega, Abel; Mayol-Cuervas, Walterio.
Computer Vision – ECCV 2022 Workshops, Proceedings. ed. / Leonid Karlinsky; Tomer Michaeli; Ko Nishino. Springer Science and Business Media Deutschland GmbH, 2023. p. 758-766 (Lecture Notes in Computer Science; Vol. 13803 LNCS).

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - One-Shot Learning for Human Affordance Detection

AU - Pacheco-Ortega, Abel

AU - Mayol-Cuervas, Walterio

PY - 2023/2/18

Y1 - 2023/2/18

N2 - The diversity of action possibilities offered by an environment, a.k.a affordances, cannot be addressed in a scalable manner simply from object categories or semantics, which are limitless. To this end, we present a one-shot learning approach that trains on one or a handful of human-scene interaction samples. Then, given a previously unseen scene, we can predict human affordances and generate the associated articulated 3D bodies. Our experiments show that our approach generates physically plausible interactions that are perceived as more natural in 60–70% of the comparisons with other methods.

AB - The diversity of action possibilities offered by an environment, a.k.a affordances, cannot be addressed in a scalable manner simply from object categories or semantics, which are limitless. To this end, we present a one-shot learning approach that trains on one or a handful of human-scene interaction samples. Then, given a previously unseen scene, we can predict human affordances and generate the associated articulated 3D bodies. Our experiments show that our approach generates physically plausible interactions that are perceived as more natural in 60–70% of the comparisons with other methods.

KW - Affordances

KW - Affordances detection

KW - Human interactions

KW - Scene understanding

KW - Visual perception

UR - https://www.scopus.com/pages/publications/85151131485

U2 - 10.1007/978-3-031-25066-8_46

DO - 10.1007/978-3-031-25066-8_46

M3 - Conference Contribution (Conference Proceeding)

AN - SCOPUS:85151131485

SN - 9783031250651

T3 - Lecture Notes in Computer Science

SP - 758

EP - 766

BT - Computer Vision – ECCV 2022 Workshops, Proceedings

A2 - Karlinsky, Leonid

A2 - Michaeli, Tomer

A2 - Nishino, Ko

PB - Springer Science and Business Media Deutschland GmbH

T2 - 17th European Conference on Computer Vision, ECCV 2022

Y2 - 23 October 2022 through 27 October 2022

ER -

One-Shot Learning for Human Affordance Detection

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Handle.net

Other files and links

Fingerprint

Cite this