Diversely-Supervised Visual Product Search

Autor: Thong, W., Snoek, C.G.M.

Publikováno v: ACM Transactions on Multimedia Computing Communications and Applications, 18(1):13. Association for Computing Machinery (ACM)

This article strives for a diversely supervised visual product search, where queries specify a diverse set of labels to search for. Where previous works have focused on representing attribute, instance, or category labels individually, we consider th

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1e08c08611ef8e2707c441432d9278b4
https://doi.org/10.1145/3461646

Localizing the Common Action Among a Few Videos

Autor: Yang, P., Hu, V.T., Mettes, P., Snoek, C.G.M., Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M.

Publikováno v: Computer Vision – ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020 : proceedings, VII, 505-521
Computer Vision – ECCV 2020 ISBN: 9783030585709
ECCV (7)

This paper strives to localize the temporal extent of an action in a long untrimmed video. Where existing work leverages many examples with their start, their ending, and/or the class of the action during training time, we propose few-shot common act

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::63a54e2831caaa328e9ab946d05b9a5c
https://hdl.handle.net/11245.1/54444605-0ec3-4859-9392-bf042065487c

Less than Few: Self-Shot Video Instance Segmentation

Autor: Yang, P., Asano, Y.M., Mettes, P., Snoek, C.G.M., Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T.

Publikováno v: Computer Vision – ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022 : proceedings, XXXIV
Lecture Notes in Computer Science ISBN: 9783031198298

The goal of this paper is to bypass the need for labelled examples in few-shot video understanding at run time. While proven effective, in many practical video settings even labelling a few examples appears unrealistic. This is especially true as the

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::76e550ea805ced3eee253f68b3526991
https://hdl.handle.net/11245.1/469816f8-1729-4d26-b3a9-d90c359aa38e

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Meta-Learning with Variational Semantic Memory for Word Sense Disambiguation

Autor: Du, Y., Holla, N., Zhen, X., Snoek, C.G.M., Shutova, E., Zong, C., Xia, F., Li, W., Navigli, R.

Publikováno v: The 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: ACL-IJCNLP 2021 : proceedings of the conference : August 1-6, 2021, 1, 5254-5268
ACL/IJCNLP (1)

A critical challenge faced by supervised word sense disambiguation (WSD) is the lack of large annotated datasets with sufficient coverage of words in their diversity of senses. This inspired recent research on few-shot WSD using meta-learning. While

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::47d8751510e4573e0dc5c71fea5c221a
https://doi.org/10.18653/v1/2021.acl-long.409