Zobrazeno 1 - 10
of 357
pro vyhledávání: '"Bernt Schiele"'
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 11, Pp 565-581 (2023)
AbstractCurrent work on image-based story generation suffers from the fact that the existing image sequence collections do not have coherent plots behind them. We improve visual story generation by producing a new image-grounded dataset, Visual Writi
Externí odkaz:
https://doaj.org/article/ee386cf2c0d44ad7b338b95c4efd7dcc
Publikováno v:
Applied AI Letters, Vol 2, Iss 4, Pp n/a-n/a (2021)
Abstract We generate natural language explanations for a fine‐grained visual recognition task. Our explanations fulfill two criteria. First, explanations are class discriminative, meaning they mention attributes in an image which are important to i
Externí odkaz:
https://doaj.org/article/69ed6439dccc42589defb07bc3c6e376
Publikováno v:
International Journal of Computer Vision
Consistency regularization is one of the most widely-used techniques for semi-supervised learning (SSL). Generally, the aim is to train a model that is invariant to various data augmentations. In this paper, we revisit this idea and find that enforci
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f4f377866218e4ddecdf654abfc45b3b
https://hdl.handle.net/21.11116/0000-000C-73A9-421.11116/0000-000C-73AB-2
https://hdl.handle.net/21.11116/0000-000C-73A9-421.11116/0000-000C-73AB-2
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031250682
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9a5a81fba62a0ce39545ac143d32807f
https://doi.org/10.1007/978-3-031-25069-9_5
https://doi.org/10.1007/978-3-031-25069-9_5
Publikováno v:
GCPR
International Journal of Computer Vision
Pattern Recognition
International Journal of Computer Vision
Pattern Recognition
Today’s deep learning systems deliver high performance based on end-to-end training but are notoriously hard to inspect. We argue that there are at least two reasons making inspectability challenging: (i) representations are distributed across hund
Publikováno v:
International Journal of Computer Vision. 129:3154-3168
Person detection and Re-identification are two well-defined support tasks for practically relevant tasks such as Person Search and Multiple Person Tracking. Person Search aims to find and locate all instances with the same identity as the query perso
Autor:
Yongqin Xian, Julian Chibane, Bharat Lal Bhatnagar, Bernt Schiele, Zeynep Akata, Gerard Pons-Moll
Publikováno v:
2022 International Conference on 3D Vision (3DV).
Publikováno v:
IEEE/CVF Conference on Computer Vision and Pattern Recognition
Human-annotated attributes serve as powerful semantic embeddings in zero-shot learning. However, their annotation process is labor-intensive and needs expert supervision. Current unsupervised semantic embeddings, i.e., word embeddings, enable knowled
Publikováno v:
IEEE/CVF Conference on Computer Vision and Pattern Recognition
Deep neural networks are very successful on many vision tasks, but hard to interpret due to their black box nature. To overcome this, various post-hoc attribution methods have been proposed to identify image regions most influential to the models' de
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::527a908c8ba84e253cc14b00c6e2e150
http://arxiv.org/abs/2205.10435
http://arxiv.org/abs/2205.10435
Publikováno v:
Pattern Recognition. 134:109068