Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Dae Ung Jo"'
Publikováno v:
IEEE Access, Vol 10, Pp 8462-8473 (2022)
Deep learning-based crowd density estimation can greatly improve the accuracy of crowd counting. Though a Bayesian loss method resolves the two problems of the need of a hand-crafted ground truth (GT) density and noisy annotations, counting accuratel
Externí odkaz:
https://doaj.org/article/633f8ecbfcd74499ac9377b3d1aeb697
Publikováno v:
IEEE Access, Vol 10, Pp 34677-34689 (2022)
Most pool-based active learning studies have focused on query strategy for active learning. In this paper, via empirical analysis on the effect of passive learning before starting active learning, we reveal that the amount of data acquired by passive
Externí odkaz:
https://doaj.org/article/9ffea871e71a4383aba41f542386eae4
Publikováno v:
AAAI
In this paper, we propose a novel structure for a multi-modal data association referred to as Associative Variational Auto-Encoder (AVAE). In contrast to the existing models using a shared latent space among modalities, our structure adopts distribut
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::867847b3c36a63b98cf3b85dae2522f6
https://doi.org/10.1609/aaai.v34i07.6778
https://doi.org/10.1609/aaai.v34i07.6778
Publikováno v:
AAAI
In person re-identification (ReID) task, because of its shortage of trainable dataset, it is common to utilize fine-tuning method using a classification network pre-trained on a large dataset. However, it is relatively difficult to sufficiently fine-
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::34763ae34a0053fafd466a94eb0b1216
Publikováno v:
2017 17th International Conference on Control, Automation and Systems (ICCAS).
This paper proposes a real-time multi-camera system that solves three-dimensional localizing and tracking of people. Unlike the existing multi-camera system, the proposed system is designed to achieve real-time performance and operate in an online ma
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4850ea10ca5d9adde4ef9bad56733356
https://doi.org/10.23919/iccas.2017.8204448
https://doi.org/10.23919/iccas.2017.8204448