Zobrazeno 1 - 10
of 61
pro vyhledávání: '"Juwei Lu"'
Publikováno v:
EURASIP Journal on Advances in Signal Processing, Vol 2008 (2008)
Externí odkaz:
https://doaj.org/article/3bfbec36fa8c4dc58d77692dc1f47c36
Publikováno v:
2022 IEEE 14th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP).
Learning Causal Representation for Training Cross-Domain Pose Estimator via Generative Interventions
Autor:
Xiheng Zhang, Yongkang Wong, Xiaofei Wu, Juwei Lu, Mohan Kankanhalli, Xiangdong Li, Weidong Geng
Publikováno v:
2021 IEEE/CVF International Conference on Computer Vision (ICCV).
Recent self-supervised video representation learning methods have found significant success by exploring essential properties of videos, e.g. speed, temporal order, etc. This work exploits an essential yet under-explored property of videos, the \text
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::092c05084ec4cdbba0f501bc6ebc2cc9
In this paper, we propose a framework centering around a novel architecture called the Event Decomposition Recomposition Network (EDRNet) to tackle the Audio-Visual Event (AVE) localization problem in the supervised and weakly supervised settings. AV
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::216da4e2e1ce21f240cb34c70d0fcd24
State of the art (SOTA) few-shot learning (FSL) methods suffer significant performance drop in the presence of domain differences between source and target datasets. The strong discrimination ability on the source dataset does not necessarily transla
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9c6b9347f6217640397297827456ba74
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585761
ECCV (30)
ECCV (30)
We propose novel approaches for simultaneously identifying important weights of a convolutional neural network (ConvNet) and providing more attention to the important weights during training. More formally, we identify two characteristics of a weight
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e39039e8190aa3368af0af232be33e8c
https://doi.org/10.1007/978-3-030-58577-8_6
https://doi.org/10.1007/978-3-030-58577-8_6
Autor:
Zhixiang Chi, Jin Tang, Juwei Lu, Konstantinos N. Plataniotis, Rasoul Mohammadi Nasiri, Zheng Liu
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585822
ECCV (27)
ECCV (27)
Recent advances in high refresh rate displays as well as the increased interest in high rate of slow motion and frame up-conversion fuel the demand for efficient and cost-effective multi-frame video interpolation solutions. To that regard, inserting
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b85279596847537e7e6648dd70a071a4
https://doi.org/10.1007/978-3-030-58583-9_7
https://doi.org/10.1007/978-3-030-58583-9_7
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585761
ECCV (30)
ECCV (30)
State-of-the-art approaches to video-based action and gesture recognition often employ two key concepts: First, they employ multistream processing; second, they use an ensemble of convolutional networks. We improve and extend both aspects. First, we
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4146e8535620a2cbe58a7e790d19cbb6
https://doi.org/10.1007/978-3-030-58577-8_3
https://doi.org/10.1007/978-3-030-58577-8_3
Publikováno v:
Multimedia Tools and Applications. 75:9295-9314
Structured scenario photos, referring to the images which capture important events that usually follow specific routines/structures (such as wedding ceremonies, graduation ceremonies, etc.), account for a significant proportion in personal photo coll