Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Hehe Fan"'
Autor:
Chuanhao Yao, Hehe Fan, Alexander Adogwa, Haifeng Xiong, Ming Yang, Fudong Liu, Zupeng Chen, Yang Lou
Publikováno v:
Resources Chemicals and Materials, Vol 2, Iss 3, Pp 189-207 (2023)
The utilization of fossil fuels has brought unprecedented prosperity and development to human society, but also caused environmental pollution and global warming triggered by excess greenhouse gases emission. For one thing, the excess emission of car
Externí odkaz:
https://doaj.org/article/e3a249614b024207b780ba857ceb721c
Publikováno v:
Intelligent Computing, Vol 2 (2023)
Motion understanding plays an important role in video-based cross-media analysis and multiple knowledge representation learning. This paper discusses physical motion recognition and prediction by deep neural networks (DNNs), such as convolutional neu
Externí odkaz:
https://doaj.org/article/e24b80955c424ded896c5e0c514f7482
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 45:2181-2192
Due to the inherent unorderliness and irregularity of point cloud, points emerge inconsistently across different frames in a point cloud video. To capture the dynamics in point cloud videos, tracking points and limiting temporal modeling range are us
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::972576d3e709af1a831a2ee31b677658
https://doi.org/10.1109/tpami.2022.3161735
https://doi.org/10.1109/tpami.2022.3161735
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 32:275-285
Hand-object interaction plays a very important role when humans manipulate objects. While existing methods focus on improving hand-object recognition with fully automatic methods, human intention has been largely neglected in the recognition process,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::04ec8f24bdaf19707db36b5386751ce5
https://doi.org/10.1109/tcsvt.2021.3058688
https://doi.org/10.1109/tcsvt.2021.3058688
Publikováno v:
IEEE Transactions on Multimedia. 24:668-676
Neighboring frames are more correlated compared to frames from further temporal distances. In this paper, we aim to explore the temporal correlations among neighboring frames and exploit cross-layer multi-scale features for action recognition. We pre
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ac8792508c5f4b1d4de43347ef1916a3
https://doi.org/10.1109/tmm.2021.3057503
https://doi.org/10.1109/tmm.2021.3057503
Publikováno v:
IEEE Transactions on Image Processing. 30:4253-4262
In the few-shot common-localization task, given few support images without bounding box annotations at each episode, the goal is to localize the common object in the query image of unseen categories. The few-shot common-localization task involves com
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7a5095e705ecaf6cf97f10e82318abb2
https://doi.org/10.1109/tip.2021.3070733
https://doi.org/10.1109/tip.2021.3070733
Publikováno v:
IEEE/CVF Conference on Computer Vision and Pattern Recognition
In this paper, we propose an unsupervised domain adaptation method for deep point cloud representation learning. To model the internal structures in target point clouds, we first propose to learn the global representations of unla-beled data by scali
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e3657d104d6b397a8c572027c01a8f00
https://doi.org/10.1109/cvpr52688.2022.00627
https://doi.org/10.1109/cvpr52688.2022.00627
Publikováno v:
ACM Transactions on Multimedia Computing, Communications, and Applications. 16:1-16
In Visual Dialog, an agent has to parse temporal context in the dialog history and spatial context in the image to hold a meaningful dialog with humans. For example, to answer “what is the man on her left wearing?” the agent needs to (1) analyze
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::88b8fdb6f39a3c916ff794f6a6fb322f
https://doi.org/10.1145/3390891
https://doi.org/10.1145/3390891
Publikováno v:
AAAI
This paper focuses on the problem of person tube (a sequence of bounding boxes which encloses a person in a video) retrieval using a natural language query. Different from images in person re-identification (re-ID) or person search, besides appearanc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3cdf7e053650fe04c99242ec8bb8f41a
https://doi.org/10.1609/aaai.v34i07.6704
https://doi.org/10.1609/aaai.v34i07.6704
Publikováno v:
ACM Transactions on Multimedia Computing, Communications, and Applications. 16:1-19
Due to domain bias, directly deploying a deep person re-identification (re-ID) model trained on one dataset often achieves considerably poor accuracy on another dataset. In this paper, we propose an Adaptive Exploration (AE) method to address the dom
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::63cb84f185d3bb9e02a16223036cec4d
https://doi.org/10.1145/3369393
https://doi.org/10.1145/3369393