Zobrazeno 1 - 10
of 15
pro vyhledávání: '"Honghu Pan"'
Publikováno v:
IET Image Processing, Vol 17, Iss 14, Pp 4000-4013 (2023)
Abstract The image‐to‐video (I2V) person re‐identification (Re‐ID) is a cross‐modality pedestrian retrieval task, whose crux is to reduce the large modality discrepancy between images and videos. To this end, this paper proposes to predict
Externí odkaz:
https://doaj.org/article/e93c4d50054b41bda9398177d6b4f2d3
Publikováno v:
Neural Computing and Applications. 35:9463-9479
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d7813bdc64342dbc57b32fc7e9fee785
https://doi.org/10.1007/s00521-023-08362-x
https://doi.org/10.1007/s00521-023-08362-x
Publikováno v:
IEEE Transactions on Information Forensics and Security. 18:2104-2118
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::70fd29b84ab1942e6555c4ee3c87f697
https://doi.org/10.1109/tifs.2023.3254449
https://doi.org/10.1109/tifs.2023.3254449
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 32:2845-2855
The triplet loss is widely used in learning the local descriptors for image matching. However, existing triplet loss-based methods, like HardNet and DSM, employ the point-to-point distance metric, which neglects the neighborhood information of descri
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ece3bfc418e3dc6d3d3893b9a78c1c71
https://doi.org/10.1109/tcsvt.2021.3099846
https://doi.org/10.1109/tcsvt.2021.3099846
Publikováno v:
Virtual Reality. 25:585-596
Escape room is a live-action adventure game, where the players search clues, solve puzzles and achieve the assigned tasks. This paper proposed a novel escape room system combining augmented reality and deep learning technology. The system adopts a cl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d443c9e9821bf8753b1da2c4fbcb9a3d
https://doi.org/10.1007/s10055-020-00476-0
https://doi.org/10.1007/s10055-020-00476-0
The video-based person re-identification (ReID) aims to identify the given pedestrian video sequence across multiple non-overlapping cameras. To aggregate the temporal and spatial features of the video samples, the graph neural networks (GNNs) are in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::72fefb7ac12e0c740b2f9052d6a8907b
Existing methods for video-based person re-identification (ReID) mainly learn the appearance feature of a given pedestrian via a feature extractor and a feature aggregator. However, the appearance models would fail when different pedestrians have sim
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::985abb786fc7ac674fa945ec0b3ed5cd
Publikováno v:
Journal of Mechanical Engineering / Strojniški Vestnik. 2018, Vol. 64 Issue 7/8, p443-452. 10p.
Publikováno v:
Knowledge-Based Systems. 236:107300
Person re-identification (ReID) is an important topic of computer vision. Existing works in this field focus primarily on learning a feature extractor that maps the pedestrian images into a feature space, in which feature vectors corresponding to the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8331cc44a9a44445e024d39282b50674
https://doi.org/10.1016/j.knosys.2021.107300
https://doi.org/10.1016/j.knosys.2021.107300