Zobrazeno 1 - 10
of 68
pro vyhledávání: '"Ka-Hou Chan"'
Autor:
Sio‐Kei Im, Ka‐Hou Chan
Publikováno v:
IET Image Processing, Vol 18, Iss 9, Pp 2304-2317 (2024)
Abstract Video captioning aims to identify multiple objects and their behaviours in a video event and generate captions for the current scene. This task aims to generate a detailed description of the current video in real‐time using natural languag
Externí odkaz:
https://doaj.org/article/d478b9ffc5bd4084be9c6c910740f841
Autor:
Sio‐Kei Im, Ka‐Hou Chan
Publikováno v:
IET Image Processing, Vol 18, Iss 3, Pp 722-730 (2024)
Abstract CABAC is the only entropy coding used in Versatile Video Coding (VVC). This is achieved through multiple estimators approach that provide more accurate predictions by considering different estimated probability results, but CABAC coding requ
Externí odkaz:
https://doaj.org/article/764e886280f0432db699be31ad549cf4
Autor:
Ka-Hou Chan, Sio-Kei Im
Publikováno v:
Technologies, Vol 12, Iss 8, p 126 (2024)
Nowadays, video is a common social media in our lives. Video summarisation has become an interesting task for information extraction, where the challenge of high redundancy of key scenes leads to difficulties in retrieving important messages. To addr
Externí odkaz:
https://doaj.org/article/8d4261637000481791864a78f8623abd
Autor:
Ka‐Hou Chan, Sio‐Kei Im
Publikováno v:
Electronics Letters, Vol 60, Iss 1, Pp n/a-n/a (2024)
Abstract Light‐field (LF) images offer the potential to improve feature capture in live scenes from multiple perspectives, and also generate additional normal vectors for performing super‐resolution (SR) image processing. With the benefit of mach
Externí odkaz:
https://doaj.org/article/a530e80e900f4fcab6e65d8a96f355fc
Autor:
Sio-Kei Im, Ka-Hou Chan
Publikováno v:
IEEE Access, Vol 11, Pp 84934-84943 (2023)
Image captions are abstract expressions of content representations using text sentences, helping readers to better understand and analyse information between different media. With the advantage of encoder-decoder neural networks, captions can provide
Externí odkaz:
https://doaj.org/article/9316f0de14fb48eeb0a1d66f10e309e2
Autor:
Sio-Kei Im, Ka-Hou Chan
Publikováno v:
Mathematics, Vol 12, Iss 7, p 997 (2024)
The attention mechanism performs well for the Neural Machine Translation (NMT) task, but heavily depends on the context vectors generated by the attention network to predict target words. This reliance raises the issue of long-term dependencies. Inde
Externí odkaz:
https://doaj.org/article/b301578b177f45e0a8c6f5e2b754e767
Autor:
Ka‐Hou Chan, Sio‐Kei Im
Publikováno v:
IET Image Processing, Vol 16, Iss 12, Pp 3155-3163 (2022)
Abstract This work describes the modification of Context‐based Adaptive Binary Arithmetic Coding (CABAC) using the double bit range estimation in the VVC engine and the consideration of range updates by using eight hypothetical probability estimato
Externí odkaz:
https://doaj.org/article/01fe16cc4a3349b7941d2f1fba8aea6f
Autor:
Sio‐Kei Im, Ka‐Hou Chan
Publikováno v:
Electronics Letters, Vol 59, Iss 7, Pp n/a-n/a (2023)
Abstract Vector Quantization (VQ) is a clustering problem in the fields of signal processing, source coding, information theory etc. Taking advantage of recent advances in the field of deep neural networks, this paper investigates the performance bet
Externí odkaz:
https://doaj.org/article/39ba9fbb2e93437aa234f71c73ad604e
Autor:
Sio‐Kei Im, Ka‐Hou Chan
Publikováno v:
Electronics Letters, Vol 58, Iss 20, Pp 759-761 (2022)
Abstract A propagation model for the CABAC entropy codec for VTM is proposed and analysed in terms of its effective estimation and packing loss. In order to be compatible and implement a next‐generation coding framework, the proposed model is desig
Externí odkaz:
https://doaj.org/article/5ce328b14f7443a6982ae03697ff0bd6
Publikováno v:
Mathematics, Vol 11, Iss 17, p 3685 (2023)
The task of dense video captioning is to generate detailed natural-language descriptions for an original video, which requires deep analysis and mining of semantic captions to identify events in the video. Existing methods typically follow a localisa
Externí odkaz:
https://doaj.org/article/1492f4c1674c4cdfa181c0fb53f66ac3