Zobrazeno 1 - 10
of 48
pro vyhledávání: '"Choi, Hyomin"'
Achieving successful variable bitrate compression with computationally simple algorithms from a single end-to-end learned image or video compression model remains a challenge. Many approaches have been proposed, including conditional auto-encoders, c
Externí odkaz:
http://arxiv.org/abs/2402.18930
As an increasing amount of image and video content will be analyzed by machines, there is demand for a new codec paradigm that is capable of compressing visual input primarily for the purpose of computer vision inference, while secondarily supporting
Externí odkaz:
http://arxiv.org/abs/2301.04183
Spatial frequency analysis and transforms serve a central role in most engineered image and video lossy codecs, but are rarely employed in neural network (NN)-based approaches. We propose a novel NN-based image coding framework that utilizes forward
Externí odkaz:
http://arxiv.org/abs/2301.01290
Autor:
Choi, Hyomin, Bajić, Ivan V.
Video content is watched not only by humans, but increasingly also by machines. For example, machine learning models analyze surveillance video for security and traffic monitoring, search through YouTube videos for inappropriate content, and so on. I
Externí odkaz:
http://arxiv.org/abs/2208.02512
When it comes to image compression in digital cameras, denoising is traditionally performed prior to compression. However, there are applications where image noise may be necessary to demonstrate the trustworthiness of the image, such as court eviden
Externí odkaz:
http://arxiv.org/abs/2205.01874
We present a dataset that contains object annotations with unique object identities (IDs) for the High Efficiency Video Coding (HEVC) v1 Common Test Conditions (CTC) sequences. Ground-truth annotations for 13 sequences were prepared and released as t
Externí odkaz:
http://arxiv.org/abs/2112.14934
Autor:
Choi, Hyomin, Bajic, Ivan V.
At present, and increasingly so in the future, much of the captured visual content will not be seen by humans. Instead, it will be used for automated machine vision analytics and may require occasional human viewing. Examples of such applications inc
Externí odkaz:
http://arxiv.org/abs/2107.08373
Autor:
Choi, Hyomin, Bajic, Ivan V.
We investigate latent-space scalability for multi-task collaborative intelligence, where one of the tasks is object detection and the other is input reconstruction. In our proposed approach, part of the latent space can be selectively decoded to supp
Externí odkaz:
http://arxiv.org/abs/2105.10089
Publikováno v:
IEEE Open Journal of Circuits and Systems, vol. 2, 13 May 2021, pp. 350-362
In collaborative intelligence applications, part of a deep neural network (DNN) is deployed on a lightweight device such as a mobile phone or edge device, and the remaining portion of the DNN is processed where more computing resources are available,
Externí odkaz:
http://arxiv.org/abs/2105.07102
Publikováno v:
2020 IEEE International Conference on Multimedia and Expo (ICME)
In collaborative intelligence applications, part of a deep neural network (DNN) is deployed on a relatively low-complexity device such as a mobile phone or edge device, and the remainder of the DNN is processed where more computing resources are avai
Externí odkaz:
http://arxiv.org/abs/2105.06002