1 code implementation • 29 Feb 2024 • Fatih Kamisli, Fabien Racape, Hyomin Choi
Third, variable rate quantization is used also for the hyper latent.
no code implementations • 10 Jan 2023 • Ezgi Ozyilkan, Mateen Ulhaq, Hyomin Choi, Fabien Racape
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 input reconstruction.
no code implementations • 3 Jan 2023 • Hyomin Choi, Fabien Racape, Shahab Hamidi-Rad, Mateen Ulhaq, Simon Feltman
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.
no code implementations • 4 Aug 2022 • Hyomin Choi, Ivan V. Bajić
Video content is watched not only by humans, but increasingly also by machines.
no code implementations • 4 May 2022 • Saeed Ranjbar Alvar, Mateen Ulhaq, Hyomin Choi, Ivan V. Bajić
In this paper, we present a learning-based image compression framework where image denoising and compression are performed jointly.
no code implementations • 30 Dec 2021 • Takehiro Tanaka, Hyomin Choi, Ivan V. Bajić
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.
no code implementations • 18 Jul 2021 • Hyomin Choi, Ivan V. Bajic
The simplest task is assigned to a subset of the latent space (the base layer), while more complicated tasks make use of additional subsets of the latent space, i. e., both the base and enhancement layer(s).
no code implementations • 21 May 2021 • Hyomin Choi, Ivan V. Bajic
We investigate latent-space scalability for multi-task collaborative intelligence, where one of the tasks is object detection and the other is input reconstruction.
no code implementations • 15 May 2021 • Robert A. Cohen, Hyomin Choi, Ivan V. Bajić
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, such as in the cloud.
no code implementations • 12 May 2021 • Robert A. Cohen, Hyomin Choi, Ivan V. Bajić
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 available, such as in the cloud.
no code implementations • 28 Aug 2020 • Junbong Kim, Kwanghee Jeong, Hyomin Choi, and Kisung Seo
Imbalance problems in object detection are one of the key issues that affect the performance greatly.
Ranked #1 on Anomaly Detection on MNIST (using extra training data)
no code implementations • 14 Feb 2020 • Hyomin Choi, Robert A. Cohen, Ivan V. Bajic
Recent AI applications such as Collaborative Intelligence with neural networks involve transferring deep feature tensors between various computing devices.
no code implementations • 31 Dec 2018 • Hyomin Choi, Ivan V. Bajic
We propose a novel frame prediction method using a deep neural network (DNN), with the goal of improving video coding efficiency.
no code implementations • 26 Apr 2018 • Hyomin Choi, Ivan V. Bajic
However, this necessitates sending deep feature data from the mobile to the cloud in order to perform inference.
no code implementations • 12 Feb 2018 • Hyomin Choi, Ivan V. Bajic
Recent studies have shown that the efficiency of deep neural networks in mobile applications can be significantly improved by distributing the computational workload between the mobile device and the cloud.
no code implementations • 30 Oct 2017 • Hyomin Choi, Ivan V. Bajic
In this paper we present a bit allocation and rate control strategy that is tailored to object detection.
no code implementations • 30 Oct 2017 • Saeed Ranjbar Alvar, Hyomin Choi, Ivan V. Bajic
Finding faces in images is one of the most important tasks in computer vision, with applications in biometrics, surveillance, human-computer interaction, and other areas.
no code implementations • 9 Sep 2017 • Saeed Ranjbar Alvar, Hyomin Choi, Ivan V. Bajic
We focus on one of the poster problems of visual analytics -- face detection -- and approach the issue of reducing the computation by asking: Is it possible to detect a face without full image reconstruction from the High Efficiency Video Coding (HEVC) bitstream?