no code implementations • 18 Apr 2024 • Gautham Vinod, Jiangpeng He, Zeman Shao, Fengqing Zhu
Image-based methods to analyze food images have alleviated the user burden and biases associated with traditional methods.
no code implementations • 11 Apr 2024 • Justin Yang, Zhihao Duan, Jiangpeng He, Fengqing Zhu
Therefore, food image classification systems should adapt to and manage data that continuously evolves.
1 code implementation • 6 Apr 2024 • Siddeshwar Raghavan, Jiangpeng He, Fengqing Zhu
A significant challenge in achieving ubiquitous Artificial Intelligence is the limited ability of models to rapidly learn new information in real-world scenarios where data follows long-tailed distributions, all while avoiding forgetting previously acquired knowledge.
2 code implementations • 30 Mar 2024 • Md Adnan Faisal Hossain, Zhihao Duan, Yuning Huang, Fengqing Zhu
By compressing different intermediate features of a pre-trained vision task model, the proposed method can scale the encoding complexity without changing the overall size of the model.
1 code implementation • 27 Mar 2024 • Yichi Zhang, Zhihao Duan, Yuning Huang, Fengqing Zhu
Recent studies reveal a significant theoretical link between variational autoencoders (VAEs) and rate-distortion theory, notably in utilizing VAEs to estimate the theoretical upper bound of the information rate-distortion function of images.
no code implementations • 25 Mar 2024 • Fiona R. Kolbinger, Jiangpeng He, Jinge Ma, Fengqing Zhu
Accurate identification and localization of anatomical structures of varying size and appearance in laparoscopic imaging are necessary to leverage the potential of computer vision techniques for surgical decision support.
no code implementations • 10 Mar 2024 • Justin Yang, Zhihao Duan, Andrew Peng, Yuning Huang, Jiangpeng He, Fengqing Zhu
To this end, we introduce a new framework to incorporate image compression for continual ML including a pre-processing data compression step and an efficient compression rate/algorithm selection method.
1 code implementation • 29 Feb 2024 • Zhihao Duan, Ming Lu, Justin Yang, Jiangpeng He, Zhan Ma, Fengqing Zhu
This paper explores the possibility of extending the capability of pre-trained neural image compressors (e. g., adapting to new data or target bitrates) without breaking backward compatibility, the ability to decode bitstreams encoded by the original model.
no code implementations • 28 Feb 2024 • Jiangpeng He, Fengqing Zhu
Class-Incremental Learning (CIL) trains a model to continually recognize new classes from non-stationary data while retaining learned knowledge.
no code implementations • 21 Jan 2024 • Yichi Zhang, Zhihao Duan, Ming Lu, Dandan Ding, Fengqing Zhu, Zhan Ma
While convolution and self-attention are extensively used in learned image compression (LIC) for transform coding, this paper proposes an alternative called Contextual Clustering based LIC (CLIC) which primarily relies on clustering operations and local attention for correlation characterization and compact representation of an image.
no code implementations • 12 Dec 2023 • Ming Lu, Zhihao Duan, Fengqing Zhu, Zhan Ma
Recently, probabilistic predictive coding that directly models the conditional distribution of latent features across successive frames for temporal redundancy removal has yielded promising results.
no code implementations • 15 Sep 2023 • Xinyue Pan, Jiangpeng He, Fengqing Zhu
Personalized food classification aims to address this problem by training a deep neural network using food images that reflect the consumption pattern of each individual.
1 code implementation • 5 Sep 2023 • Zhihao Duan, Jack Ma, Jiangpeng He, Fengqing Zhu
Recent work has shown that Variational Autoencoders (VAEs) can be used to upper-bound the information rate-distortion (R-D) function of images, i. e., the fundamental limit of lossy image compression.
no code implementations • 1 Sep 2023 • Jack Ma, Jiangpeng He, Fengqing Zhu
Dietary assessment is essential to maintaining a healthy lifestyle.
no code implementations • 1 Sep 2023 • Yue Han, Jiangpeng He, Mridul Gupta, Edward J. Delp, Fengqing Zhu
Image-based dietary assessment serves as an efficient and accurate solution for recording and analyzing nutrition intake using eating occasion images as input.
no code implementations • 3 Aug 2023 • Zeman Shao, Gautham Vinod, Jiangpeng He, Fengqing Zhu
Dietary assessment is a key contributor to monitoring health status.
no code implementations • 25 Jul 2023 • Justin Yang, Peter Bauer, Todd Harris, Changhyung Lee, Hyeon Seok Seo, Jan P Allebach, Fengqing Zhu
Different from many existing works which aim to estimate a visual quality score, we propose a machine learning based classification method to determine whether the visual quality of a scanned raster image at a given resolution setting is acceptable.
no code implementations • 1 Jul 2023 • Jiangpeng He, Luotao Lin, Jack Ma, Heather A. Eicher-Miller, Fengqing Zhu
First, as new foods appear sequentially overtime, a trained model needs to learn the new classes continuously without causing catastrophic forgetting for already learned knowledge of existing food types.
no code implementations • 1 Jul 2023 • Jiangpeng He, Fengqing Zhu
Deep learning based food image classification has enabled more accurate nutrition content analysis for image-based dietary assessment by predicting the types of food in eating occasion images.
no code implementations • 16 Mar 2023 • Andrew Peng, Jiangpeng He, Fengqing Zhu
Food image analysis is the groundwork for image-based dietary assessment, which is the process of monitoring what kinds of food and how much energy is consumed using captured food or eating scene images.
no code implementations • 16 Mar 2023 • WenJin Fu, Yue Han, Jiangpeng He, Sriram Baireddy, Mridul Gupta, Fengqing Zhu
Therefore, we aim to explore the capability and improve the performance of GAN methods for food image generation.
2 code implementations • 16 Feb 2023 • Zhihao Duan, Ming Lu, Jack Ma, Yuning Huang, Zhan Ma, Fengqing Zhu
This paper addresses the problem of lossy image compression, a fundamental problem in image processing and information theory that is involved in many real-world applications.
no code implementations • 19 Jan 2023 • Yue Han, Sri Kalyan Yarlagadda, Tonmoy Ghosh, Fengqing Zhu, Edward Sazonov, Edward J. Delp
In this paper, we propose an approach to pre-process images collected by the AIM imaging sensor by rejecting extremely blurry images to improve the performance of food detection.
1 code implementation • 12 Jan 2023 • Siddeshwar Raghavan, Jiangpeng He, Fengqing Zhu
In this work, we explore OCIL for real-world food image classification by first introducing a probabilistic framework to simulate realistic food consumption scenarios.
1 code implementation • 17 Nov 2022 • Zhihao Duan, Fengqing Zhu
Optimizing computation in an edge-cloud system is an important yet challenging problem.
no code implementations • 26 Oct 2022 • Jiangpeng He, Luotao Lin, Heather Eicher-Miller, Fengqing Zhu
Food classification serves as the basic step of image-based dietary assessment to predict the types of foods in each input image.
2 code implementations • 27 Aug 2022 • Zhihao Duan, Ming Lu, Zhan Ma, Fengqing Zhu
Recent research has shown a strong theoretical connection between variational autoencoders (VAEs) and the rate-distortion theory.
no code implementations • 25 Aug 2022 • Gautham Vinod, Zeman Shao, Fengqing Zhu
In this paper, we propose an "Energy Density Map" which is a pixel-to-pixel mapping from the RGB image to the energy density of the food.
no code implementations • 13 Aug 2022 • Xinyue Pan, Jiangpeng He, Andrew Peng, Fengqing Zhu
Food image classification serves as the foundation of image-based dietary assessment to predict food categories.
1 code implementation • 6 Jul 2022 • Runyu Mao, Chen Bai, Yatong An, Fengqing Zhu, Cheng Lu
To the best of our knowledge, 3DG-STFM is the first student-teacher learning method for the local feature matching task.
no code implementations • 5 Jun 2022 • Zeman Shao, Jiangpeng He, Ya-Yuan Yu, Luotao Lin, Alexandra Cowan, Heather Eicher-Miller, Fengqing Zhu
Food classification is critical to the analysis of nutrients comprising foods reported in dietary assessment.
no code implementations • 12 Apr 2022 • Jiangpeng He, Fengqing Zhu
Our method is evaluated on CIFAR-100 dataset by following the proposed evaluation protocol and we show improved performance compared with existing OOD detection methods under the unsupervised continual learning scenario.
no code implementations • 26 Feb 2022 • Zhihao Duan, Ming Lu, Zhan Ma, Fengqing Zhu
End-to-end learned lossy image coders (LICs), as opposed to hand-crafted image codecs, have shown increasing superiority in terms of the rate-distortion performance.
no code implementations • 11 Feb 2022 • Jiangpeng He, Fengqing Zhu
Targeted for real world scenarios, online continual learning aims to learn new tasks from sequentially available data under the condition that each data is observed only once by the learner.
no code implementations • 17 Oct 2021 • Jiangpeng He, Fengqing Zhu
Continual learning in online scenario aims to learn a sequence of new tasks from data stream using each data only once for training, which is more realistic than in offline mode assuming data from new task are all available.
no code implementations • 5 Oct 2021 • Zeman Shao, Yue Han, Jiangpeng He, Runyu Mao, Janine Wright, Deborah Kerr, Carol Boushey, Fengqing Zhu
Accurate assessment of dietary intake requires improved tools to overcome limitations of current methods including user burden and measurement error.
no code implementations • 6 Sep 2021 • Runyu Mao, Jiangpeng He, Luotao Lin, Zeman Shao, Heather A. Eicher-Miller, Fengqing Zhu
Image-based dietary assessment refers to the process of determining what someone eats and how much energy and nutrients are consumed from visual data.
no code implementations • 6 Sep 2021 • Runyu Mao, Mackenzie Tweardy, Stephan W. Wegerich, Craig J. Goergen, George R. Wodicka, Fengqing Zhu
Therefore, our proposed method can determine the reliability of the raw noisy PPG by considering quality of the corresponding pseudo clean PPG signal.
no code implementations • 15 Aug 2021 • Jiangpeng He, Fengqing Zhu
Food image classification is challenging for real-world applications since existing methods require static datasets for training and are not capable of learning from sequentially available new food images.
no code implementations • 14 Apr 2021 • Jiangpeng He, Fengqing Zhu
Continual learning aims to learn new tasks incrementally using less computation and memory resources instead of retraining the model from scratch whenever new task arrives.
no code implementations • 12 Mar 2021 • Zeman Shao, Shaobo Fang, Runyu Mao, Jiangpeng He, Janine Wright, Deborah Kerr, Carol Jo Boushey, Fengqing Zhu
We aim to estimate food portion size, a property that is strongly related to the presence of food object in 3D space, from single monocular images under real life setting.
no code implementations • 13 Feb 2021 • Sri Kalyan Yarlagadda, Daniel Mas Montserrat, David Guerra, Carol J. Boushey, Deborah A. Kerr, Fengqing Zhu
Our method uses a pair of eating scene images, one before start eating and one after eating is completed.
no code implementations • 9 Feb 2021 • Shengtai Ju, Sneha Mahapatra, Marisa A. Erasmus, Amy R. Reibman, Fengqing Zhu
In this paper, we propose a video analytics system to identify the behavior of turkeys.
no code implementations • 1 Feb 2021 • Jiangpeng He, Runyu Mao, Zeman Shao, Janine L. Wright, Deborah A. Kerr, Carol J. Boushey, Fengqing Zhu
Our end-to-end framework is evaluated on a real life food image dataset collected from a nutrition feeding study.
no code implementations • 6 Dec 2020 • Runyu Mao, Jiangpeng He, Zeman Shao, Sri Kalyan Yarlagadda, Fengqing Zhu
Experimental results demonstrate that our system can significantly improve both classification and recognition performance on 4 publicly available datasets and the new VFN dataset.
no code implementations • 1 Dec 2020 • Ming Lu, Tong Chen, Dandan Ding, Fengqing Zhu, Zhan Ma
Inspired by the facts that retinal cells actually segregate the visual scene into different attributes (e. g., spatial details, temporal motion) for respective neuronal processing, we propose to first decompose the input video into respective spatial texture frames (STF) at its native spatial resolution that preserve the rich spatial details, and the other temporal motion frames (TMF) at a lower spatial resolution that retain the motion smoothness; then compress them together using any popular video coder; and finally synthesize decoded STFs and TMFs for high-fidelity video reconstruction at the same resolution as its native input.
no code implementations • 8 Oct 2020 • Daniel Mas Montserrat, János Horváth, S. K. Yarlagadda, Fengqing Zhu, Edward J. Delp
Satellite imagery is becoming increasingly accessible due to the growing number of orbiting commercial satellites.
no code implementations • 27 Apr 2020 • Jiangpeng He, Zeman Shao, Janine Wright, Deborah Kerr, Carol Boushey, Fengqing Zhu
Deep learning based methods have achieved impressive results in many applications for image-based diet assessment such as food classification and food portion size estimation.
no code implementations • 25 Apr 2020 • Daniel Mas Montserrat, Hanxiang Hao, S. K. Yarlagadda, Sriram Baireddy, Ruiting Shao, János Horváth, Emily Bartusiak, Justin Yang, David Güera, Fengqing Zhu, Edward J. Delp
Altered and manipulated multimedia is increasingly present and widely distributed via social media platforms.
no code implementations • CVPR 2020 • Jiangpeng He, Runyu Mao, Zeman Shao, Fengqing Zhu
Modern deep learning approaches have achieved great success in many vision applications by training a model using all available task-specific data.
no code implementations • 24 Oct 2019 • Sri Kalyan Yarlagadda, Sriram Baireddy, David Güera, Carol J. Boushey, Deborah A. Kerr, Fengqing Zhu
The variation in the number of clusters and images captured by different individual makes this a very challenging problem.
no code implementations • 11 Oct 2019 • Zeman Shao, Runyu Mao, Fengqing Zhu
The web crawler is used to download large sets of online food images based on the given food labels.
no code implementations • 11 Jul 2018 • Sri Kalyan Yarlagadda, Fengqing Zhu
Shadows are common aspect of images and when left undetected can hinder scene understanding and visual processing.
no code implementations • 4 May 2018 • David Güera, Sri Kalyan Yarlagadda, Paolo Bestagini, Fengqing Zhu, Stefano Tubaro, Edward J. Delp
This refers to the problem of detecting which camera model has been used to acquire an image by only exploiting pixel information.
no code implementations • 27 Feb 2018 • Shaobo Fang, Zeman Shao, Runyu Mao, Chichen Fu, Deborah A. Kerr, Carol J. Boushey, Edward J. Delp, Fengqing Zhu
We can then estimate food energy based on the energy distribution.
no code implementations • 8 Feb 2018 • Chichen Fu, Di Chen, Edward J. Delp, Zoe Liu, Fengqing Zhu
There has been a growing interest in using different approaches to improve the coding efficiency of modern video codec in recent years as demand for web-based video consumption increases.