Aaron Chadha
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Aaron Chadha has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
Yiannis Andreopoulos
3 shared publications- Alhabib Abbas
Department of Electronic & Electrical Engineering University College London London U.K
2 shared publications - Eirina Bourtsoulatze
School of Computer Science and Electronic Engineering (CSEE), University of Essex, Colchester, U.K.
2 shared publications Ilya Fadeev
2 shared publications- Yiannis Andreopoulos
Department of Electronic and Electrical Engineering, University College London, London, U.K.
2 shared publications Matthias Treder
1 shared publication
Latest Publications
- 1 May 2022
- Published by Society of Motion Picture and Television Engineers (SMPTE) in SMPTE Motion Imaging Journal
- Vol. 131 (4) , 39-44
Toward Generalized Psychovisual Preprocessing For Video Encoding
Deep perceptual preprocessing has recently emerged as a new way to enable further bitrate savings across several generations of video encoders without breaking standards or requiring any changes in client devices. In this article, we lay the foundation for a generalized psychovisual preprocessing framework for video encoding and describe one of its promising instantiations that is practically deployable for video-on-demand, live, gaming, and user-generated content (UGC). Results using state-of-the-art advanced video coding (AVC), high efficiency video coding (HEVC), and versatile video coding (VVC) encoders show that average bitrate [Bjontegaard delta-rate (BD-rate)] gains of 11%–17% are obtained over three state-of-the-art reference-based quality metrics [Netflix video multi-method assessment fusion (VMAF), structural similarity index (SSIM), and Apple advanced video quality tool (AVQT)], as well as the recently proposed nonreference International Telecommunication Union-Telecommunication?(ITU-T) P.1204 metric. The proposed framework on CPU is shown to be twice faster than $\times 264$ medium-preset encoding. On GPU hardware, our approach achieves 714 frames/sec for 1080p video (below 2 ms/frame), thereby enabling its use in very-low-latency live video or game streaming applications.
- 1 May 2022
- Published by Society of Motion Picture and Television Engineers (SMPTE) in SMPTE Motion Imaging Journal
- Vol. 131 (4) , 39-44
Toward Generalized Psychovisual Preprocessing For Video Encoding
Deep perceptual preprocessing has recently emerged as a new way to enable further bitrate savings across several generations of video encoders without breaking standards or requiring any changes in client devices. In this article, we lay the foundation for a generalized psychovisual preprocessing framework for video encoding and describe one of its promising instantiations that is practically deployable for video-on-demand, live, gaming, and user-generated content (UGC). Results using state-of-the-art advanced video coding (AVC), high efficiency video coding (HEVC), and versatile video coding (VVC) encoders show that average bitrate [Bjontegaard delta-rate (BD-rate)] gains of 11%–17% are obtained over three state-of-the-art reference-based quality metrics [Netflix video multi-method assessment fusion (VMAF), structural similarity index (SSIM), and Apple advanced video quality tool (AVQT)], as well as the recently proposed nonreference International Telecommunication Union-Telecommunication?(ITU-T) P.1204 metric. The proposed framework on CPU is shown to be twice faster than $\times 264$ medium-preset encoding. On GPU hardware, our approach achieves 714 frames/sec for 1080p video (below 2 ms/frame), thereby enabling its use in very-low-latency live video or game streaming applications.
- 17 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 29 (10577149) , 9084-9098
Graph-Based Spatio-Temporal Feature Learning for Neuromorphic Vision Sensing
Neuromorphic vision sensing (NVS) devices represent visual information as sequences of asynchronous discrete events (a.k.a., “spikes”) in response to changes in scene reflectance. Unlike conventional active pixel sensing (APS), NVS allows for significantly higher event sampling rates at substantially increased energy efficiency and robustness to illumination changes. However, feature representation for NVS is far behind its APS-based counterparts, resulting in lower performance in high-level computer vision tasks. To fully utilize its sparse and asynchronous nature, we propose a compact graph representation for NVS, which allows for end-to-end learning with graph convolution neural networks. We couple this with a novel end-to-end feature learning framework that accommodates both appearancebased and motion-based tasks. The core of our framework comprises a spatial feature learning module, which utilizes residual-graph convolutional neural networks (RG-CNN), for end-to-end learning of appearance-based features directly from graphs. We extend this with our proposed Graph2Grid block and temporal feature learning module for efficiently modelling temporal dependencies over multiple graphs and a long temporal extent. We show how our framework can be configured for object classification, action recognition and action similarity labeling. Importantly, our approach preserves the spatial and temporal coherence of spike events, while requiring less computation and memory. The experimental validation shows that our proposed framework outperforms all recent methods on standard datasets. Finally, to address the absence of large real-world NVS datasets for complex recognition tasks, we introduce, evaluate and make available the American Sign Language letters (ASL-DVS), as well as human action dataset (UCF101-DVS, HMDB51-DVS and ASLAN-DVS).
- 17 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 29 (10577149) , 9084-9098
Graph-Based Spatio-Temporal Feature Learning for Neuromorphic Vision Sensing
Neuromorphic vision sensing (NVS) devices represent visual information as sequences of asynchronous discrete events (a.k.a., “spikes”) in response to changes in scene reflectance. Unlike conventional active pixel sensing (APS), NVS allows for significantly higher event sampling rates at substantially increased energy efficiency and robustness to illumination changes. However, feature representation for NVS is far behind its APS-based counterparts, resulting in lower performance in high-level computer vision tasks. To fully utilize its sparse and asynchronous nature, we propose a compact graph representation for NVS, which allows for end-to-end learning with graph convolution neural networks. We couple this with a novel end-to-end feature learning framework that accommodates both appearancebased and motion-based tasks. The core of our framework comprises a spatial feature learning module, which utilizes residual-graph convolutional neural networks (RG-CNN), for end-to-end learning of appearance-based features directly from graphs. We extend this with our proposed Graph2Grid block and temporal feature learning module for efficiently modelling temporal dependencies over multiple graphs and a long temporal extent. We show how our framework can be configured for object classification, action recognition and action similarity labeling. Importantly, our approach preserves the spatial and temporal coherence of spike events, while requiring less computation and memory. The experimental validation shows that our proposed framework outperforms all recent methods on standard datasets. Finally, to address the absence of large real-world NVS datasets for complex recognition tasks, we introduce, evaluate and make available the American Sign Language letters (ASL-DVS), as well as human action dataset (UCF101-DVS, HMDB51-DVS and ASLAN-DVS).
- 16 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 30 (12) , 4913-4928
Deep Video Precoding
Several groups worldwide are currently investigating how deep learning may advance the state-of-the-art in image and video coding. An open question is how to make deep neural networks work in conjunction with existing (and upcoming) video codecs, such as MPEG H.264/AVC, H.265/HEVC, VVC, Google VP9 and AOMedia AV1, AV2, as well as existing container and transport formats, without imposing any changes at the client side. Such compatibility is a crucial aspect when it comes to practical deployment, especially when considering the fact that the video content industry and hardware manufacturers are expected to remain committed to supporting these standards for the foreseeable future. We propose to use deep neural networks as precoders for current and future video codecs and adaptive video streaming systems. In our current design, the core precoding component comprises a cascaded structure of downscaling neural networks that operates during video encoding, prior to transmission. This is coupled with a precoding mode selection algorithm for each independently-decodable stream segment, which adjusts the downscaling factor according to scene characteristics, the utilized encoder, and the desired bitrate and encoding configuration. Our framework is compatible with all current and future codec and transport standards, as our deep precoding network structure is trained in conjunction with linear upscaling filters (e.g., the bilinear filter), which are supported by all web video players. Extensive evaluation on FHD (1080p) and UHD (2160p) content and with widely-used H.264/AVC, H.265/HEVC and VP9 encoders, as well as a preliminary evaluation with the current test model of VVC (v.6.2rc1), shows that coupling such standards with the proposed deep video precoding allows for 8% to 52% rate reduction under encoding configurations and bitrates suitable for video-on-demand adaptive streaming systems. The use of precoding can also lead to encoding complexity reduction, which is essential for cost-effective cloud deployment of complex encoders like H.265/HEVC, VP9 and VVC, especially when considering the prominence of high-resolution adaptive video streaming.
- 16 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 30 (12) , 4913-4928
Deep Video Precoding
Several groups worldwide are currently investigating how deep learning may advance the state-of-the-art in image and video coding. An open question is how to make deep neural networks work in conjunction with existing (and upcoming) video codecs, such as MPEG H.264/AVC, H.265/HEVC, VVC, Google VP9 and AOMedia AV1, AV2, as well as existing container and transport formats, without imposing any changes at the client side. Such compatibility is a crucial aspect when it comes to practical deployment, especially when considering the fact that the video content industry and hardware manufacturers are expected to remain committed to supporting these standards for the foreseeable future. We propose to use deep neural networks as precoders for current and future video codecs and adaptive video streaming systems. In our current design, the core precoding component comprises a cascaded structure of downscaling neural networks that operates during video encoding, prior to transmission. This is coupled with a precoding mode selection algorithm for each independently-decodable stream segment, which adjusts the downscaling factor according to scene characteristics, the utilized encoder, and the desired bitrate and encoding configuration. Our framework is compatible with all current and future codec and transport standards, as our deep precoding network structure is trained in conjunction with linear upscaling filters (e.g., the bilinear filter), which are supported by all web video players. Extensive evaluation on FHD (1080p) and UHD (2160p) content and with widely-used H.264/AVC, H.265/HEVC and VP9 encoders, as well as a preliminary evaluation with the current test model of VVC (v.6.2rc1), shows that coupling such standards with the proposed deep video precoding allows for 8% to 52% rate reduction under encoding configurations and bitrates suitable for video-on-demand adaptive streaming systems. The use of precoding can also lead to encoding complexity reduction, which is essential for cost-effective cloud deployment of complex encoders like H.265/HEVC, VP9 and VVC, especially when considering the prominence of high-resolution adaptive video streaming.
- 6 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 29 (10577149) , 2622-2637
Improved Techniques for Adversarial Discriminative Domain Adaptation
Adversarial discriminative domain adaptation (ADDA) is an efficient framework for unsupervised domain adaptation in image classification, where the source and target domains are assumed to have the same classes, but no labels are available for the target domain. While ADDA has already achieved better training efficiency and competitive accuracy on image classification in comparison to other adversarial based methods, we investigate whether we can improve its performance with a new framework and new loss formulations. Following the framework of semi-supervised GANs, we first extend the discriminator output over the source classes, in order to model the joint distribution over domain and task. We thus leverage on the distribution over the source encoder posteriors (which is fixed during adversarial training) and propose maximum mean discrepancy (MMD) and reconstruction-based loss functions for aligning the target encoder distribution to the source domain. We compare and provide a comprehensive analysis of how our framework and loss formulations extend over simple multi-class extensions of ADDA and other discriminative variants of semi-supervised GANs. In addition, we introduce various forms of regularization for stabilizing training, including treating the discriminator as a denoising autoencoder and regularizing the target encoder with source examples to reduce overfitting under a contraction mapping (i.e., when the target per-class distributions are contracting during alignment with the source). Finally, we validate our framework on standard datasets like MNIST, USPS, SVHN, MNIST-M and Office-31. We additionally examine how the proposed framework benefits recognition problems based on sensing modalities that lack training data. This is realized by introducing and evaluating on a neuromorphic vision sensing (NVS) sign language recognition dataset, where the source domain constitutes emulated neuromorphic spike events converted from conventional pixel-based video and the target domain is experimental (real) spike events from an NVS camera. Our results on all datasets show that our proposal is both simple and efficient, as it competes or outperforms the state-of-the-art in unsupervised domain adaptation, such as DIFA and MCDDA, whilst offering lower complexity than other recent adversarial methods.
- 6 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 29 (10577149) , 2622-2637
Improved Techniques for Adversarial Discriminative Domain Adaptation
Adversarial discriminative domain adaptation (ADDA) is an efficient framework for unsupervised domain adaptation in image classification, where the source and target domains are assumed to have the same classes, but no labels are available for the target domain. While ADDA has already achieved better training efficiency and competitive accuracy on image classification in comparison to other adversarial based methods, we investigate whether we can improve its performance with a new framework and new loss formulations. Following the framework of semi-supervised GANs, we first extend the discriminator output over the source classes, in order to model the joint distribution over domain and task. We thus leverage on the distribution over the source encoder posteriors (which is fixed during adversarial training) and propose maximum mean discrepancy (MMD) and reconstruction-based loss functions for aligning the target encoder distribution to the source domain. We compare and provide a comprehensive analysis of how our framework and loss formulations extend over simple multi-class extensions of ADDA and other discriminative variants of semi-supervised GANs. In addition, we introduce various forms of regularization for stabilizing training, including treating the discriminator as a denoising autoencoder and regularizing the target encoder with source examples to reduce overfitting under a contraction mapping (i.e., when the target per-class distributions are contracting during alignment with the source). Finally, we validate our framework on standard datasets like MNIST, USPS, SVHN, MNIST-M and Office-31. We additionally examine how the proposed framework benefits recognition problems based on sensing modalities that lack training data. This is realized by introducing and evaluating on a neuromorphic vision sensing (NVS) sign language recognition dataset, where the source domain constitutes emulated neuromorphic spike events converted from conventional pixel-based video and the target domain is experimental (real) spike events from an NVS camera. Our results on all datasets show that our proposal is both simple and efficient, as it competes or outperforms the state-of-the-art in unsupervised domain adaptation, such as DIFA and MCDDA, whilst offering lower complexity than other recent adversarial methods.
- 18 December 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 30 (1) , 145-154
Rate-Accuracy Trade-Off in Video Classification With Deep Convolutional Neural Networks
- 18 December 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 30 (1) , 145-154
Rate-Accuracy Trade-Off in Video Classification With Deep Convolutional Neural Networks