% Hadi Amirpourazarian
% Encoding: utf-8
@InProceedings{Menon2021,
  author = {Vignesh Menon and Hadi Amirpourazarian and Christian Timmerer and Mohammad Ghanbari},
  booktitle = {2021 Picture Coding Symposium (PCS)},
  title = {{Efficient Multi-Encoding Algorithms for HTTP Adaptive Bitrate Streaming}},
  year = {2021},
  month = jun,
  pages = {1--5},
  publisher = {IEEE},
  abstract = {Since video accounts for the majority of today’s internet traffic, the popularity of HTTP Adaptive Streaming (HAS) is increasing steadily. In HAS, each video is encoded at multiple bitrates and spatial resolutions (i.e., representations) to adapt to a heterogeneity of network conditions, device characteristics, and end-user preferences. Most of the streaming services utilize cloud-based encoding techniques which enable a fully parallel encoding process to speed up the encoding and consequently to reduce the overall time complexity. State-of-the-art approaches further improve the encoding process by utilizing encoder analysis information from already encoded representation(s) to improve the encoding time complexity of the remaining representations. In this paper, we investigate various multi-encoding algorithms (i.e., multi-rate and multi-resolution) and propose novel multi- encoding algorithms for large-scale HTTP Adaptive Streaming deployments. Experimental results demonstrate that the proposed multi-encoding algorithm optimized for the highest compression efficiency reduces the overall encoding time by 39% with a 1.5% bitrate increase compared to stand-alone encodings. Its optimized version for the highest time savings reduces the overall encoding time by 50% with a 2.6% bitrate increase compared to stand-alone encodings.},
  doi = {10.1109/pcs50896.2021.9477499},
  keywords = {HTTP Adaptive Streaming, HEVC, Multi-rate Encoding, Multi-encoding},
  url = {https://ieeexplore.ieee.org/document/9477499}
}
@InProceedings{Amirpourazarian2021a,
  author = {Hadi Amirpourazarian and Christian Timmerer and Mohammad Ghanbari},
  booktitle = {2021 Data Compression Conference (DCC)},
  title = {{SLFC: Scalable Light Field Coding}},
  year = {2021},
  month = {mar},
  pages = {43-52},
  publisher = {IEEE},
  abstract = {Light field imaging enables some post-processing capabilities like refocusing, changing view perspective, and depth estimation. As light field images are represented by multiple views they contain a huge amount of data that makes compression inevitable. Although there are some proposals to efficiently compress light field images, their main focus is on encoding efficiency. However, some important functionalities such as viewpoint and quality scalabilities, random access, and uniform quality distribution have not been addressed adequately. In this paper, an efficient light field image compression method based on a deep neural network is proposed, which classifies multiple views into various layers. In each layer, the target view is synthesized from the available views of previously encoded/decoded layers using a deep neural network. This synthesized view is then used as a virtual reference for the target view inter-coding. In this way, random access to an arbitrary view is provided. Moreover, uniform quality distribution among multiple views is addressed. In higher bitrates where random access to an arbitrary view is more crucial, the required bitrate to access the requested view is minimized.},
  doi = {10.1109/dcc50243.2021.00012},
  keywords = {Light field, Compression, Scalable, Random Access},
  url = {https://ieeexplore.ieee.org/document/9418753}
}
@InProceedings{Amirpourazarian2021,
  author = {Hadi Amirpourazarian and Christian Timmerer and Mohammad Ghanbari},
  booktitle = {2021 IEEE International Conference on Multimedia and Expo (ICME)},
  title = {{PSTR: Per-Title Encoding Using Spatio-Temporal Resolutions}},
  year = {2021},
  month = jun,
  pages = {1--6},
  publisher = {IEEE},
  abstract = {Current per-title encoding schemes encode the same video content (or snippets/subsets thereof) at various bitrates and spatial resolutions to find an optimal bitrate ladder for each video content. Compared to traditional approaches, in which a predefined, content-agnostic ("fit-to-all") encoding ladder is applied to all video contents, per-title encoding can result in (i) a significant decrease of storage and delivery costs and (ii) an increase in the Quality of Experience (QoE). In the current per-title encoding schemes, the bitrate ladder is optimized using only spatial resolutions, while we argue that with the emergence of high framerate videos, this principle can be extended to temporal resolutions as well. In this paper, we improve the per-title encoding for each content using spatio-temporal resolutions. Experimental results show that our proposed approach doubles the performance of bitrate saving by considering both temporal and spatial resolutions compared to considering only spatial resolutions.},
  doi = {10.1109/icme51207.2021.9428247},
  keywords = {Bitrate ladder, per-title encoding, framerate, spatial resolution},
  url = {https://ieeexplore.ieee.org/document/9428247}
}
@InProceedings{Ghamsarian2020,
  author = {Negin Ghamsarian and Hadi Amirpourazarian and Christian Timmerer and Mario Taschwer and Klaus Schöffmann},
  booktitle = {Proceedings of the 28th ACM International Conference on Multimedia},
  title = {{Relevance-Based Compression of Cataract Surgery Videos Using Convolutional Neural Networks}},
  year = {2020},
  month = {oct},
  pages = {3577--3585},
  publisher = {ACM},
  abstract = {Recorded cataract surgery videos play a prominent role in training and investigating the surgery, and enhancing the surgical outcomes. Due to storage limitations in hospitals, however, the recorded cataract surgeries are deleted after a short time and this precious source of information cannot be fully utilized. Lowering the quality to reduce the required storage space is not advisable since the degraded visual quality results in the loss of relevant information that limits the usage of these videos. To address this problem, we propose a relevance-based compression technique consisting of two modules: (i) relevance detection, which uses neural networks for semantic segmentation and classification of the videos to detect relevant spatio-temporal information, and (ii) content-adaptive compression, which restricts the amount of distortion applied to the relevant content while allocating less bitrate to irrelevant content. The proposed relevance-based compression framework is implemented considering five scenarios based on the definition of relevant information from the target audience's perspective. Experimental results demonstrate the capability of the proposed approach in relevance detection. We further show that the proposed approach can achieve high compression efficiency by abstracting substantial redundant information while retaining the high quality of the relevant content.},
  doi = {10.1145/3394171.3413658},
  keywords = {Convolutional Neural Networks, ROI Detection, Video Coding, HEVC, Medical Multimedia},
  url = {https://dl.acm.org/doi/10.1145/3394171.3413658}
}