Sijia Chen
Research Subjects
Sijia Chen has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Bin Song
Xidian University
2 shared publications - Mohsen Guizani
Mohamed bin Zayed University of Artificial Intelligence
2 shared publications - Xiaojiang Du
Stevens Institute of Technology, Hoboken, New Jersey, USA
2 shared publications Bin Song
1 shared publication- Bin Zhu
Department of Business Information Systems, College of Business, Oregon State University, Corvallis, USA
1 shared publication - Chen Yu
School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China
1 shared publication
Latest Publications
- Open Access
An Optimized H.266/VVC Software Decoder On Mobile Platform
As the successor of H.265/HEVC, the new versatile video coding standard (H.266/VVC) can provide up to 50% bitrate saving with the same subjective quality, at the cost of increased decoding complexity. To accelerate the application of the new coding standard, a real-time H.266/VVC software decoder that can support various platforms is implemented, where SIMD technologies, parallelism optimization, and the acceleration strategies based on the characteristics of each coding tool are applied. As the mobile devices have become an essential carrier for video services nowadays, the mentioned optimization efforts are not only implemented for the x86 platform, but more importantly utilized to highly optimize the decoding performance on the ARM platform in this work. The experimental results show that when running on the Apple A14 SoC (iPhone 12pro), the average single-thread decoding speed of the present implementation can achieve 53fps (RA and LB) for full HD (1080p) bitstreams generated by VTM-11.0 reference software using 8bit Common Test Conditions (CTC). When multi-threading is enabled, an average of 32 fps (RA) can be achieved when decoding the 4K bitstreams.
Open AccessAn Optimized H.266/VVC Software Decoder On Mobile Platform
As the successor of H.265/HEVC, the new versatile video coding standard (H.266/VVC) can provide up to 50% bitrate saving with the same subjective quality, at the cost of increased decoding complexity. To accelerate the application of the new coding standard, a real-time H.266/VVC software decoder that can support various platforms is implemented, where SIMD technologies, parallelism optimization, and the acceleration strategies based on the characteristics of each coding tool are applied. As the mobile devices have become an essential carrier for video services nowadays, the mentioned optimization efforts are not only implemented for the x86 platform, but more importantly utilized to highly optimize the decoding performance on the ARM platform in this work. The experimental results show that when running on the Apple A14 SoC (iPhone 12pro), the average single-thread decoding speed of the present implementation can achieve 53fps (RA and LB) for full HD (1080p) bitstreams generated by VTM-11.0 reference software using 8bit Common Test Conditions (CTC). When multi-threading is enabled, an average of 32 fps (RA) can be achieved when decoding the 4K bitstreams.
- 15 January 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 5 (2) , 347-357
Multi-Modal Data Semantic Localization With Relationship Dependencies for Efficient Signal Processing in EH CRNs
Due to spectrum scarcity and energy consumption caused by processing and transmitting multimodal data signals in cognitive radio networks (CRNs), locating key information in the signal for further energy management in EH CRNs is necessary. Therefore, to adaptively capture semantic associations of multimedia signals, we present a novel visual-semantic reasoning framework for phrases simultaneously localization. To address the preferences limitations of current algorithms caused by the independent localizing of phrases and the ignorance of inter-phrase dependencies, our framework models the phrases simultaneously followed by inter-phrase dependencies-based jointly localization. Specifically, the framework consists two core modules, including spatialsemantic perception tensor factorization and visual-semantic relationship reasoning network which can be donated as SSPTF and VSRN respectively. That is, SSPTF integrates regions and phrases into a tensor so that tensor factorization can be used to capture a shared potential association for all phrases. Furthermore, based on the predefined phrasessemantic dependencies graph, VSRN explicitly exploits the conjunctions between phrases to refine the phrase-region matching scores from SSPTF to achieve jointly localization. By constructing it as an end-to-end training architecture, the strong performance of the framework over Flicker-Entities30K on accuracy and the state-of-art results on some categories demonstrate the effectiveness of the proposed unified framework.
- 15 January 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 5 (2) , 347-357
Multi-Modal Data Semantic Localization With Relationship Dependencies for Efficient Signal Processing in EH CRNs
Due to spectrum scarcity and energy consumption caused by processing and transmitting multimodal data signals in cognitive radio networks (CRNs), locating key information in the signal for further energy management in EH CRNs is necessary. Therefore, to adaptively capture semantic associations of multimedia signals, we present a novel visual-semantic reasoning framework for phrases simultaneously localization. To address the preferences limitations of current algorithms caused by the independent localizing of phrases and the ignorance of inter-phrase dependencies, our framework models the phrases simultaneously followed by inter-phrase dependencies-based jointly localization. Specifically, the framework consists two core modules, including spatialsemantic perception tensor factorization and visual-semantic relationship reasoning network which can be donated as SSPTF and VSRN respectively. That is, SSPTF integrates regions and phrases into a tensor so that tensor factorization can be used to capture a shared potential association for all phrases. Furthermore, based on the predefined phrasessemantic dependencies graph, VSRN explicitly exploits the conjunctions between phrases to refine the phrase-region matching scores from SSPTF to achieve jointly localization. By constructing it as an end-to-end training architecture, the strong performance of the framework over Flicker-Entities30K on accuracy and the state-of-art results on some categories demonstrate the effectiveness of the proposed unified framework.
- 1 October 2018
- Published by Elsevier in Computer Networks
- Vol. 143, 98-111
FPAN: Fine-grained and progressive attention localization network for data retrieval
- 1 October 2018
- Published by Elsevier in Computer Networks
- Vol. 143, 98-111
FPAN: Fine-grained and progressive attention localization network for data retrieval
- Open Access
FPAN: Fine-grained and Progressive Attention Localization Network for Data Retrieval
The Localization of the target object for data retrieval is a key issue in the Intelligent and Connected Transportation Systems (ICTS). However, due to lack of intelligence in the traditional transportation system, it can take tremendous resources to manually retrieve and locate the queried objects among a large number of images. In order to solve this issue, we propose an effective method to query-based object localization that uses artificial intelligence techniques to automatically locate the queried object in the complex background. The presented method is termed as Fine-grained and Progressive Attention Localization Network (FPAN), which uses an image and a queried object as input to accurately locate the target object in the image. Specifically, the fine-grained attention module is naturally embedded into each layer of the convolution neural network (CNN), thereby gradually suppressing the regions that are irrelevant to the queried object and eventually shrinking attention to the target area. We further employ top-down attentions fusion algorithm operated by a learnable cascade up-sampling structure to establish the connection between the attention map and the exact location of the queried object in the original image. Furthermore, the FPAN is trained by multi-task learning with box segmentation loss and cosine loss. At last, we conduct comprehensive experiments on both queried-based digit localization and object tracking with synthetic and benchmark datasets, respectively. The experimental results show that our algorithm is far superior to other algorithms in the synthesis datasets and outperforms most existing trackers on the OTB and VOT datasets.
Open AccessFPAN: Fine-grained and Progressive Attention Localization Network for Data Retrieval
The Localization of the target object for data retrieval is a key issue in the Intelligent and Connected Transportation Systems (ICTS). However, due to lack of intelligence in the traditional transportation system, it can take tremendous resources to manually retrieve and locate the queried objects among a large number of images. In order to solve this issue, we propose an effective method to query-based object localization that uses artificial intelligence techniques to automatically locate the queried object in the complex background. The presented method is termed as Fine-grained and Progressive Attention Localization Network (FPAN), which uses an image and a queried object as input to accurately locate the target object in the image. Specifically, the fine-grained attention module is naturally embedded into each layer of the convolution neural network (CNN), thereby gradually suppressing the regions that are irrelevant to the queried object and eventually shrinking attention to the target area. We further employ top-down attentions fusion algorithm operated by a learnable cascade up-sampling structure to establish the connection between the attention map and the exact location of the queried object in the original image. Furthermore, the FPAN is trained by multi-task learning with box segmentation loss and cosine loss. At last, we conduct comprehensive experiments on both queried-based digit localization and object tracking with synthetic and benchmark datasets, respectively. The experimental results show that our algorithm is far superior to other algorithms in the synthesis datasets and outperforms most existing trackers on the OTB and VOT datasets.