Tao Long
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Tao Long has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Laizhong Cui
Shenzhen University, Shenzhen, China
2 shared publications - Lei Zhang
Shenzhen University
2 shared publications - Cheng Pan
Simon Fraser University, Burnaby, BC, Canada
1 shared publication Cong Zhang
Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, China
1 shared publication- Jiangchuan Liu
Simon Fraser University, Burnaby, Canada
1 shared publication - Liang Zhang
Sun Yat-Sen University, Shenzhen, CHINA
1 shared publication
Latest Publications
- Open Access
- 20 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1924-1935
Generalizing Personalized Federated Graph Augmentation via Min-max Adversarial Learning
- 20 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1924-1935
Open AccessGeneralizing Personalized Federated Graph Augmentation via Min-max Adversarial Learning
- 16 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24 (10) , 10441-10455
Optimizing Mobile-Friendly Viewport Prediction for Live 360-Degree Video Streaming
Viewport prediction is the crucial task for adaptive 360-degree video streaming, as the bitrate control algorithms usually require the knowledge of the user's viewing portions of the frames. Various methods are studied and adopted for viewport prediction from less accurate statistic tools to highly calibrated deep neural networks. Conventionally, it is difficult to implement sophisticated deep learning methods on mobile devices, which have limited computation capability. In this work, we propose an advanced learning-based viewport prediction approach and carefully design it to minimize transmission and computation overhead for mobile terminals. To improve viewport prediction accuracy, we utilize both spatial information through a saliency prediction model and temporal information through a modified LSTM model. Different computations introduced by the neural network models are distributed across the network to keep the computation light on mobile devices. To better adapt to the content dynamics in live streaming, we employ the model-agnostic meta-learning (MAML) method for video saliency prediction. The learned saliency prediction model with optimized initialization via offline meta-training can be fast fine-tuned online using a few samples. We further discuss how to integrate this mobile-friendly viewport prediction (MFVP) approach into a typical 360-degree video live streaming system by formulating and solving the bitrate adaptation problem. Extensive experiment results demonstrate that our approach achieves real-time prediction for live video streaming and surpasses existing methods in prediction accuracy on mobile terminals, which, together with our bitrate adaptation algorithm, significantly improves the streaming QoE from various aspects. Compared to baseline methods, MFVP achieves a 4.7–28.7% improvement in accuracy and demonstrates faster adaptability to dynamic content changes, enabling rapid fine-tuning and adjustment. When integrated into a streaming system and paired with our adaptive bitrate allocation algorithm, MFVP enhances overall video quality by 5.6–12.9% and reduces quality fluctuations by 33.3–50.9%.
- 16 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24 (10) , 10441-10455
Optimizing Mobile-Friendly Viewport Prediction for Live 360-Degree Video Streaming
Viewport prediction is the crucial task for adaptive 360-degree video streaming, as the bitrate control algorithms usually require the knowledge of the user's viewing portions of the frames. Various methods are studied and adopted for viewport prediction from less accurate statistic tools to highly calibrated deep neural networks. Conventionally, it is difficult to implement sophisticated deep learning methods on mobile devices, which have limited computation capability. In this work, we propose an advanced learning-based viewport prediction approach and carefully design it to minimize transmission and computation overhead for mobile terminals. To improve viewport prediction accuracy, we utilize both spatial information through a saliency prediction model and temporal information through a modified LSTM model. Different computations introduced by the neural network models are distributed across the network to keep the computation light on mobile devices. To better adapt to the content dynamics in live streaming, we employ the model-agnostic meta-learning (MAML) method for video saliency prediction. The learned saliency prediction model with optimized initialization via offline meta-training can be fast fine-tuned online using a few samples. We further discuss how to integrate this mobile-friendly viewport prediction (MFVP) approach into a typical 360-degree video live streaming system by formulating and solving the bitrate adaptation problem. Extensive experiment results demonstrate that our approach achieves real-time prediction for live video streaming and surpasses existing methods in prediction accuracy on mobile terminals, which, together with our bitrate adaptation algorithm, significantly improves the streaming QoE from various aspects. Compared to baseline methods, MFVP achieves a 4.7–28.7% improvement in accuracy and demonstrates faster adaptability to dynamic content changes, enabling rapid fine-tuning and adjustment. When integrated into a streaming system and paired with our adaptive bitrate allocation algorithm, MFVP enhances overall video quality by 5.6–12.9% and reduces quality fluctuations by 33.3–50.9%.