Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- posterAugust 2024
BurstRTC: Harnessing Variable Bit-Rate of RTC through Frame-Bursting Congestion Control
APNet '24: Proceedings of the 8th Asia-Pacific Workshop on NetworkingPages 213–214https://doi.org/10.1145/3663408.3665821The rapid growth of online interactive video applications reflects the increasing popularity of real-time communication (RTC). Despite advancements in network and video technologies, the worse quality of experience (QoE) such as large delay, rebuffering ...
- research-articleOctober 2024
Optimization of Graph Convolutional Network for the Domestic DCU Accelerator
- Shuxin Yang,
- Lingbo Kong,
- Lu Liu,
- Dujuan Zhang,
- Yang Guo,
- Jiandong Shang,
- Tao Wan,
- Qingyang Li,
- Gang Wu,
- Hengliang Guo
AIAHPC '24: Proceedings of the 2024 4th International Conference on Artificial Intelligence, Automation and High Performance ComputingPages 152–157https://doi.org/10.1145/3690931.3690958Graph Convolutional Network (GCN) are a commonly used method in the field of artificial intelligence. Due to the often large scale of graph data, GPUs are commonly used to accelerate GCN. The domestic Deep Computing Unit (DCU) accelerator is a GPU-like ...
- research-articleMay 2024
Optimizing sparse general matrix–matrix multiplication for DCUs
- Hengliang Guo,
- Haolei Wang,
- Wanting Chen,
- Congxiang Zhang,
- Yubo Han,
- Shengguang Zhu,
- Dujuan Zhang,
- Yang Guo,
- Jiandong Shang,
- Tao Wan,
- Qingyang Li,
- Gang Wu
The Journal of Supercomputing (JSCO), Volume 80, Issue 14Pages 20176–20200https://doi.org/10.1007/s11227-024-06234-2AbstractSparse general matrix–matrix multiplication (SpGEMM) is a crucial and complex computational task in many practical applications. Improving the performance of SpGEMM on SIMT processors like modern GPUs is challenging due to the unpredictable ...
- research-articleFebruary 2024
MF-Net: Multi-frequency intrusion detection network for Internet traffic data
AbstractThe rapid growth of Internet technology renders intrusion detection an important research topic in the field of pattern recognition. Considering that traffic data relate to not only temporal information, but also attack frequency, this paper ...
Graphical abstractDisplay Omitted
Highlights- MF-Net captures multiple frequencies features with both long-term and short-term dependencies.
- Both MF-LSTM and MF-Transformer detect network intrusion data with different frequencies.
- MF-Net achieve state-of-the-art performance on ...
Heterogeneous Testing for Coverage Profilers Empowered with Debugging Support
ESEC/FSE 2023: Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software EngineeringPages 670–681https://doi.org/10.1145/3611643.3616340Ensuring the correctness of code coverage profilers is crucial, given the widespread adoption of code coverage for various software engineering tasks. Existing validation techniques, such as differential testing and metamorphic testing, have shown ...
-
- research-articleSeptember 2023
Offline Model-Based Adaptable Policy Learning for Decision-Making in Out-of-Support Regions
IEEE Transactions on Pattern Analysis and Machine Intelligence (ITPM), Volume 45, Issue 12Pages 15260–15274https://doi.org/10.1109/TPAMI.2023.3317131In reinforcement learning, a promising direction to avoid online trial-and-error costs is learning from an offline dataset. Current offline reinforcement learning methods commonly learn in the policy space constrained to in-support regions by the offline ...
- research-articleOctober 2022
DoCam: depth sensing with an optical image stabilization supported RGB camera
MobiCom '22: Proceedings of the 28th Annual International Conference on Mobile Computing And NetworkingPages 405–418https://doi.org/10.1145/3495243.3560523Optical image stabilizers (OIS) are widely used in digital cameras to counteract motion blur caused by camera shakes in capturing videos and photos. In this paper, we sought to expand the applicability of the lens-shift OIS technology for metric depth ...
- research-articleAugust 2022
Human-machine interactive streaming anomaly detection by online self-adaptive forest
Frontiers of Computer Science: Selected Publications from Chinese Universities (FCS), Volume 17, Issue 2https://doi.org/10.1007/s11704-022-1270-yAbstractAnomaly detectors are used to distinguish differences between normal and abnormal data, which are usually implemented by evaluating and ranking the anomaly scores of each instance. A static unsupervised streaming anomaly detector is difficult to ...
- research-articleJune 2024
Offline model-based adaptable policy learning
NIPS '21: Proceedings of the 35th International Conference on Neural Information Processing SystemsArticle No.: 645, Pages 8432–8443In reinforcement learning, a promising direction to avoid online trial-and-error costs is learning from an offline dataset. Current offline reinforcement learning methods commonly learn in the policy space constrained to in-support regions by the offline ...
- research-articleSeptember 2021
Partially observable environment estimation with uplift inference for reinforcement learning based recommendation
Machine Language (MALE), Volume 110, Issue 9Pages 2603–2640https://doi.org/10.1007/s10994-021-05969-wAbstractReinforcement learning (RL) aims at searching the best policy model for decision making, and has been shown powerful for sequential recommendations. The training of the policy by RL, however, is placed in an environment. In many real-world ...
- research-articleMay 2021
Autonomous Decentralized Shape-Based Navigation for Snake Robots in Dense Environments
2021 IEEE International Conference on Robotics and Automation (ICRA)Pages 9276–9282https://doi.org/10.1109/ICRA48506.2021.9561987In this work, we focus on the autonomous navigation of snake robots in densely-cluttered environments, where collisions between the robot and obstacles are frequent, which could happen often in disaster scenarios, underground caves, or grassland/forest ...
- research-articleJanuary 2021
Human-Machine Cooperative Video Anomaly Detection
Proceedings of the ACM on Human-Computer Interaction (PACMHCI), Volume 4, Issue CSCW3Article No.: 274, Pages 1–18https://doi.org/10.1145/3434183It is still a challenge to detect anomalous events in video sequences in the field of computer vision due to heavy object occlusions, varying crowded densities and complex situations. To address this, we propose a novel human-machine cooperative approach ...
- research-articleDecember 2020
Mapping and Taking Stock of the Personal Informatics Literature
- Daniel A. Epstein,
- Clara Caldeira,
- Mayara Costa Figueiredo,
- Xi Lu,
- Lucas M. Silva,
- Lucretia Williams,
- Jong Ho Lee,
- Qingyang Li,
- Simran Ahuja,
- Qiuer Chen,
- Payam Dowlatyari,
- Craig Hilby,
- Sazeda Sultana,
- Elizabeth V. Eikey,
- Yunan Chen
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT), Volume 4, Issue 4Article No.: 126, Pages 1–38https://doi.org/10.1145/3432231The research community on the study and design of systems for personal informatics has grown over the past decade. To take stock of what the topics the field has studied and methods the field has used, we map and label 523 publications from ACM's library,...
- research-articleFebruary 2021
Supporting Caring among Intergenerational Family Members through Family Fitness Tracking
PervasiveHealth '20: Proceedings of the 14th EAI International Conference on Pervasive Computing Technologies for HealthcarePages 1–10https://doi.org/10.1145/3421937.3422018We present results from a qualitative study involving eight intergenerational families (27 participants) to understand how a family tracking intervention can help support care among intergenerational family members. Our findings show that family members ...
- research-articleApril 2020
Hierarchical Adaptive Contextual Bandits for Resource Constraint based Recommendation
Contextual multi-armed bandit (MAB) achieves cutting-edge performance on a variety of problems. When it comes to real-world scenarios such as recommendation system and online advertising, however, it is essential to consider the resource consumption of ...
- abstractNovember 2019
Understanding Enjoyment in VR Games with GameFlow
VRST '19: Proceedings of the 25th ACM Symposium on Virtual Reality Software and TechnologyArticle No.: 96, Pages 1–2https://doi.org/10.1145/3359996.3364800In this paper, we report on a work in progress project that aims to understand affordances and inhibiters of enjoyment in virtual reality (VR) video games. We apply the GameFlow model to review and analyse VR and non-VR versions of the same games to ...
- research-articleJuly 2019
Housing Demand Estimation Based on Express Delivery Data
ACM Transactions on Knowledge Discovery from Data (TKDD), Volume 13, Issue 4Article No.: 43, Pages 1–25https://doi.org/10.1145/3332522Housing demand estimation is an important topic in the field of economic research. It is beneficial and helpful for various applications including real estate market regulation and urban planning, and therefore is crucial for both real estate investors ...
- research-articleJuly 2019
Environment Reconstruction with Hidden Confounders for Reinforcement Learning based Recommendation
KDD '19: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data MiningPages 566–576https://doi.org/10.1145/3292500.3330933Reinforcement learning aims at searching the best policy model for decision making, and has been shown powerful for sequential recommendations. The training of the policy by reinforcement learning, however, is placed in an environment. In many real-...
- ArticleJuly 2019
Long Short-Term Attention
AbstractAttention is an important cognition process of humans, which helps humans concentrate on critical information during their perception and learning. However, although many machine learning models can remember information of data, they have no the ...
- articleMay 2017
Optical proposals for controlled delayed-choice experiment based on weak cross-Kerr nonlinearities
Quantum Information Processing (JQIP), Volume 16, Issue 5Pages 1–12https://doi.org/10.1007/s11128-017-1574-2Employing polarization modes of a photon, we propose two theoretical proposals to exhibit the wave---particle duality of the photon with the assistance of weak cross-Kerr nonlinearities. The first proposal is a classical controlled delayed-choice ...