Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleJuly 2024
Energy-Aware Satellite-Ground Co-Inference via Layer-Wise Processing Schedule Optimization
- Yijie Chen,
- Qiyang Zhang,
- Ruolin Xing,
- Yuanzhe Li,
- Xiao Ma,
- Chaoxin Yu,
- Yiran Zhang,
- Ao Zhou,
- Shangguang Wang
Internetware '24: Proceedings of the 15th Asia-Pacific Symposium on InternetwareJuly 2024, Pages 303–312https://doi.org/10.1145/3671016.3674811Recent advancements in Low Earth Orbit (LEO) satellites are facilitating the provision of Deep Neural Networks (DNNs)-inherent services to achieve ubiquitous coverage via satellite computing. However, the computational demands and energy consumption of ...
- research-articleJuly 2024
Mirrored X-Net: Joint classification and contrastive learning for weakly supervised GA segmentation in SD-OCT
Highlights- The anisotropic downsampling, a novel downsampling baseline, is proposed.
- A novel contrastive learning module is designed to extract negative representations.
- Anomalous probability map can be generated from the contrastive learning ...
Deep learning achieves impressive performance in medical image segmentation, but the training phase requires a large amount of annotated data with precise clinical definitions. Weakly supervised lesion segmentation aims to produce pixel-level ...
- ArticleJune 2024
A Method for Estimating Human Respiratory Rate and Heart Rate Using Sparse Spectrum Analysis
Engineering Psychology and Cognitive ErgonomicsJun 2024, Pages 61–78https://doi.org/10.1007/978-3-031-60728-8_6AbstractMonitoring human health conditions has always been a significant concern, especially in the operational safety industry, such as civil aviation. Traditional contact-based methods can accurately measure human heartbeat and other vital sign ...
- ArticleJune 2024
A Non-contact Vital Signs Retrieving Method for Aviation Safety Personnel Using TVF-EMD
Engineering Psychology and Cognitive ErgonomicsJun 2024, Pages 243–258https://doi.org/10.1007/978-3-031-60731-8_17AbstractConducting real-time monitoring of aviation safety personnel’s vital signs during their duty, like respiration and heart rate, is essential for ensuring the safety of civil aviation operations, especially in promptly detecting fatigue-related ...
- research-articleJune 2024
Large Language Models on Mobile Devices: Measurements, Analysis, and Insights
EdgeFM '24: Proceedings of the Workshop on Edge and Mobile Foundation ModelsJune 2024, Pages 1–6https://doi.org/10.1145/3662006.3662059Deploying large language models (LLMs) inference into mobile devices is cost-efficient for companies, and well addresses the privacy concern of users. However, the limited computation capacity and memory constraints of mobile devices hinder their ...
-
- short-paperJune 2024
Poster: Service Orchestration for Satellite Computing
MOBISYS '24: Proceedings of the 22nd Annual International Conference on Mobile Systems, Applications and ServicesJune 2024, Pages 686–687https://doi.org/10.1145/3643832.3661421Satellite computing is emerging as a promising domain for delivering mobile services that meet stringent Quality of Service (QoS) requirements, such as low latency, to users. However, the inherent mobility of satellites as computing nodes can precipitate ...
- Work in ProgressMay 2024
Beyond ChatBots: ExploreLLM for Structured Thoughts and Personalized Model Responses
- Xiao Ma,
- Swaroop Mishra,
- Ariel Liu,
- Sophie Ying Su,
- Jilin Chen,
- Chinmay Kulkarni,
- Heng-Tze Cheng,
- Quoc Le,
- Ed Chi
CHI EA '24: Extended Abstracts of the 2024 CHI Conference on Human Factors in Computing SystemsMay 2024, Article No.: 56, Pages 1–12https://doi.org/10.1145/3613905.3651093Large language model (LLM) powered chatbots are primarily text-based today, and impose a large interactional cognitive load, especially for exploratory or sensemaking tasks such as planning a trip or learning about a new city. Because the interaction is ...
- ArticleApril 2024
Foreground and Background Separate Adaptive Equilibrium Gradients Loss for Long-Tail Object Detection
AbstractThe current mainstream object detection methods usually tend to implement on datasets where the categories remain balanced, and have made great progress. However, in the presence of long-tail distribution, the performance is still unsatisfactory. ...
- research-articleMay 2024
Efficient diffusion policies for offline reinforcement learning
NIPS '23: Proceedings of the 37th International Conference on Neural Information Processing SystemsDecember 2023, Article No.: 2937, Pages 67195–67212Offline reinforcement learning (RL) aims to learn optimal policies from offline datasets, where the parameterization of policies is crucial but often overlooked. Recently, Diffsuion-QL [37] significantly boosts the performance of offline RL by ...
- research-articleMay 2024
InsActor: instruction-driven physics-based characters
NIPS '23: Proceedings of the 37th International Conference on Neural Information Processing SystemsDecember 2023, Article No.: 2618, Pages 59911–59923Generating animation of physics-based characters with intuitive control has long been a desirable task with numerous applications. However, generating physically simulated animations that reflect high-level human instructions remains a difficult problem ...
- research-articleMay 2024
Mutual information regularized offline reinforcement learning
NIPS '23: Proceedings of the 37th International Conference on Neural Information Processing SystemsDecember 2023, Article No.: 835, Pages 19058–19072The major challenge of offline RL is the distribution shift that appears when out-of-distribution actions are queried, which makes the policy improvement direction biased by extrapolation errors. Most existing methods address this problem by penalizing ...
- research-articleFebruary 2024
Characterization on the thermal field inside IGBT cells during switching based on TCAD modeling and Thermoreflectance imaging
Microelectronics Journal (MICROJ), Volume 142, Issue CDec 2023https://doi.org/10.1016/j.mejo.2023.106016Abstract—Temperature characterization of power semiconductors is a hot topic in power electronics. Nevertheless, the transient temperature field inside an IGBT cell is highly difficult to measure. In this study, we presented a method combining ...
- research-articleMay 2024
Design and Implementation of CSR Based on LoongArch and Interruption Exception Support
IoTAAI '23: Proceedings of the 2023 5th International Conference on Internet of Things, Automation and Artificial IntelligenceNovember 2023, Pages 855–860https://doi.org/10.1145/3653081.3653225Control and Status Register (CSR) is an essential module in the LoongArch architecture CPU. Its primary function is to record the current state of the CPU, handle exceptions/interruptions, and provide the necessary environment for normal instruction ...
- research-articleNovember 2023
On exploring pose estimation as an auxiliary learning task for Visible–Infrared Person Re-identification
AbstractVisible–infrared person re-identification (VI-ReID) has been challenging due to the existence of large discrepancies between visible and infrared modalities. Most pioneering approaches reduce intra-modality variations and inter-...
- research-articleNovember 2023
Financial sentiment classification with fresh and hot public opinions
Computers and Electrical Engineering (CENG), Volume 111, Issue PBNov 2023https://doi.org/10.1016/j.compeleceng.2023.108955AbstractFinancial sentiment analysis aims to extract public opinion about an institution to help financial researchers make better decisions. To predict sentiment more accurately, it is necessary for models to improve their capability to capture long-...
- research-articleApril 2024
Visual Analysis of the Current Research Status in Acupuncture and Moxibustion Academic Thought
ISAIMS '23: Proceedings of the 2023 4th International Symposium on Artificial Intelligence for Medicine ScienceOctober 2023, Pages 1051–1058https://doi.org/10.1145/3644116.3644296This study aims to explore the current research status, hot topics, and development trends in acupuncture and moxibustion academic thought of literature and experience in China over the past 20 years. It provides reference for researchers to ...
- research-articleApril 2024
Design and Implementation of Memory Management Unit for LoongArch Architecture
EITCE '23: Proceedings of the 2023 7th International Conference on Electronic Information Technology and Computer EngineeringOctober 2023, Pages 1447–1452https://doi.org/10.1145/3650400.3650643A memory management unit (MMU) is designed and implemented for a 32-bit LoongArch architecture pipeline CPU using the FPAG platform. A simple yet performance-oriented TLB module is designed and implemented. TLB-related instructions from the LoongArch ...
- ArticleDecember 2023
CBAV-Loss: Crossover and Branch Losses for Artery-Vein Segmentation in OCTA Images
Pattern Recognition and Computer VisionOct 2023, Pages 51–60https://doi.org/10.1007/978-981-99-8558-6_5AbstractObvious errors still exist in the segmentation of artery-vein (AV) in retinal optical coherence tomography angiography (OCTA) images, especially near crossover and branch points. It is believed that these errors occur because the existed ...
- ArticleOctober 2023
Adjustable Robust Transformer for High Myopia Screening in Optical Coherence Tomography
Medical Image Computing and Computer Assisted Intervention – MICCAI 2023Oct 2023, Pages 504–514https://doi.org/10.1007/978-3-031-43904-9_49AbstractMyopia is a manifestation of visual impairment caused by an excessively elongated eyeball. Image data is critical material for studying high myopia and pathological myopia. Measurements of spherical equivalent and axial length are the gold ...
- research-articleOctober 2023
The Beauty of Repetition: An Algorithmic Composition Model With Motif-Level Repetition Generator and Outline-to-Music Generator in Symbolic Music Generation
IEEE Transactions on Multimedia (TOM), Volume 262024, Pages 4320–4333https://doi.org/10.1109/TMM.2023.3321495Most musical compositions utilize repetition as a fundamental element to create captivating aesthetic experiences. However, the potential of repetition in machine-learning-based algorithmic composition has not been thoroughly investigated. This article ...