8 papers
A Subjective Study on a New Sharpness Informed Class of Metrics
Uditangshu Aurangabadkar, Vibhoothi Vibhoothi, Darren Ramsook +1
Perceptual loss functions in Deep Neural Network (DNN) deblurring architectures improve the overall quality of restored images. However, few focus on explicitly targeting sharpness…
Using Lower-Bound Representations for Trajectory Similarity Learning
Liwei Deng, Haotian Meng, Yupu Zhang +4
Trajectory similarity learning is fundamental to efficient trajectory retrieval under complex distance measures. Existing learning-based methods typically rely on embeddings traine…
Energy-Efficient Autonomous Driving with Adaptive Perception and Robust Decision
Yuyang Xia, Zibo Liang, Liwei Deng +3
Autonomous driving is an emerging technology that is expected to bring significant social, economic, and environmental benefits. However, these benefits come with rising energy con…
Unraveling Spatio-Temporal Foundation Models via the Pipeline Lens: A Comprehensive Review
Yuchen Fang, Hao Miao, Yuxuan Liang +9
Spatio-temporal deep learning models aims to utilize useful patterns in such data to support tasks like prediction. However, previous deep learning models designed for specific tas…
LIRA: A Learning-based Query-aware Partition Framework for Large-scale ANN Search
Ximu Zeng, Liwei Deng, Penghao Chen +3
Approximate nearest neighbor search is fundamental in information retrieval. Previous partition-based methods enhance search efficiency by probing partial partitions, yet they face…
Efficient Large-Scale Traffic Forecasting with Transformers: A Spatial Data Management Perspective
Yuchen Fang, Yuxuan Liang, Bo Hui +5
Road traffic forecasting is crucial in real-world intelligent transportation scenarios like traffic dispatching and path planning in city management and personal traveling. Spatio-…