ResDNet: Efficient Dense Multi-Scale Representations With Residual Learning for High-Level Vision Tasks.
Sign Up to like & getrecommendations! Published in 2022 at "IEEE transactions on neural networks and learning systems"
DOI: 10.1109/tnnls.2022.3169779
Abstract: Deep feature fusion plays a significant role in the strong learning ability of convolutional neural networks (CNNs) for computer vision tasks. Recently, works continually demonstrate the advantages of efficient aggregation strategy and some of them… read more here.
Keywords: vision tasks; dense; representations residual; high level ... See more keywords
Multi-Dataset, Multitask Learning of Egocentric Vision Tasks.
Sign Up to like & getrecommendations! Published in 2021 at "IEEE transactions on pattern analysis and machine intelligence"
DOI: 10.1109/tpami.2021.3061479
Abstract: For egocentric vision tasks such as action recognition, there is a relative scarcity of labeled data. This increases the risk of overfitting during training. In this paper, we address this issue by introducing a multitask… read more here.
Keywords: multitask; action; egocentric vision; vision tasks ... See more keywords
A Heterogeneous Architecture for the Vision Processing Unit with a Hybrid Deep Neural Network Accelerator
Sign Up to like & getrecommendations! Published in 2022 at "Micromachines"
DOI: 10.3390/mi13020268
Abstract: The vision chip is widely used to acquire and process images. It connects the image sensor directly with the vision processing unit (VPU) to execute the vision tasks. Modern vision tasks mainly consist of image… read more here.
Keywords: vision tasks; deep neural; processing unit; vision processing ... See more keywords