LAUSR

About LAUSR
Donate
Contact Us

Follow us:

You are not signed in:

Sign Up!


   Articles with "feature aggregation" as a keyword



Photo from wikipedia

Novel up-scale feature aggregation for object detection in aerial images

Sign Up to like & get
recommendations! Published in 2020 at "Neurocomputing"

DOI: 10.1016/j.neucom.2020.06.011

Abstract: Abstract Object detection is a pivotal task for many unmanned aerial vehicle (UAV) applications. Compared to general scenes, the objects in aerial images are typically much smaller. For this reason, most general object detectors suffer… read more here.

Keywords: object detection; detection; feature; aerial images ... See more keywords
Photo from wikipedia

Rethinking feature aggregation for deep RGB-D salient object detection

Sign Up to like & get
recommendations! Published in 2021 at "Neurocomputing"

DOI: 10.1016/j.neucom.2020.10.079

Abstract: Abstract Two-stream UNet based architectures are widely used in deep RGB-D salient object detection (SOD) models. However, UNet only adopts a top-down decoder network to progressively aggregate high-level features with low-level ones. In this paper,… read more here.

Keywords: rgb salient; aggregation; level; feature aggregation ... See more keywords

Road manhole cover defect detection via multi-scale edge enhancement and feature aggregation pyramid

Sign Up to like & get
recommendations! Published in 2025 at "Scientific Reports"

DOI: 10.1038/s41598-025-95450-8

Abstract: The safety and management efficiency of urban infrastructure are crucial in the urbanization process, and the rapid, precise identification of road manhole covers is essential for ensuring public safety and optimizing maintenance operations. However, the… read more here.

Keywords: detection; feature aggregation; edge; road manhole ... See more keywords

DSFA-PINN: Deep Spectral Feature Aggregation Physics Informed Neural Network

Sign Up to like & get
recommendations! Published in 2022 at "IEEE Access"

DOI: 10.1109/access.2022.3153056

Abstract: Solving parametric partial differential equations using artificial intelligence is taking the pace. It is primarily because conventional numerical solvers are computationally expensive and require significant time to converge a solution. However, physics informed deep learning… read more here.

Keywords: neural network; spectral feature; physics; physics informed ... See more keywords
Photo from wikipedia

Anchor-Free Feature Aggregation Network for Instrument Detection in Endoscopic Surgery

Sign Up to like & get
recommendations! Published in 2023 at "IEEE Access"

DOI: 10.1109/access.2023.3250400

Abstract: Endoscopic endonasal approach has been widely used for removing various sellae tumors including pituitary adenomas, meningiomas, etc. While, performing these surgeries in such a narrow space with different instruments remains a challenge for surgeons, due… read more here.

Keywords: network; anchor free; feature; detection ... See more keywords

PSFNet: Efficient Detection of SAR Image Based on Petty-Specialized Feature Aggregation

Sign Up to like & get
recommendations! Published in 2024 at "IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"

DOI: 10.1109/jstars.2023.3327344

Abstract: With the rapid development of deep learning, convolutional neural networks have achieved milestones in synthetic aperture radar (SAR) image object detection. However, object detection in SAR images is still a great challenge due to the… read more here.

Keywords: detection; feature; sar image; feature aggregation ... See more keywords

Multiagent Detection System Based on Spatial Adaptive Feature Aggregation

Sign Up to like & get
recommendations! Published in 2024 at "IEEE Systems Journal"

DOI: 10.1109/jsyst.2024.3423752

Abstract: Detection systems based on computer vision play important roles in Large-Scale Multiagent Systems. In particular, it can automatically locate and identify key objects and enhance intelligent collaboration and coordination among multiple agents. However, classification and… read more here.

Keywords: detection; multiagent detection; sdba net; feature aggregation ... See more keywords

Multiview Feature Aggregation for Facade Parsing

Sign Up to like & get
recommendations! Published in 2022 at "IEEE Geoscience and Remote Sensing Letters"

DOI: 10.1109/lgrs.2020.3035721

Abstract: Facade image parsing is essential to the semantic understanding and 3-D reconstruction of urban scenes. Considering the occlusion and appearance ambiguity in single-view images and the easy acquisition of multiple views, in this letter, we… read more here.

Keywords: facade parsing; aggregation; view; multiview ... See more keywords

Bidirectional Feature Aggregation and Adaptive Fusion Network for ALS Point Cloud Semantic Segmentation

Sign Up to like & get
recommendations! Published in 2025 at "IEEE Geoscience and Remote Sensing Letters"

DOI: 10.1109/lgrs.2025.3532795

Abstract: Significant progress has been achieved using deep learning technology for the semantic segmentation of airborne laser scanning (ALS) point clouds. However, there are still challenges in effectively capturing contextual information and fusing network multilevel features… read more here.

Keywords: bidirectional feature; feature aggregation; segmentation; adaptive fusion ... See more keywords

Meta-RangeSeg: LiDAR Sequence Semantic Segmentation Using Multiple Feature Aggregation

Sign Up to like & get
recommendations! Published in 2022 at "IEEE Robotics and Automation Letters"

DOI: 10.1109/lra.2022.3191040

Abstract: LiDAR sensor is essential to the perception system in autonomous vehicles and intelligent robots. To fulfill the real-time requirements in real-world applications, it is necessary to efficiently segment the LiDAR scans. Most of previous approaches… read more here.

Keywords: range; segmentation; meta rangeseg; feature aggregation ... See more keywords

Two-Stream Temporal Feature Aggregation Based on Clustering for Few-Shot Action Recognition

Sign Up to like & get
recommendations! Published in 2024 at "IEEE Signal Processing Letters"

DOI: 10.1109/lsp.2024.3456670

Abstract: The metric learning paradigm has achieved notable success in few-shot action recognition; however, it faces unaddressed challenges. Specifically, (1) limited training data could impede the exploration of temporal action relations, and (2) precision would decline… read more here.

Keywords: feature aggregation; shot action; action recognition; action ... See more keywords