Leveraging instance-, image-and dataset-level information for weakly supervised instance segmentation
Weakly supervised semantic instance segmentation with only image-level supervision,
instead of relying on expensive pixel-wise masks or bounding box annotations, is an …
instead of relying on expensive pixel-wise masks or bounding box annotations, is an …
The improved image inpainting algorithm via encoder and similarity constraint
Y Chen, L Liu, J Tao, R Xia, Q Zhang, K Yang… - The Visual …, 2021 - Springer
Existing image inpainting algorithms based on neural network models are affected by
structural distortions and blurred textures on visible connectivity. As a result, overfitting and …
structural distortions and blurred textures on visible connectivity. As a result, overfitting and …
Robust visual tracking for UAVs with dynamic feature weight selection
Z An, X Wang, B Li, Z Xiang, B Zhang - Applied Intelligence, 2023 - Springer
The low reliability of feature and tracking box detection remains a problem in visual object
tracking. Currently, most discriminative correlation filter (DCF) trackers integrate multiple …
tracking. Currently, most discriminative correlation filter (DCF) trackers integrate multiple …
Proposalclip: Unsupervised open-category object proposal generation via exploiting clip cues
Object proposal generation is an important and fundamental task in computer vision. In this
paper, we propose ProposalCLIP, a method towards unsupervised open-category object …
paper, we propose ProposalCLIP, a method towards unsupervised open-category object …
DNA: Deeply supervised nonlinear aggregation for salient object detection
Recent progress on salient object detection mainly aims at exploiting how to effectively
integrate multiscale convolutional features in convolutional neural networks (CNNs). Many …
integrate multiscale convolutional features in convolutional neural networks (CNNs). Many …
Pose refinement graph convolutional network for skeleton-based action recognition
With the advances in capturing 2D or 3D skeleton data, skeleton-based action recognition
has received an increasing interest over the last years. As skeleton data is commonly …
has received an increasing interest over the last years. As skeleton data is commonly …
Regularized densely-connected pyramid network for salient instance segmentation
Much of the recent efforts on salient object detection (SOD) have been devoted to producing
accurate saliency maps without being aware of their instance labels. To this end, we …
accurate saliency maps without being aware of their instance labels. To this end, we …
Class-agnostic object detection
Object detection models perform well at localizing and classifying objects that they are
shown during training. However, due to the difficulty and cost associated with creating and …
shown during training. However, due to the difficulty and cost associated with creating and …
[PDF][PDF] A Region-Based Efficient Network for Accurate Object Detection.
Accepted: 27 February 2021 Object detection in images is an important task in image
processing and computer vision. Many approaches are available for object detection. For …
processing and computer vision. Many approaches are available for object detection. For …
A serial attention frame for multi-label waste bottle classification
Featured Application This work is mainly applied to the waste recycling industry, especially
to the waste plastic bottle image classification task. Abstract The multi-label recognition of …
to the waste plastic bottle image classification task. Abstract The multi-label recognition of …