Results 1 to 10 of about 9,227 (304)
Scene Graph Prediction with Limited Labels [PDF]
2019 IEEE/CVF International Conference on Computer Vision (ICCV), 2019 Visual knowledge bases such as Visual Genome power numerous applications in computer vision, including visual question answering and captioning, but suffer from sparse, incomplete relationships. All scene graph models to date are limited to training on a small set of visual relationships that have thousands of training labels each.
Chen, Vincent S. +5 more
openalex +6 more sources
Learning Hierarchical Features for Scene Labeling [PDF]
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013 Scene labeling consists of labeling each pixel in an image with the category of the object it belongs to. We propose a method that uses a multiscale convolutional network trained from raw pixels to extract dense feature vectors that encode regions of multiple sizes centered on each pixel.
Clement Farabet +2 more
exaly +4 more sources
Scene classification based on semantic labeling [PDF]
Advanced Robotics, 2016 This work was supported by the Ministerio de Economia y Competitividad of the Spanish Government, supported with Feder funds [grant number DPI2013-40534-R], [grant number TIN2015-65686-C5-3-R]; Consejería de Educación, Cultura y Deportes of the JCCM regional government under project PPII-2014-015-P.
JOSÉ CARLOS Rangel +2 more
exaly +5 more sources
Stacked Learning to Search for Scene Labeling
IEEE Transactions on Image Processing, 2017 Search-based structured prediction methods have shown promising successes in both computer vision and natural language processing recently. However, most existing search-based approaches lead to a complex multi-stage learning process, which is ill-suited for scene labeling problems with a high-dimensional output space. In this paper, a stacked learning
Feiyang Cheng, Xuming He, Hong Zhang
exaly +4 more sources
Fast scene labeling via structural inference
Neurocomputing, 2021 Abstract Scene labeling or parsing aims to assign pixelwise semantic labels for an input image. Existing CNN-based models cannot leverage the label dependencies, while RNN-based models predict labels within the local context. In this paper, we propose a fast LSTM scene labeling network via structural inference.
Huaidong Zhang +2 more
exaly +3 more sources
Deep contextual recurrent residual networks for scene labeling [PDF]
Pattern Recognition, 2018 Designed as extremely deep architectures, deep residual networks which provide a rich visual representation and offer robust convergence behaviors have recently achieved exceptional performance in numerous computer vision problems. Being directly applied to a scene labeling problem, however, they were limited to capture long-range contextual dependence,
Ngan Le, Chi Nhan Duong, Ligong Han
exaly +3 more sources
LICS: Locating Inter-Character Spaces for Multilingual Scene Text Detection. [PDF]
Sensors (Basel)Scene text detection in multilingual environments poses significant challenges. Traditional detection methods often struggle with language-specific features and require extensive annotated training data for each language, making them less practical for ...
Su PC +5 more
europepmc +2 more sources
Contextually Constrained Deep Networks for Scene Labeling [PDF]
Proceedings of the British Machine Vision Conference 2014, 2014 Learning using deep learning architectures is a difficult problem: the complexity of the prediction model and the difficulty of solving non-convex optimization problems inherent to most learning algorithms can both lead to overfitting phenomena and bad local optima.
Taygun Kekeç +4 more
openalex +5 more sources
In-Place Scene Labelling and Understanding with Implicit Scene Representation [PDF]
2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2021 Semantic labelling is highly correlated with geometry and radiance reconstruction, as scene entities with similar shape and appearance are more likely to come from similar classes. Recent implicit neural reconstruction techniques are appealing as they do not require prior training data, but the same fully self-supervised approach is not possible for ...
Shuaifeng Zhi +3 more
openaire +2 more sources
Labeling contours in natural scenes
Journal of Vision, 2010 Jared Christensen, James T. Todd
openalex +2 more sources