Results 231 to 240 of about 31,762 (259)

Weakly Supervised Photo Cropping

IEEE Transactions on Multimedia, 2014
Photo cropping is widely used in the printing industry, photography, and cinematography. Conventional photo cropping methods suffer from three drawbacks: 1) the semantics used to describe photo aesthetics are determined by the experience of model designers and specific data sets, 2) image global configurations, an essential cue to capture photos ...
Luming Zhang, Mingli Song, Yi Yang, Qi Zhao, Xiao Liu, Chen Zhao, Sebe, Niculae   +6 more
openaire   +5 more sources

Weakly Supervised Person Search

2020 IEEE 7th International Conference on Data Science and Advanced Analytics (DSAA), 2020
While existing person search methods have achieved good performance, they require the images used for training contain labels about the identity and bounding box location of each person. However, it is expensive and difficult to manually annotate these labels in the large scale scenario.
Lan Yan, Wenbo Zheng 0001, Fei-Yue Wang 0001, Chao Gou   +3 more
openaire   +1 more source

Weakly Supervised Fog Detection

2018 25th IEEE International Conference on Image Processing (ICIP), 2018
Image dehazing tries to solve an undesired loss of visibility in outdoor images due to the presence of fog. Recently, machine-learning techniques have shown great dehazing ability. However, in order to be trained, they require training sets with pairs of foggy images and their clean counterparts, or a depth-map.
Adrian Galdran, Pedro Costa 0005, Javier Vazquez-Corral, Aurélio Campilho   +3 more
openaire   +1 more source

Weakly Supervised Affordance Detection

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017
Localizing functional regions of objects or affordances is an important aspect of scene understanding and relevant for many robotics applications. In this work, we introduce a pixel-wise annotated affordance dataset of 3090 images containing 9916 object instances.
Johann Sawatzky, Abhilash Srikantha, Juergen Gall   +2 more
openaire   +1 more source

Compound Weakly Supervised Clustering

IEEE Transactions on Image Processing
Clustering is a fundamental and important step in many image processing tasks, such as face recognition and image segmentation. The performance of clustering can be largely enhanced if relevant weak supervision information is appropriately exploited. To achieve this goal, in this paper, we propose the Compound Weakly Supervised Clustering (CSWC) method.
Hong Tao, Jiacheng Jiang, Chenping Hou, Tingjin Luo, Ruidong Fan, Jing Zhang 0064   +5 more
openaire   +2 more sources

On a Weakly Supervised Classification Problem

2022
Vladimir B. Berikov, Alexander Litvinenko, Igor Pestunov, Yuriy Sinyavskiy   +3 more
openaire   +1 more source

Weakly Supervised Object Detection Using Proposal- and Semantic-Level Relationships

IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022
Junwei Han, Dingwen Zhang
exaly  

Weakly-supervised semantic segmentation with saliency and incremental supervision updating

Pattern Recognition, 2021
Weishi Zheng
exaly  

A Weakly Supervised Semantic Segmentation Network by Aggregating Seed Cues: The Multi-Object Proposal Generation Perspective

ACM Transactions on Multimedia Computing, Communications and Applications, 2021
Honghao Gao, Huahu Xu, Junsheng Xiao
exaly  

Weakly supervised segmentation with cross-modality equivariant constraints

Medical Image Analysis, 2022
Gaurav Patel, JOSÉ Dolz
exaly