Results 31 to 40 of about 48,305 (299)

Proximal methods for point source localisation [PDF]

Journal of Nonsmooth Analysis and Optimization, 2023
Point source localisation is generally modelled as a Lasso-type problem on measures. However, optimisation methods in non-Hilbert spaces, such as the space of Radon measures, are much less developed than in Hilbert spaces.
Tuomo Valkonen
doaj   +1 more source

Gaussian guided frame sequence encoder network for action quality assessment

Complex & Intelligent Systems, 2022
Can a computer evaluate an athlete’s performance automatically? Many action quality assessment (AQA) methods have been proposed in recent years. Limited by the randomness of video sampling and the simple strategy of model training, the performance of the
Ming-Zhe Li, Hong-Bo Zhang, Li-Jia Dong, Qing Lei, Ji-Xiang Du   +4 more
doaj   +1 more source

The Challenges of HTR Model Training: Feedback from the Project Donner le gout de l'archive a l'ere numerique [PDF]

Journal of Data Mining and Digital Humanities, 2023
The arrival of handwriting recognition technologies offers new possibilities for research in heritage studies. However, it is now necessary to reflect on the experiences and the practices developed by research teams.
Beatrice Couture, Farah Verret, Maxime Gohier, Dominique Deslandres   +3 more
doaj   +1 more source

Computer Analysis of Architecture Using Automatic Image Understanding [PDF]

Journal of Data Mining and Digital Humanities, 2019
In the past few years, computer vision and pattern recognition systems have been becoming increasingly more powerful, expanding the range of automatic tasks enabled by machine vision.
Fan Wei, Yuan Li, Lior Shamir
doaj   +3 more sources

Trainable COSFIRE Filters for Keypoint Detection and Pattern Recognition [PDF]

, 2013
Background: Keypoint detection is important for many computer vision applications. Existing methods suffer from insufficient selectivity regarding the shape properties of features and are vulnerable to contrast variations and to the presence of noise or ...
Azzopardi, George,, Petkov, Nicolai, Petkov, N., Petkov, Nicolai,, Azzopardi, George, Azzopardi, George; id_orcid, Azzopardi, G.   +6 more
core   +1 more source

A Hybrid Quantum-Classical Algorithm for Robust Fitting

, 2022
Fitting geometric models onto outlier contaminated data is provably intractable. Many computer vision systems rely on random sampling heuristics to solve robust fitting, which do not provide optimality guarantees and error bounds.
Sasdelli, M., Chin, T.J., Sasdelli, Michele, Suter, David, Doan, A.D., Chin, Tat-Jun, Suter, D., Doan, Anh-Dzung   +7 more
core   +1 more source

Bilinear programming for human activity recognition with unknown MRF graphs [PDF]

, 2013
Markov Random Fields (MRFs) have been successfully applied to human activity modelling, largely due to their ability to model complex dependencies and deal with local uncertainty.
Qinfeng Shi, Van Den Hengel, A., Zhenhua Wang, Shen, C., Anton van den Hengel, Chunhua Shen, Wang, Z., Shi, Q.   +7 more
core   +1 more source

UMAG-Net: A New Unsupervised Multiattention-Guided Network for Hyperspectral and Multispectral Image Fusion

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021
To reconstruct images with high spatial resolution and high spectral resolution, one of the most common methods is to fuse a low-resolution hyperspectral image (HSI) with a high-resolution (HR) multispectral image (MSI) of the same scene.
Shuaiqi Liu, Siyu Miao, Jian Su, Bing Li, Weiming Hu, Yu-Dong Zhang   +5 more
doaj   +1 more source

Batch mode Adaptive Multiple Instance Learning for computer vision tasks

, 2012
Multiple Instance Learning (MIL) has been widely exploited in many computer vision tasks, such as image retrieval, object tracking and so on. To handle ambiguity of instance labels in positive bags, the training process of traditional MIL methods is ...
I. W. Tsang, Duan, L, Duan, Lixin, Wen Li, Tsang, Ivor Wai-Hung, Xu, Dong, Lixin Duan, Li, Wen, Tsang, Ivor Wai Hung, Dong Xu, Li, W, Tsang, IWH, Xu, D   +12 more
core   +1 more source

Unsupervised learning for robust fitting: A reinforcement learning approach

, 2021
Robust model fitting is a core algorithm in a large number of computer vision applications. Solving this problem efficiently for datasets highly contaminated with outliers is, however, still challenging due to the underlying computational complexity ...
Suter, David, Erchuan Zhang, Zhang, Erchuan, Le, H., Truong, G., Truong, Giang, Gilani, Syed Zulqarnain,, Truong, Giang,, Huu Le, Zhang, E., Gilani, Syed Zulqarnain, Le, Huu, Syed Zulqarnain Gilani, Le, Huu,, Suter, David,, Giang Truong, Zhang, Erchuan,, Suter, D., David Suter, Gilani, S.Z.   +19 more
core   +1 more source