-
381
University Media Content Detection and Classification Based on Information Fusion Algorithm
Published 2022-01-01“…This essay mainly introduces the technology of university media content detection and classification based on information fusion algorithm and focuses on the application of university multimedia content detection, analysis, and understanding, to explore the image discrimination auxiliary attribute feature learning and content association prediction and classification. …”
Get full text
Article -
382
Action-driven contrastive representation for reinforcement learning.
Published 2022-01-01“…In reinforcement learning, reward-driven feature learning directly from high-dimensional images faces two challenges: sample-efficiency for solving control tasks and generalization to unseen observations. …”
Get full text
Article -
383
An improved multi-scale branching convolutional neural network for rolling bearing fault diagnosis.
Published 2023-01-01“…The proposed method first applies the multiscale feature learning strategy to extract rich and compelling fault information from diverse and complex vibration signals. …”
Get full text
Article -
384
Scaling object detection by transferring learning
Published 2020“…The detection network and WTN are trained by Objects 365 dataset which is the large-scale object detection dataset and works well in feature learning. The experimental results show that the performance of WTN is improved.…”
Get full text
Thesis-Master by Coursework -
385
Robust real-time visual tracking
Published 2017“…In this thesis we present four different tracking algorithms which exploit the sparse coding, part-based model, color feature learning and convolutional network features to handle the aforementioned challenges.Extensive experiments have been done respectively to prove the effectiveness of our proposed trackers.…”
Get full text
Thesis -
386
Contrastive learning for unsupervised radar place recognition
Published 2022“…Our method is based on invariant instance feature learning but is tailored for the task of re-localisation by exploiting for data augmentation the temporal successivity of data as collected by a mobile platform moving through the scene smoothly. …”
Conference item -
387
Efficient and Robust: A Cross-Modal Registration Deep Wavelet Learning Method for Remote Sensing Images
Published 2023-01-01“…Deep convolutional networks are powerful for local feature learning and have shown advantages in image matching and registration. …”
Get full text
Article -
388
Improving object detection quality with structural constraints.
Published 2022-01-01“…Structural constraint supervises feature learning in classification and localization network branches with Fisher Loss and Equi-proportion Loss respectively, by requiring feature similarities of training sample pairs to be consistent with corresponding ground truth label similarities. …”
Get full text
Article -
389
An Asymmetric Contrastive Loss for Handling Imbalanced Datasets
Published 2022-09-01“…The learning process is typically conducted using a two-stage training architecture, and it utilizes the contrastive loss (CL) for its feature learning. Contrastive learning has been shown to be quite successful in handling imbalanced datasets, in which some classes are overrepresented while some others are underrepresented. …”
Get full text
Article -
390
<inline-formula><tex-math notation="LaTeX">$C^{2}N^{2}$</tex-math></inline-formula>: Complex-Valued Contourlet Neural Network
Published 2024-01-01“…This is the key to feature learning representation of high-order singularity. …”
Get full text
Article -
391
-
392
An Unsupervised Character Recognition Method for Tibetan Historical Document Images Based on Deep Learning
Published 2024-03-01“…Then, the character baseline information is introduced, and a fine-grained feature learning strategy is proposed. For the samples above and below the baseline, the Up-CNN recognition model and Down-CNN recognition model are established. …”
Get full text
Article -
393
ARTFLOW: A Fast, Biologically Inspired Neural Network that Learns Optic Flow Templates for Self-Motion Estimation
Published 2021-12-01“…This design affords fast, local feature learning across parallel modules in each network layer. …”
Get full text
Article -
394
Orientation-Encoding CNN for Point Cloud Classification and Segmentation
Published 2021-08-01“…By searching for the same number of points in 8 directions and arranging them in order in 8 directions, the OE convolution is then carried out according to the number of points in the direction, which realizes the effective feature learning of the local structure of the point sets. …”
Get full text
Article -
395
Combined Spatial-Spectral Schroedinger Eigenmaps with Multiple Kernel Learning for Hyperspectral Image Classification Using a Low Number of Training Samples
Published 2022-09-01“…Then MKL is utilized to enhance the feature learning process and obtain an optimum combination of some specified kernels. …”
Get full text
Article -
396
Digital construction of higher education management based on multimodal machine database
Published 2024-01-01“…Then, the higher education management system is constructed based on semi-supervised fusion feature learning and homogeneous multimodal features of multimodal machines, and the system architecture and database design are explained in detail. …”
Get full text
Article -
397
Bearing Fault Diagnosis based on Feature Visualization and Depth Adaptive Network
Published 2022-01-01“…It can not only select the similar modal components of the noisy signal and the original signal to improve the signal-to-noise ratio of the noisy signal,but also eliminate the similar modal components of different types of signals to highlight the signal characteristics; then,the signal is reconstructed by using the selected IMFs,and the reconstructed signal is visualized based on GAF transform; finally,the depth adaptive network is used for feature learning and state recognition. The results show that the accuracy of the proposed method is 94.97%,which is better than the common vibration signal fault diagnosis methods,and the proposed method can also suppress the noise and has good robustness,which provides a reasonable idea for the intelligent and accurate diagnosis of bearings.…”
Get full text
Article -
398
Spatiotemporal image fusion using multiscale attention-aware two-stream convolutional neural networks
Published 2022-12-01“…With a coarse image at the prediction date and two pairs of coarse and fine images at other dates as inputs, it employs a multiscale module to characterize different sizes of objects and a spatial and channel attention module to emphasize important information in feature learning. Two experiments on real Landsat and MODIS images are conducted to demonstrate the effectiveness of the proposed MACNN and it outperforms four existing STF methods in both visual and quantitative.…”
Get full text
Article -
399
3D object recognition with a linear time‐varying system of overlay layers
Published 2021-08-01“…The challenge is in selecting appropriate robust features with tolerable computing costs. Feature learning attempts to solve the feature extraction problem through a learning process using various samples of the objects. …”
Get full text
Article -
400
Learning a spatial-temporal texture transformer network for video inpainting
Published 2022-10-01“…Such a design encourages joint feature learning across the input and reference frames. …”
Get full text
Article