[PDF][PDF] A new document representation based on global policy for supervised term weighting schemes in text categorization

L Jia, B Zhang - Mathematical Biosciences and Engineering, 2022 - aimspress.com
… ) is the most widely used text representation model in text categorization. In VSM, a document
is … Guo, Projected-prototype based classifier for text categorization, Knowl.Based Syst., 49 (…

Prototype adaption and projection for few-and zero-shot 3d point cloud semantic segmentation

S He, X Jiang, W Jiang, H Ding - IEEE Transactions on Image …, 2023 - ieeexplore.ieee.org
… embedding as input and outputs a projected prototype, supervised by real prototypes from …
paradigms: classifier-based methods and instance-based methods. Classifier-based methods …

Towards Visual Taxonomy Expansion

T Zhu, J Liu, J Liang, H Jiang, Y Xiao, Z Wang… - Proceedings of the 31st …, 2023 - dl.acm.org
… We also include other projected prototype representations 𝑧𝑖 … taxonomy. Here, we directly
fuse the generated textual and visual features and subsequently feed them into the classifier

A contrastive learning-based task adaptation model for few-shot intent recognition

X Zhang, F Cai, X Hu, J Zheng, H Chen - Information Processing & …, 2022 - Elsevier
… the traditional text classification. Different from the standard text input in the text classification,
… To obtain the weight of each linear projected prototype in the transformed embeddings, we …

Protgnn: Towards self-explaining graph neural networks

Z Zhang, Q Liu, H Wang, C Lu, C Lee - Proceedings of the AAAI …, 2022 - ojs.aaai.org
… We aim to learn representative prototypical graph patterns that can be used for classification
… the highest similarity score from all the expanded nodes as the new projected prototype. …

Low-rank embedded orthogonal subspace learning for zero-shot classification

X Li, M Fang, J Liu - Journal of Visual Communication and Image …, 2021 - Elsevier
… The distance between the projected test image y i and the projected prototype r j is calculated.
The unseen label of the test image is assigned based on the distance. (34) ϕ ( y i ) = a r g …

Prototypical Transformer as Unified Motion Learners

C Han, Y Lu, G Sun, JC Liang, Z Cao, Q Wang… - arXiv preprint arXiv …, 2024 - arxiv.org
… The projected prototype representation P(·) describes the learnable dense vector from a …
This function aggregates across all clusters K, with each projected prototype P(θk,θj) denoting …

Crosspoint: Self-supervised cross-modal contrastive learning for 3d point cloud understanding

M Afham, I Dissanayake… - Proceedings of the …, 2022 - openaccess.thecvf.com
… for varying tasks such as 3D object classification, segmentation and detection is often …
range of downstream tasks including 3D object classification and segmentation. Further, the …

Kernel-based data transformation model for nonlinear classification of symbolic data

X Yan, L Chen, G Guo - Soft Computing, 2022 - Springer
… NB is a probability-based classification based on the Bayes … Distance-based classifiers arise
our interest due to their … performance of a distance-based classifier largely depends on the …

Bio-inspired Approach for Early Diabetes Prediction and Diet Recommendation

A Jain, A Singhal - SN Computer Science, 2024 - Springer
classification algorithms, and the accuracy of the classifiers was improved by tuning their
hyperparameters using Hybrid Bat Algorithm. Most of the classifiers in … The projected prototype