Imposing semantic consistency of local descriptors for few-shot learning
Few-shot learning suffers from the scarcity of labeled training data. Regarding local
descriptors of an image as representations for the image could greatly augment existing …
descriptors of an image as representations for the image could greatly augment existing …
Co-learning meets stitch-up for noisy multi-label visual recognition
In real-world scenarios, collected and annotated data often exhibit the characteristics of
multiple classes and long-tailed distribution. Additionally, label noise is inevitable in large …
multiple classes and long-tailed distribution. Additionally, label noise is inevitable in large …
Self-paced multi-grained cross-modal interaction modeling for referring expression comprehension
As an important and challenging problem in vision-language tasks, referring expression
comprehension (REC) generally requires a large amount of multi-grained information of …
comprehension (REC) generally requires a large amount of multi-grained information of …
Gaga: Deciphering age-path of generalized self-paced regularizer
Nowadays self-paced learning (SPL) is an important machine learning paradigm that mimics
the cognitive process of humans and animals. The SPL regime involves a self-paced …
the cognitive process of humans and animals. The SPL regime involves a self-paced …
Efficient 3D object recognition in mobile edge environment
M Song, Q Guo - Journal of Cloud Computing, 2022 - Springer
Abstract 3D object recognition has great research and application value in the fields of
automatic drive, virtual reality, and commercial manufacturing. Although various deep …
automatic drive, virtual reality, and commercial manufacturing. Although various deep …
ACOA: Archimedes conditional autoregressive optimization algorithm based RMDL for web data classification
K Ramesh, R Mohanasundaram - Intelligent Decision …, 2024 - journals.sagepub.com
Web<? show [AQ ID= GQ2]?><? show [AQ ID= GQ4 POS= 12pt]?><? show [AQ ID= GQ5
POS= 24pt]?> data classification has become a subject of great value due to the increase of …
POS= 24pt]?> data classification has become a subject of great value due to the increase of …
Confidence-Aware Active Feedback for Interactive Instance Search
Y Zhang, C Liang, L Jiang - IEEE Transactions on Multimedia, 2022 - ieeexplore.ieee.org
Online relevance feedback (RF) is widely utilized in instance search (INS) tasks to further
refine imperfect ranking results, but it often has low interaction efficiency. The active learning …
refine imperfect ranking results, but it often has low interaction efficiency. The active learning …