Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleDecember 2024
Feature-weighted Multi-stage Bayesian Prototype for Few-shot Classification
MMAsia '24: Proceedings of the 6th ACM International Conference on Multimedia in AsiaArticle No.: 82, Pages 1–7https://doi.org/10.1145/3696409.3700244Few-shot classification aims to recognize the query sample through a limited amount of support data, where a prototype classifier is commonly applied. However, although the prototype classifier is simple and non-parametric, it does not fully utilize the ...
- posterDecember 2024
A Encoder-Decoder Framework for Foundation Model-based Remote Sensing Semantic Segmentation
MMAsia '24 Workshops: Proceedings of the 6th ACM International Conference on Multimedia in Asia WorkshopsArticle No.: 16, Pages 1–7https://doi.org/10.1145/3700410.3702132Remote sensing semantic segmentation technology has been widely applied in various fields such as urban planning, land source management and agriculture. Due to the large number of ground objects with different scales and boundaries in remote sensing ...
- research-articleJuly 2024
Group benefits instance for data purification
Computers and Electrical Engineering (CENG), Volume 116, Issue Chttps://doi.org/10.1016/j.compeleceng.2024.109156AbstractManually annotating datasets for training deep models is very labor-intensive and time-consuming. To overcome such inferiority, directly leveraging web images to conduct training data becomes a natural choice. Nevertheless, the presence of label ...
- research-articleOctober 2023
Incorporating Domain Knowledge Graph into Multimodal Movie Genre Classification with Self-Supervised Attention and Contrastive Learning
MM '23: Proceedings of the 31st ACM International Conference on MultimediaPages 3337–3345https://doi.org/10.1145/3581783.3612085Multimodal movie genre classification has always been regarded as a demanding multi-label classification task due to the diversity of multimodal data such as posters, plot summaries, trailers and metadata. Although existing works have made great progress ...
- research-articleSeptember 2022
Dual collaborative representation based discriminant projection for face recognition
Computers and Electrical Engineering (CENG), Volume 102, Issue Chttps://doi.org/10.1016/j.compeleceng.2022.108281AbstractCollaborative representation based techniques have shown promising results for face recognition; however, most of them code the samples by taking the overall samples as a dictionary, which may contain much noise information. To tackle ...
- research-articleJune 2022
Guided by Meta-Set: A Data-Driven Method for Fine-Grained Visual Recognition
IEEE Transactions on Multimedia (TOM), Volume 25Pages 4691–4703https://doi.org/10.1109/TMM.2022.3181439The lack of sufficient training data has been one obstacle to fine-grained visual classification research because labeling subcategories generally requires specialist knowledge. As one optional approach to alleviating the data-hunger problem, leveraging ...
- research-articleJune 2022
An Uncertainly Dynamic Loss Correction and Global Sample Selection Method for Webly Supervised Fine-Grained Visual Classification
Circuits, Systems, and Signal Processing (CSSP), Volume 41, Issue 6Pages 3265–3281https://doi.org/10.1007/s00034-021-01928-xAbstractTo distinguish the subtle differences among fine-grained categories, a large amount of well-labeled images are typically required. However, manual annotations for fine-grained categories is an extremely difficult task as it usually has a high ...
- ArticleMay 2022
CORSID Enables de novo Identification of Transcription Regulatory Sequences and Genes in Coronaviruses
Research in Computational Molecular BiologyPages 360–362https://doi.org/10.1007/978-3-031-04749-7_28AbstractCoronaviruses are comprised of a single-stranded RNA genome that is ready to be translated by the host ribosome.
- research-articleOctober 2021
Extracting Useful Knowledge from Noisy Web Images via Data Purification for Fine-Grained Recognition
MM '21: Proceedings of the 29th ACM International Conference on MultimediaPages 4063–4072https://doi.org/10.1145/3474085.3475536Fine-grained visual recognition tasks typically require training data with reliable acquisition and annotation processes. Acquiring such datasets with precise fine-grained annotations is very expensive and time-consuming. Conversely, a vast amount of ...
- research-articleOctober 2020
Data-driven Meta-set Based Fine-Grained Visual Recognition
MM '20: Proceedings of the 28th ACM International Conference on MultimediaPages 2372–2381https://doi.org/10.1145/3394171.3414044Constructing fine-grained image datasets typically requires domain-specific expert knowledge, which is not always available for crowd-sourcing platform annotators. Accordingly, learning directly from web images becomes an alternative method for fine-...
- ArticleMay 2012
A 3D Localization Method of Multiple Acoustic Sources Based on Two L-type Microphone Array
In order to solve the problem that the traditional methods can't accurately measure the localization of multiple acoustic sources in far field, this paper presents a new multiple acoustic sources localization method using in the near field and the far ...