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-articleJanuary 2024
Adapting Object Detection to Fisheye Cameras: A Knowledge Distillation with Semi-Pseudo-Label Approach
MMAsia '23: Proceedings of the 5th ACM International Conference on Multimedia in AsiaArticle No.: 111, Pages 1–6https://doi.org/10.1145/3595916.3628350In this paper, we introduce a lightweight object detection system, custom-designed for fisheye cameras and optimized for quick deployment on embedded systems. Given the constraints of training solely on standard images, our methodology centers on the ...
- research-articleJanuary 2024
Monocular 3D Pose Estimation of Very Small Airplane in the Air
MMAsia '23: Proceedings of the 5th ACM International Conference on Multimedia in AsiaArticle No.: 82, Pages 1–7https://doi.org/10.1145/3595916.3626456In this paper, a novel pose estimation algorithm is proposed specifically for maneuvering airplanes in the air. The algorithm consists of two main stages. The first stage involves semantic segmentation of a monocular input image of a flying airplane, ...
- research-articleJanuary 2024
Multi-Scale Superpoint Network for 3D Point Cloud Semantic Segmentation
MMAsia '23: Proceedings of the 5th ACM International Conference on Multimedia in AsiaArticle No.: 75, Pages 1–7https://doi.org/10.1145/3595916.36264493D point cloud semantic segmentation is a fundamental task for 3D scene understanding. However, most existing pipelines usually use k-NN or ball query operation to form hard neighborhoods, which may cross different semantic objects, resulting low-...
- research-articleJanuary 2024
Image Cropping under Design Constraints
MMAsia '23: Proceedings of the 5th ACM International Conference on Multimedia in AsiaArticle No.: 40, Pages 1–7https://doi.org/10.1145/3595916.3626412Image cropping is essential in image editing for obtaining a compositionally enhanced image. In display media, image cropping is a prospective technique for automatically creating media content. However, image cropping for media contents is often ...
- research-articleJanuary 2024
Adaptive Fusion for Visual Question Answering: Integrating Multi-Label Classification and Similarity Matching
MMAsia '23: Proceedings of the 5th ACM International Conference on Multimedia in AsiaArticle No.: 12, Pages 1–7https://doi.org/10.1145/3595916.3626381Visual Question Answering (VQA) is an important multimodal task in which models are required to answer questions based on visual cues. However, most visual question-answering models suffer from the language prior problem, which is caused by data bias. ...
- research-articleJanuary 2024
From Pixels to Explanations: Uncovering the Reasoning Process in Visual Question Answering
MMAsia '23: Proceedings of the 5th ACM International Conference on Multimedia in AsiaArticle No.: 7, Pages 1–9https://doi.org/10.1145/3595916.3626376Visual reasoning requires models to construct a reasoning process towards the final decision. Previous studies have used attention maps or textual explanations to illustrate the reasoning process, but both have their limitations. Attention maps can be ...
- demonstrationJanuary 2024
A consulting system for guiding various image recognitions
MMAsia '23: Proceedings of the 5th ACM International Conference on Multimedia in AsiaArticle No.: 108, Pages 1–3https://doi.org/10.1145/3595916.3626356In recent years, various image recognition tasks have been used in many real-world applications thanks to the development and open sources of computer vision technologies. However, the expertise of users is often required for selecting appropriate ...