N
Ngai-Man Cheung
Researcher at Singapore University of Technology and Design
Publications - 28
Citations - 370
Ngai-Man Cheung is an academic researcher from Singapore University of Technology and Design. The author has contributed to research in topics: Image retrieval & Feature (computer vision). The author has an hindex of 10, co-authored 28 publications receiving 275 citations.
Papers
More filters
Proceedings ArticleDOI
SDRSAC: Semidefinite-Based Randomized Approach for Robust Point Cloud Registration Without Correspondences
TL;DR: In this paper, the authors propose a novel sampling mechanism, in which the size of the sampled subsets can be larger than minimal, and a tight relaxation scheme enables fast rejection of the outliers in the sampled sets, resulting in high quality hypotheses.
Proceedings ArticleDOI
Selective Deep Convolutional Features for Image Retrieval
TL;DR: Wang et al. as mentioned in this paper proposed various masking schemes to select a representative subset of local convolutional features and remove a large number of redundant features, which can effectively address the burstiness issue and improve retrieval accuracy.
Journal ArticleDOI
On-Device Scalable Image-Based Localization via Prioritized Cascade Search and Fast One-Many RANSAC
Ngoc-Trung Tran,Dang-Khoa Le Tan,Anh-Dzung Doan,Thanh-Toan Do,Tuan-Anh Bui,Mengxuan Tan,Ngai-Man Cheung +6 more
TL;DR: This work presents the design of an entire on-device system for large-scale urban localization using images, and proposes a new hashing-based cascade search for fast computation of 2D–3D correspondences and a new one-many RANSAC for accurate pose estimation.
Proceedings ArticleDOI
Simultaneous Feature Aggregating and Hashing for Large-Scale Image Search
TL;DR: In this article, the authors proposed a novel framework where feature aggregating and hashing are designed simultaneously and optimized jointly, which leads to more discriminative binary hash codes and improved retrieval accuracy.
Journal ArticleDOI
Embedding Based on Function Approximation for Large Scale Image Search
Thanh-Toan Do,Ngai-Man Cheung +1 more
TL;DR: The objective of this paper is to design an embedding method that maps local features describing an image to a higher dimensional representation useful for the image retrieval problem and compares the proposed embedding methods with the state of the art in the context of image search.