2k citations
- Institute of High Performance ComputingSG402 papers
- National University of SingaporeSG364 papers
- Nanyang Technological UniversitySG280 papers
- Institute for Infocomm ResearchSG266 papers
- Institute of Materials Research and EngineeringSG173 papers
- Data Storage InstituteSG90 papers
- Singapore University of Technology and DesignSG70 papers
- Centre for Quantum TechnologiesSG40 papers
- Chinese Academy of SciencesCN33 papers
- Australian National UniversityAU27 papers
- Massachusetts Institute of TechnologyUS27 papers
- Bioinformatics InstituteSG25 papers
10 papers · 2 filters
Class Balance Matters to Active Class-Incremental Learning
Zitong Huang, Ze Chen, Yuanze Li +6
Few-Shot Class-Incremental Learning has shown remarkable efficacy in efficient learning new concepts with limited annotations. Nevertheless, the heuristic few-shot annotations may…
D-LORD for Motion Stylization
Meenakshi Gupta, Mingyuan Lei, Tat-Jen Cham +1
This paper introduces a novel framework named D-LORD (Double Latent Optimization for Representation Disentanglement), which is designed for motion stylization (motion style transfe…
FaceTracer: Unveiling Source Identities from Swapped Face Images and Videos for Fraud Prevention
Zhongyi Zhang, Jie Zhang, Wenbo Zhou +5
Face-swapping techniques have advanced rapidly with the evolution of deep learning, leading to widespread use and growing concerns about potential misuse, especially in cases of fr…
On-the-fly Point Feature Representation for Point Clouds Analysis
Jiangyi Wang, Zhongyao Cheng, Na Zhao +2
Point cloud analysis is challenging due to its unique characteristics of unorderness, sparsity and irregularity. Prior works attempt to capture local relationships by convolution o…
PetalView: Fine-grained Location and Orientation Extraction of Street-view Images via Cross-view Local Search with Supplementary Materials
Wenmiao Hu, Yichen Zhang, Yuxuan Liang +5
Satellite-based street-view information extraction by cross-view matching refers to a task that extracts the location and orientation information of a given street-view image query…
ViDSOD-100: A New Dataset and a Baseline Model for RGB-D Video Salient Object Detection
Junhao Lin, Lei Zhu, Jiaxing Shen +3
With the rapid development of depth sensor, more and more RGB-D videos could be obtained. Identifying the foreground in RGB-D videos is a fundamental and important task. However, t…