48 citations
- Hiroshima UniversityJP2 papers
- University of LuxembourgLU2 papers
- Bielefeld UniversityDE1 paper
- Forschungszentrum JülichDE1 paper
- Indonesian Institute of SciencesID1 paper
- Nagasaki UniversityJP1 paper
- National Research and Innovation AgencyID1 paper
- Sakon Nakhon Rajabhat UniversityTH1 paper
- Universitas Trunodjoyo MaduraID1 paper
- University of IndonesiaID1 paper
4 papers · 1 filter
Hybrid of DiffStride and Spectral Pooling in Convolutional Neural Networks
Sulthan Rafif, Mochamad Arfan Ravy Wahyu Pratama, Mohammad Faris Azhar +3
Stride determines the distance between adjacent filter positions as the filter moves across the input. A fixed stride causes important information contained in the image can not be…
SparseSwin: Swin Transformer with Sparse Transformer Block
Krisna Pinasthika, Blessius Sheldo Putra Laksono, Riyandi Banovbi Putera Irsal +2
Advancements in computer vision research have put transformer architecture as the state of the art in computer vision tasks. One of the known drawbacks of the transformer architect…
Weakly-Supervised Action Localization and Action Recognition using Global-Local Attention of 3D CNN
Novanto Yudistira, Muthu Subash Kavitha, Takio Kurita
3D Convolutional Neural Network (3D CNN) captures spatial and temporal information on 3D data such as video sequences. However, due to the convolution and pooling mechanism, the in…
Correlation Net: Spatiotemporal multimodal deep learning for action recognition
Novanto Yudistira, Takio Kurita
This paper describes a network that captures multimodal correlations over arbitrary timestamps. The proposed scheme operates as a complementary, extended network over a multimodal…