Research map / Label-efficient and robust learning / Recognition and long-tail
Multi-View Deep Network for Cross-View Classification
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use the supervised, nonlinear MvDN instead of GMA | cross-pose face recognition · MultiPIE | average rank-1 recognition rate: 0.838 -> 0.887 | Helped |
| use the supervised, nonlinear MvDN instead of MvDA | cross-pose face recognition · MultiPIE | average rank-1 recognition rate: 0.837 -> 0.887 | Helped |
| use MvDN instead of MVP+LDA | cross-pose face recognition · MultiPIE, six-pose protocol | rank-1 recognition rate: 0.934 -> 0.991; 1.00 -> 0.995; 1.00 -> 1.00; 1.00 -> 1.00; 0.993 -> 0.991; 0.956 -> 0.976 | Mixed |
| increase the second-to-last common-subnetwork layer from 400 to 1400 neurons (ablation) | MvDN · MultiPIE | average rank-1 recognition rate: 0.871 -> 0.892 | Helped |
| increase the second-to-last common-subnetwork layer from 1400 to 1600 neurons (ablation) | MvDN · MultiPIE | average rank-1 recognition rate: 0.892 -> 0.880 | Hurt |
| increase the second-to-last common-subnetwork layer from 1400 to 1800 neurons (ablation) | MvDN · MultiPIE | average rank-1 recognition rate: 0.892 -> 0.877 | Hurt |
Closest papers by meaning
- CPM-Nets: Cross Partial Multi-View Networks (NeurIPS 2019 · similarity 0.87)
- Deep Embedded Complementary and Interactive Information for Multi-View Classification (AAAI 2020 · similarity 0.87)
- Deep Incomplete Multi-View Learning Network with Insufficient Label Information (AAAI 2024 · similarity 0.84)
- Rethinking Multi-view Representation Learning via Distilled Disentangling (CVPR 2024 · similarity 0.83)
- SparX: A Sparse Cross-Layer Connection Mechanism for Hierarchical Vision Mamba and Transformer Networks (AAAI 2025 · similarity 0.83)
- DVANet: Disentangling View and Action Features for Multi-View Action Recognition (AAAI 2024 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.