Research map / Label-efficient and robust learning / Recognition and long-tail
Discriminative Semi-Coupled Projective Dictionary Learning for Low-Resolution Person Re-Identification
Read the paperCheck 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 |
|---|---|---|---|
| add discriminative graph regularizer (positive and negative pairs) to SPDL (ablation) | SPDL · VIPeR | rank-1 matching rate (%): 26.27 -> 28.51 | Helped |
| add discriminative graph regularizer to SPDL (ablation) | SPDL · VIPeR | rank-10 matching rate (%): 73.73 -> 76.11 | Helped |
| add discriminative graph regularizer to SPDL (ablation) | SPDL · CUHK01 | rank-1 matching rate (%): 20.66 -> 21.75 | Helped |
| add discriminative graph regularizer to SPDL (ablation) | SPDL · QMUL-iLIDS | rank-1 matching rate (%): 52.83 -> 55.17 | Helped |
| add semi-coupled mapping and projective dictionaries (SPDL) versus best dictionary baseline SSSVM | dictionary learning for re-ID · VIPeR | rank-1 matching rate (%): 24.53 -> 26.27 | Helped |
| use resolution-specific methods (SLD2L) rather than general ones | SLD2L · VIPeR | rank-1 matching rate (%): 16.86 vs 24.72 (MLAPG) | Hurt |
| reduce down-sampling rate to 1/8 (larger resolution gap) | DSPDL and baselines · VIPeR | rank-5 matching rate (%) | Hurt |
| vary lambda1 from 1e-3 to 10 (ablation) | DSPDL · VIPeR, CUHK01, QMUL-iLIDS | rank-1 matching rate (%) | Mixed |
Closest papers by meaning
- Learning Heterogeneous Dictionary Pair with Feature Projection Matrix for Pedestrian Video Retrieval via Single Query Image (AAAI 2017 · similarity 0.90)
- Sample-Specific SVM Learning for Person Re-Identification (CVPR 2016 · similarity 0.88)
- Deep Low-Resolution Person Re-Identification (AAAI 2018 · similarity 0.87)
- Learning Resolution-Invariant Deep Representations for Person Re-Identification (AAAI 2019 · similarity 0.87)
- Semi-Supervised Bayesian Attribute Learning for Person Re-Identification (AAAI 2018 · similarity 0.86)
- Unsupervised Cross-Dataset Transfer Learning for Person Re-Identification (CVPR 2016 · similarity 0.86)
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.