AI Paper Atlas

Research map / Video / Video segmentation and tracking

Self-Supervised Representation Learning Framework for Remote Physiological Measurement Using Spatiotemporal Augmentation Loss

Hao Wang, Euijoon Ahn, Jinman Kim

AAAI 2022 · Video › Video segmentation and tracking · approach: Sign language and physiological video analysis · 52 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (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 changedWhereMeasuredEffect
Use landmark-based facial spatial augmentation rather than standard spatial augmentations (ablation)SLF-RPM · HR estimationMAE (bpm): 9.54 -> 5.12Improved
Include all seven facial ROIs instead of omitting any one ROI (ablation)SLF-RPM · HR estimationMAE (bpm): 5.82 -> 5.12Improved
Use sparsity-based temporal augmentation rather than standard temporal transformations (ablation)SLF-RPM · HR estimationMAE (bpm): 5.74 -> 5.28Improved
Use sparsity range {1, 2, 3, 4, 5} rather than the smaller range {1, 2, 3, 4} (ablation)SLF-RPM · HR estimationMAE (bpm): 6.21 -> 5.28Improved
Extend the temporal sparsity range to include stride 6 (ablation)SLF-RPM · HR estimationMAE (bpm): 5.28 -> 5.92Hurt
Add pseudo-label auxiliary classification tasks to the contrastive objective (ablation)SLF-RPM · MAHNOB-HCIMAE (bpm): 4.25 -> 3.6Improved
Use simCLR rather than CPC, CPC + MoCo, or MoCo (ablation)SLF-RPM · HR estimationMAE (bpm): 13.49, 13.05, 11.73 -> 9.54Improved
Use SLF-RPM rather than the strongest SSL baseline, SeCoLinear evaluation · MAHNOB-HCIMAE (bpm): 7.03 -> 3.60Improved
Use SLF-RPM rather than the strongest SSL baseline, SeCoLinear evaluation · VIPL-HR-V2MAE (bpm): 13.32 -> 12.56Improved
Use SLF-RPM rather than the strongest SSL baseline, SeCoLinear evaluation · UBFC-rPPGMAE (bpm): 9.83 -> 8.39Improved
Self-supervise pre-training on VIPL-HR-V2 before fine-tuning instead of training the supervised baseline3D ResNet-18 · MAHNOB-HCIMAE (bpm): 7.34 -> 6.23Improved
Self-supervise pre-training on VIPL-HR-V2 before fine-tuning instead of training the supervised baseline3D ResNet-18 · UBFC-rPPGMAE (bpm): 8.08 -> 7.35Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy