Research map / Video / Action recognition
Is Sharing of Egocentric Video Giving Away Your Biometric Signature?
Daksh Thapar, Chetan Arora, Aditya Nigam
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use EgoGaitNet instead of prior method [9] | wearer recognition · EVPR (closed set) | classification accuracy (%): 90.0 -> 92.5 | Improved |
| use EgoGaitNet instead of prior method [9] | wearer recognition · DB-01 (closed set) | EER (%): 4.38 -> 2.79 | Improved |
| use EgoGaitNet instead of prior method [9] | wearer recognition · DB-04 combined (closed set) | classification accuracy (%): 85.6 -> 89.9 | Improved |
| move from closed-set to open-set (unseen wearers) | EgoGaitNet · EVPR | EER (%): 9.8 -> 14.35 | Mixed |
| move from closed-set to open-set (unseen wearers) | EgoGaitNet · DB-04 | EER (%): 15.44 -> 20.61 | Hurt |
| average optical flow to a single global vector instead of dense flow (ablation) | EgoGaitNet · egocentric wearer identification | accuracy (%): 92 -> 84 | Hurt |
| use 7x7 optical flow matrix instead of dense flow (ablation) | EgoGaitNet · egocentric wearer identification | accuracy (%): 92 | No clear effect |
| fuse HSN-FT and HSN-TF scores instead of one stream (ablation) | HSN · IITMD-WTP closed set | EER (%): 11.45 -> 8.76 | Improved |
| fuse features with CombineNet instead of score fusion (ablation) | HSN · IITMD-WTP closed set | rank-one CRR (%): 76.24 -> 79.86 | Improved |
| restrict test to three subjects of similar height (ablation) | EgoGaitNet · wearer height analysis | EER (%): 2.03 | No clear effect |
Closest papers by meaning
- Anonymizing Egocentric Videos (ICCV 2021 · similarity 0.94)
- EgoPrivacy: What Your First-Person Camera Says About You? (ICML 2025 · similarity 0.87)
- EgoSim: An Egocentric Multi-view Simulator and Real Dataset for Body-worn Cameras during Motion and Activity (NeurIPS 2024 · similarity 0.86)
- Estimating Ego-Body Pose from Doubly Sparse Egocentric Video Data (NeurIPS 2024 · similarity 0.84)
- Instance Tracking in 3D Scenes from Egocentric Videos (CVPR 2024 · similarity 0.84)
- Exploring More from Multiple Gait Modalities for Human Identification (AAAI 2025 · similarity 0.84)
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.
