Research map / Video / Video segmentation and tracking
Visual Transformation Aided Contrastive Learning for Video-Based Kinship Verification
Hamdi Dibeklioglu
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 |
|---|---|---|---|
| add expression matching of sub-sequences (vs random five-frame pairs) (ablation) | proposed method · UvA-NEMO Smile (video kinship) | accuracy (%): 82.74 -> 93.65 | Improved |
| use temporal sequences of 5 frames instead of single frames (m=0) (ablation) | proposed method · UvA-NEMO Smile (video kinship) | accuracy (%): 89.51 -> 93.65 | Improved |
| increase sequence length from 5 to 7 frames (ablation) | proposed method · UvA-NEMO Smile (video kinship) | accuracy (%): 93.65 -> 91.21 | Hurt |
| increase sequence length from 1 to 3 frames (ablation) | proposed method · UvA-NEMO Smile (video kinship) | accuracy (%): 89.51 -> 92.93 | Improved |
| add non-kinship loss with 10% most similar non-kins (ablation) | proposed method · UvA-NEMO Smile (video kinship) | accuracy (%): 90.28 -> 93.65 | Improved |
| use 10% instead of 100% of non-kins in non-kinship loss (ablation) | proposed method · UvA-NEMO Smile (video kinship) | accuracy (%): 91.31 -> 93.65 | Improved |
| use 10% instead of 50% of non-kins in non-kinship loss (ablation) | proposed method · UvA-NEMO Smile (video kinship) | accuracy (%): 92.15 -> 93.65 | Improved |
| add contrastive loss in both pre-training and fine-tuning (ablation) | proposed method · UvA-NEMO Smile (video kinship) | accuracy (%): 86.30 -> 93.65 | Improved |
| use appearance-based contrastive pre-training instead of standard (ablation) | proposed method · UvA-NEMO Smile (video kinship) | accuracy (%): 90.28 -> 93.65 | Improved |
| use feature-based contrastive fine-tuning instead of standard (logistic regression) (ablation) | proposed method · UvA-NEMO Smile (video kinship) | accuracy (%): 92.72 -> 93.65 | Improved |
| replace coupled encoder-decoder with stacked denoising autoencoders (ablation) | proposed method · UvA-NEMO Smile (video kinship) | accuracy (%): 93.65 -> 86.40 | Hurt |
| use short-term temporal video information vs static images (SMCNN) (ablation) | SMCNN baseline · UvA-NEMO Smile (video kinship) | accuracy (%): 84.56 -> 93.65 | Improved |
Closest papers by meaning
- Facial Kinship Verification: A Comprehensive Review and Outlook (IJCV 2022 · similarity 0.88)
- A Unified Approach to Kinship Verification (TPAMI 2020 · similarity 0.88)
- StyleGene: Crossover and Mutation of Region-Level Facial Genes for Kinship Face Synthesis (CVPR 2023 · similarity 0.86)
- Survey on the Analysis and Modeling of Visual Kinship: A Decade in the Making (TPAMI 2021 · similarity 0.86)
- FaithfulFaces: Pose-Faithful Facial Identity Preservation for Text-to-Video Generation (NeurIPS 2026 · similarity 0.82)
- FSRT: Facial Scene Representation Transformer for Face Reenactment from Factorized Appearance Head-pose and Facial Expression Features (CVPR 2024 · similarity 0.81)
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.
