Research map / 3D vision / Human pose estimation
Deep Graph Pose: a semi-supervised deep graphical model for improved animal pose tracking
Anqi Wu, Estefany Kelly Buchanan, Matthew Whiteway, Michael Schartner, Guido Meijer, Jean-Paul Noel, Erica Rodriguez, Claire Everett, Amy Norovich, Evan Schaffer, Neeli Mishra, C. Daniel Salzman and 5 more
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 semi-supervised unimodality-encouraging ELBO term on unlabeled frames (DGP-semi vs DLC) (ablation) | DeepLabCut-style pose network, mouse-wheel · mouse-wheel test error vs training fraction (10%-90% of 55 labels) | test pixel error | Improved |
| Add spatial and temporal potentials to DGP-semi (full DGP) (ablation) | DGP-semi, mouse-wheel · mouse-wheel test error vs training fraction | test pixel error | Improved |
| Post-process DLC with Kalman smoothers or total variation denoisers | DLC output · mouse-wheel glitch frames | glitch removal | No clear effect |
| Use DGP traces instead of DLC traces for ARHMM segmentation | two-state ARHMM · mouse-wheel paw traces | state interpretability | Improved |
| Condition CAE on DGP markers instead of DLC markers | conditional convolutional autoencoder · mouse-wheel test frames | MSE per pixel | Improved |
Closest papers by meaning
- APT-36K: A Large-scale Benchmark for Animal Pose Estimation and Tracking (NeurIPS 2022 · similarity 0.91)
- Animal Pose Tracking: 3D Multimodal Dataset and Token-based Pose Optimization (IJCV 2022 · similarity 0.89)
- PosePAL: Efficient Animal Pose Labeling Using Point Trackers (IJCV 2026 · similarity 0.89)
- Pose Splatter: A 3D Gaussian Splatting Model for Quantifying Animal Pose and Appearance (NeurIPS 2025 · similarity 0.87)
- Probabilistic Prompt Distribution Learning for Animal Pose Estimation (CVPR 2025 · similarity 0.86)
- BEAST3D: animal behavioral analysis and neural encoding from multi-view video via Gaussian splatting (NeurIPS 2026 · similarity 0.85)
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.
