Research map / 3D vision / Human pose estimation
Online Localization and Prediction of Actions and Interactions
Khurram Soomro, Haroon Idrees, Mubarak A. Shah
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 structural SVM instead of binary SVMs with dynamic programming (ablation) | online prediction · MSR-II Boxing | average precision: 37.3 -> 75.3 | Improved |
| use structural SVM instead of binary SVMs with dynamic programming (ablation) | online prediction · MSR-II Handclapping | average precision: 28.3 -> 43.4 | Improved |
| use structural SVM instead of binary SVMs with dynamic programming (ablation) | online prediction · MSR-II Handwaving | average precision: 42.9 -> 71.3 | Improved |
| use structural SVM instead of binary SVMs with dynamic programming (ablation) | online prediction · UCF Sports (long actions) | prediction accuracy: about 12% | Improved |
| use structural SVM instead of binary SVMs with dynamic programming (ablation) | online localization and prediction · sub-JHMDB | AUC and ROC | Improved |
| add spatio-temporal smoothness refinement of poses (ablation) | pose-based foreground likelihood · kicking and walking videos | pose joint accuracy | Improved |
| lower overlap threshold for evaluation | online localization · JHMDB, UCF Sports and others | AUC | Improved |
| observe more of the action | online prediction · JHMDB, sub-JHMDB, UCF Sports | prediction accuracy | Improved |
| observe more of the action | online prediction · MSR-II and UT Interaction | prediction accuracy | No clear effect |
Closest papers by meaning
- Predicting the Where and What of Actors and Actions Through Online Action Localization (CVPR 2016 · similarity 0.96)
- Pointly-Supervised Action Localization (IJCV 2018 · similarity 0.90)
- Graph Convolutional Module for Temporal Action Localization in Videos (TPAMI 2021 · similarity 0.89)
- Subjects and Their Objects: Localizing Interactees for a Person-Centric View of Importance (IJCV 2016 · similarity 0.89)
- AVA: A Video Dataset of Spatio-Temporally Localized Atomic Visual Actions (CVPR 2018 · similarity 0.88)
- SpatioTemporal Learning for Human Pose Estimation in Sparsely-Labeled Videos (AAAI 2025 · 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.
