Research map / Video / Action recognition
Action Localization through Continual Predictive Learning
Sathyanarayanan Aakur, Sudeep Sarkar
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 prediction error-based localization instead of trained attention-based localization (ablation) | proposed approach · UCF Sports | AUC over overlap thresholds | Improved |
| use selective search or EdgeBox proposals instead of SSD proposals (ablation) | proposed approach · UCF Sports | AUC over overlap thresholds: 50 compared to the 10 | Mixed |
| add Bahdanau attention layer in the prediction module (ablation) | proposed approach · UCF Sports | AUC over overlap thresholds | Hurt |
Closest papers by meaning
- Temporal Action Localization in the Deep Learning Era: A Survey (TPAMI 2023 · similarity 0.90)
- Actor-Centered Representations for Action Localization in Streaming Videos (ECCV 2022 · similarity 0.89)
- Pointly-Supervised Action Localization (IJCV 2018 · similarity 0.89)
- Temporal Action Localization by Structured Maximal Sums (CVPR 2017 · similarity 0.89)
- A Perceptual Prediction Framework for Self Supervised Event Segmentation (CVPR 2019 · similarity 0.89)
- Weakly-Supervised Temporal Action Localization by Inferring Salient Snippet-Feature (AAAI 2024 · similarity 0.87)
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.
