Research map / Video / Action recognition
Temporal Context Network for Activity Localization in Videos
Xiyang Dai, Bharat Singh, Guyue Zhang, Larry S. Davis, Yan Qiu Chen
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 temporal context for ranking proposals (ablation) | TCN · ActivityNet val | mAP@.5: 15.91 -> 36.17 | Improved |
| add temporal context for ranking proposals (ablation) | TCN · ActivityNet val | mAP@.75: 3.11 -> 21.12 | Improved |
| add temporal context for ranking proposals (ablation) | TCN · ActivityNet val | mAP@.95: 0.13 -> 3.89 | Improved |
| add temporal context (ablation) | TCN · THUMOS14 test | Avg.Recall@100: 22.5 -> 29.6 | Improved |
| add temporal context (ablation) | TCN · THUMOS14 test | mAP@0.5: 20.5 -> 25.6 | Improved |
| increase context scale from 2 to 3 (ablation) | TCN · ActivityNet val | mAP@.75: 21.12 -> 14.35 | Hurt |
| increase context scale from 1 to 1.5 (ablation) | TCN · ActivityNet val | mAP@.5: 15.91 -> 30.51 | Improved |
| increase context scale from 2 to 2.5 (ablation) | TCN · ActivityNet val | mAP@.95: 3.89 -> 0.92 | Hurt |
| add bilinear pooling (ablation) | TCN classifier · ActivityNet val | mAP@.5: 26.35 -> 30.31 | Improved |
| add optical flow (ablation) | TCN classifier · ActivityNet val | mAP@.5: 30.31 -> 33.83 | Improved |
| add global video-level priors (ablation) | TCN classifier · ActivityNet val | mAP@.5: 33.83 -> 36.17 | Improved |
| increase proposals per video from 1 to 20 (ablation) | TCN · ActivityNet val | mAP@.5: 25.70 -> 36.17 | Improved |
Closest papers by meaning
- Weakly Supervised Action Localization by Sparse Temporal Pooling Network (CVPR 2018 · similarity 0.90)
- METAL: Minimum Effort Temporal Activity Localization in Untrimmed Videos (CVPR 2020 · similarity 0.90)
- Temporal Convolutional Networks for Action Segmentation and Detection (CVPR 2017 · similarity 0.90)
- Rethinking the Faster R-CNN Architecture for Temporal Action Localization (CVPR 2018 · similarity 0.89)
- Adversarial Background-Aware Loss for Weakly-supervised Temporal Activity Localization (ECCV 2020 · similarity 0.89)
- Enriching Local and Global Contexts for Temporal Action Localization (ICCV 2021 · similarity 0.89)
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.
