# Scalable Temporal Localization of Sensitive Activities in Movies and TV Episodes

arXiv: https://arxiv.org/abs/2206.08429 · HTML: https://mlsanity.com/paper/2206.08429/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 46 references that are in the map.
- First posted on arXiv 16 Jun 2022.

## Builds on (most cited first, 30 of 31)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [Temporal Segment Networks: Towards Good Practices for Deep Action Recognition](https://mlsanity.com/paper/1608.00859/) (2016)
- [AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions](https://mlsanity.com/paper/1705.08421/) (2017)
- [BSN: Boundary Sensitive Network for Temporal Action Proposal Generation](https://mlsanity.com/paper/1806.02964/) (2018)
- [Temporal Action Detection with Structured Segment Networks](https://mlsanity.com/paper/1704.06228/) (2017)
- [Human Action Recognition and Prediction: A Survey](https://mlsanity.com/paper/1806.11230/) (2018)
- [Graph Convolutional Networks for Temporal Action Localization](https://mlsanity.com/paper/1909.03252/) (2019)
- [MovieNet: A Holistic Dataset for Movie Understanding](https://mlsanity.com/paper/2007.10937/) (2020)
- [Rethinking the Faster R-CNN Architecture for Temporal Action Localization](https://mlsanity.com/paper/1804.07667/) (2018)
- [Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles](https://mlsanity.com/paper/1811.09795/) (2018)
- [Gaussian Temporal Awareness Networks for Action Localization](https://mlsanity.com/paper/1909.03877/) (2019)
- [UntrimmedNets for Weakly Supervised Action Recognition and Detection](https://mlsanity.com/paper/1703.03329/) (2017)
- [Single Shot Temporal Action Detection](https://mlsanity.com/paper/1710.06236/) (2017)
- [End-to-end Learning of Action Detection from Frame Glimpses in Videos](https://mlsanity.com/paper/1511.06984/) (2015)
- [Weakly Supervised Action Localization by Sparse Temporal Pooling Network](https://mlsanity.com/paper/1712.05080/) (2017)
- [W-TALC: Weakly-supervised Temporal Activity Localization and Classification](https://mlsanity.com/paper/1807.10418/) (2018)
- [RED: Reinforced Encoder-Decoder Networks for Action Anticipation](https://mlsanity.com/paper/1707.04818/) (2017)
- [Background Suppression Network for Weakly-supervised Temporal Action Localization](https://mlsanity.com/paper/1911.09963/) (2019)
- [Online Action Detection](https://mlsanity.com/paper/1604.06506/) (2016)
- [SF-Net: Single-Frame Supervision for Temporal Action Localization](https://mlsanity.com/paper/2003.06845/) (2020)
- [Weakly-supervised Action Localization with Background Modeling](https://mlsanity.com/paper/1908.06552/) (2019)
- [3C-Net: Category Count and Center Loss for Weakly-Supervised Action Localization](https://mlsanity.com/paper/1908.08216/) (2019)
- [Multi-shot Temporal Event Localization: a Benchmark](https://mlsanity.com/paper/2012.09434/) (2020)
- [Real-time Action Recognition with Enhanced Motion Vector CNNs](https://mlsanity.com/paper/1604.07669/) (2016)
- [Finding Action Tubes](https://mlsanity.com/paper/1411.6031/) (2014)
- [A Better Baseline for AVA](https://mlsanity.com/paper/1807.10066/) (2018)

## Abstract (arXiv)

To help customers make better-informed viewing choices, video-streaming services try to moderate their content and provide more visibility into which portions of their movies and TV episodes contain age-appropriate material (e.g., nudity, sex, violence, or drug-use). Supervised models to localize these sensitive activities require large amounts of clip-level labeled data which is hard to obtain, while weakly-supervised models to this end usually do not offer competitive accuracy. To address this challenge, we propose a novel Coarse2Fine network designed to make use of readily obtainable video-level weak labels in conjunction with sparse clip-level labels of age-appropriate activities. Our model aggregates frame-level predictions to make video-level classifications and is therefore able to leverage sparse clip-level labels along with video-level labels. Furthermore, by performing frame-level predictions in a hierarchical manner, our approach is able to overcome the label-imbalance problem caused due to the rare-occurrence nature of age-appropriate content. We present comparative results of our approach using 41,234 movies and TV episodes (~3 years of video-content) from 521 sub-genres and 250 countries making it by far the largest-scale empirical analysis of age-appropriate activity localization in long-form videos ever published. Our approach offers 107.2% relative mAP improvement (from 5.5% to 11.4%) over existing state-of-the-art activity-localization approaches.