# Untrimmed Video Classification for Activity Detection: submission to ActivityNet Challenge

arXiv: https://arxiv.org/abs/1607.01979 · HTML: https://mlsanity.com/paper/1607.01979/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jul 2016.

## Built on by (most cited first, 7 of 7)

- [Temporal Context Aggregation Network for Temporal Action Proposal Refinement](https://mlsanity.com/paper/2103.13141/) (2021)
- [Graph Convolutional Module for Temporal Action Localization in Videos](https://mlsanity.com/paper/2112.00302/) (2021)
- [Temporal Action Proposal Generation with Transformers](https://mlsanity.com/paper/2105.12043/) (2021)
- [SegTAD: Precise Temporal Action Detection via Semantic Segmentation](https://mlsanity.com/paper/2203.01542/) (2022)
- [Transferable Knowledge-Based Multi-Granularity Aggregation Network for Temporal Action Localization: Submission to ActivityNet Challenge 2021](https://mlsanity.com/paper/2107.12618/) (2021)
- [Action Shuffling for Weakly Supervised Temporal Localization](https://mlsanity.com/paper/2105.04208/) (2021)
- [Progression-Guided Temporal Action Detection in Videos](https://mlsanity.com/paper/2308.09268/) (2023)

## Abstract (arXiv)

Current state-of-the-art human activity recognition is focused on the classification of temporally trimmed videos in which only one action occurs per frame. We propose a simple, yet effective, method for the temporal detection of activities in temporally untrimmed videos with the help of untrimmed classification. Firstly, our model predicts the top k labels for each untrimmed video by analysing global video-level features. Secondly, frame-level binary classification is combined with dynamic programming to generate the temporally trimmed activity proposals. Finally, each proposal is assigned a label based on the global label, and scored with the score of the temporal activity proposal and the global score. Ultimately, we show that untrimmed video classification models can be used as stepping stone for temporal detection.