# Exploring Temporal Preservation Networks for Precise Temporal Action Localization

arXiv: https://arxiv.org/abs/1708.03280 · HTML: https://mlsanity.com/paper/1708.03280/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Aug 2017.

## Built on by (most cited first, 11 of 11)

- [Glitch in the Matrix: A Large Scale Benchmark for Content Driven Audio-Visual Forgery Detection and Localization](https://mlsanity.com/paper/2305.01979/) (2023)
- [Learning Action Completeness from Points for Weakly-supervised Temporal Action Localization](https://mlsanity.com/paper/2108.05029/) (2021)
- [Graph Convolutional Module for Temporal Action Localization in Videos](https://mlsanity.com/paper/2112.00302/) (2021)
- [Large-scale Robustness Analysis of Video Action Recognition Models](https://mlsanity.com/paper/2207.01398/) (2022)
- [Learning to Refactor Action and Co-occurrence Features for Temporal Action Localization](https://mlsanity.com/paper/2206.11493/) (2022)
- [Decomposed Cross-modal Distillation for RGB-based Temporal Action Detection](https://mlsanity.com/paper/2303.17285/) (2023)
- [Multiscale Vision Transformers meet Bipartite Matching for efficient single-stage Action Localization](https://mlsanity.com/paper/2312.17686/) (2023)
- [1M-Deepfakes Detection Challenge](https://mlsanity.com/paper/2409.06991/) (2024)
- [Enhancing Temporal Action Localization: Advanced S6 Modeling with Recurrent Mechanism](https://mlsanity.com/paper/2407.13078/) (2024)
- [Do You Really Mean That? Content Driven Audio-Visual Deepfake Dataset and Multimodal Method for Temporal Forgery Localization](https://mlsanity.com/paper/2204.06228/) (2022)
- [TadML: A fast temporal action detection with Mechanics-MLP](https://mlsanity.com/paper/2206.02997/) (2022)

## Abstract (arXiv)

Temporal action localization is an important task of computer vision. Though a variety of methods have been proposed, it still remains an open question how to predict the temporal boundaries of action segments precisely. Most works use segment-level classifiers to select video segments pre-determined by action proposal or dense sliding windows. However, in order to achieve more precise action boundaries, a temporal localization system should make dense predictions at a fine granularity. A newly proposed work exploits Convolutional-Deconvolutional-Convolutional (CDC) filters to upsample the predictions of 3D ConvNets, making it possible to perform per-frame action predictions and achieving promising performance in terms of temporal action localization. However, CDC network loses temporal information partially due to the temporal downsampling operation. In this paper, we propose an elegant and powerful Temporal Preservation Convolutional (TPC) Network that equips 3D ConvNets with TPC filters. TPC network can fully preserve temporal resolution and downsample the spatial resolution simultaneously, enabling frame-level granularity action localization. TPC network can be trained in an end-to-end manner. Experiment results on public datasets show that TPC network achieves significant improvement on per-frame action prediction and competing results on segment-level temporal action localization.