# Skimming and Scanning for Untrimmed Video Action Recognition

arXiv: https://arxiv.org/abs/2104.10492 · HTML: https://mlsanity.com/paper/2104.10492/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 34 references that are in the map.
- First posted on arXiv 21 Apr 2021.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://mlsanity.com/paper/1711.11248/) (2017)
- [Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?](https://mlsanity.com/paper/1711.09577/) (2017)
- [Temporal Convolutional Networks for Action Segmentation and Detection](https://mlsanity.com/paper/1611.05267/) (2016)
- [Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks](https://mlsanity.com/paper/1711.10305/) (2017)
- [Video Classification with Channel-Separated Convolutional Networks](https://mlsanity.com/paper/1904.02811/) (2019)
- [Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition](https://mlsanity.com/paper/1708.07632/) (2017)
- [Listen to Look: Action Recognition by Previewing Audio](https://mlsanity.com/paper/1912.04487/) (2019)
- [Explainable Reinforcement Learning: A Survey](https://mlsanity.com/paper/2005.06247/) (2020)
- [AdaFrame: Adaptive Frame Selection for Fast Video Recognition](https://mlsanity.com/paper/1811.12432/) (2018)
- [SCSampler: Sampling Salient Clips from Video for Efficient Action Recognition](https://mlsanity.com/paper/1904.04289/) (2019)
- [ECO: Efficient Convolutional Network for Online Video Understanding](https://mlsanity.com/paper/1804.09066/) (2018)
- [SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach](https://mlsanity.com/paper/2007.09389/) (2020)
- [Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data](https://mlsanity.com/paper/1709.07902/) (2017)
- [AR-Net: Adaptive Frame Resolution for Efficient Action Recognition](https://mlsanity.com/paper/2007.15796/) (2020)
- [Multi-Agent Reinforcement Learning Based Frame Sampling for Effective Untrimmed Video Recognition](https://mlsanity.com/paper/1907.13369/) (2019)
- [LiteEval: A Coarse-to-Fine Framework for Resource Efficient Video Recognition](https://mlsanity.com/paper/1912.01601/) (2019)
- [Resource Efficient 3D Convolutional Neural Networks](https://mlsanity.com/paper/1904.02422/) (2019)
- [Exploiting Feature and Class Relationships in Video Categorization with Regularized Deep Neural Networks](https://mlsanity.com/paper/1502.07209/) (2015)
- [Would Mega-scale Datasets Further Enhance Spatiotemporal 3D CNNs?](https://mlsanity.com/paper/2004.04968/) (2020)
- [A Commentary on the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/2007.14184/) (2020)

## Abstract (arXiv)

Video action recognition (VAR) is a primary task of video understanding, and untrimmed videos are more common in real-life scenes. Untrimmed videos have redundant and diverse clips containing contextual information, so sampling dense clips is essential. Recently, some works attempt to train a generic model to select the N most representative clips. However, it is difficult to model the complex relations from intra-class clips and inter-class videos within a single model and fixed selected number, and the entanglement of multiple relations is also hard to explain. Thus, instead of "only look once", we argue "divide and conquer" strategy will be more suitable in untrimmed VAR. Inspired by the speed reading mechanism, we propose a simple yet effective clip-level solution based on skim-scan techniques. Specifically, the proposed Skim-Scan framework first skims the entire video and drops those uninformative and misleading clips. For the remaining clips, it scans clips with diverse features gradually to drop redundant clips but cover essential content. The above strategies can adaptively select the necessary clips according to the difficulty of the different videos. To trade off the computational complexity and performance, we observe the similar statistical expression between lightweight and heavy networks, thus it supports us to explore the combination of them. Comprehensive experiments are performed on ActivityNet and mini-FCVID datasets, and results demonstrate that our solution surpasses the state-of-the-art performance in terms of both accuracy and efficiency.