# Pooled Motion Features for First-Person Videos

arXiv: https://arxiv.org/abs/1412.6505 · HTML: https://mlsanity.com/paper/1412.6505/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Dec 2014.

## Built on by (most cited first, 10 of 10)

- [Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language](https://mlsanity.com/paper/2204.00598/) (2022)
- [Self-Regulated Learning for Egocentric Video Activity Anticipation](https://mlsanity.com/paper/2111.11631/) (2021)
- [Sensor-Augmented Egocentric-Video Captioning with Dynamic Modal Attention](https://mlsanity.com/paper/2109.02955/) (2021)
- [Learning to Recognize Actions on Objects in Egocentric Video with Attention Dictionaries](https://mlsanity.com/paper/2102.08065/) (2021)
- [Discovering Novel Actions from Open World Egocentric Videos with Object-Grounded Visual Commonsense Reasoning](https://mlsanity.com/paper/2305.16602/) (2023)
- [Seeing without Pixels: Perception from Camera Trajectories](https://mlsanity.com/paper/2511.21681/) (2025)
- [ProbRes: Probabilistic Jump Diffusion for Open-World Egocentric Activity Recognition](https://mlsanity.com/paper/2504.03948/) (2025)
- [Free-Form Composition Networks for Egocentric Action Recognition](https://mlsanity.com/paper/2307.06527/) (2023)
- [Speeding Up Action Recognition Using Dynamic Accumulation of Residuals in Compressed Domain](https://mlsanity.com/paper/2209.14757/) (2022)
- [A Survey on Human Action Recognition](https://mlsanity.com/paper/2301.06082/) (2022)

## Abstract (arXiv)

In this paper, we present a new feature representation for first-person videos. In first-person video understanding (e.g., activity recognition), it is very important to capture both entire scene dynamics (i.e., egomotion) and salient local motion observed in videos. We describe a representation framework based on time series pooling, which is designed to abstract short-term/long-term changes in feature descriptor elements. The idea is to keep track of how descriptor values are changing over time and summarize them to represent motion in the activity video. The framework is general, handling any types of per-frame feature descriptors including conventional motion descriptors like histogram of optical flows (HOF) as well as appearance descriptors from more recent convolutional neural networks (CNN). We experimentally confirm that our approach clearly outperforms previous feature representations including bag-of-visual-words and improved Fisher vector (IFV) when using identical underlying feature descriptors. We also confirm that our feature representation has superior performance to existing state-of-the-art features like local spatio-temporal features and Improved Trajectory Features (originally developed for 3rd-person videos) when handling first-person videos. Multiple first-person activity datasets were tested under various settings to confirm these findings.