# Temporal Aggregate Representations for Long-Range Video Understanding

arXiv: https://arxiv.org/abs/2006.00830 · HTML: https://mlsanity.com/paper/2006.00830/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jun 2020.

## Built on by (most cited first, 5 of 5)

- [Predicting the Future from First Person (Egocentric) Vision: A Survey](https://mlsanity.com/paper/2107.13411/) (2021)
- [TAMFormer: Multi-Modal Transformer with Learned Attention Mask for Early Intent Prediction](https://mlsanity.com/paper/2210.14714/) (2022)
- [Anticipating Next Active Objects for Egocentric Videos](https://mlsanity.com/paper/2302.06358/) (2023)
- [Untrimmed Action Anticipation](https://mlsanity.com/paper/2202.04132/) (2022)
- [Learning to Anticipate Future with Dynamic Context Removal](https://mlsanity.com/paper/2204.02587/) (2022)

## Abstract (arXiv)

Future prediction, especially in long-range videos, requires reasoning from current and past observations. In this work, we address questions of temporal extent, scaling, and level of semantic abstraction with a flexible multi-granular temporal aggregation framework. We show that it is possible to achieve state of the art in both next action and dense anticipation with simple techniques such as max-pooling and attention. To demonstrate the anticipation capabilities of our model, we conduct experiments on Breakfast, 50Salads, and EPIC-Kitchens datasets, where we achieve state-of-the-art results. With minimal modifications, our model can also be extended for video segmentation and action recognition.