TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Action Anticipation	Assembly101	TempAgg	Actions Recall@5	8.53	# 2
Action Anticipation	Assembly101	TempAgg	Verbs Recall@5	59.11	# 2
Action Anticipation	Assembly101	TempAgg	Objects Recall@5	26.27	# 2

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/temporal-aggregate-representations-for-long/action-anticipation-on-assembly101)](https://paperswithcode.com/sota/action-anticipation-on-assembly101?p=temporal-aggregate-representations-for-long)`

Temporal Aggregate Representations for Long-Range Video Understanding

ECCV 2020 · Fadime Sener, Dipika Singhania, Angela Yao ·

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.