EgoTask QA benchmark contains 40K balanced question-answer pairs selected from 368K programmatically generated questions generated over 2K egocentric videos. It provides a single home for the crucial dimensions of task understanding through question-answering on real-world egocentric videos.
Source: EgoTaskQA: Understanding Human Tasks in Egocentric Videos
Image Source: https://arxiv.org/pdf/2210.03929.pdf
Variants: EgoTaskQA
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Question Answering | GF(sup) | Glance and Focus: Memory Prompting … | 2024-01-03 |
| Question Answering | GF(uns) | Glance and Focus: Memory Prompting … | 2024-01-03 |
| Question Answering | EgoVLPv2 | EgoVLPv2: Egocentric Video-Language Pre-training with … | 2023-07-11 |
| Question Answering | EgoVLP | Egocentric Video-Language Pretraining | 2022-06-03 |
Recent papers with results on this dataset: