HowMany-Qa is a object counting dataset. It is taken from the counting-specific union of VQA 2.0 (Goyal et al., 2017) and Visual Genome QA (Krishna et al., 2016).
Variants: HowMany-QA
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Object Counting | MoVie-ResNeXt | MoVie: Revisiting Modulated Convolutions for … | 2020-04-24 |
| Object Counting | MoVie | MoVie: Revisiting Modulated Convolutions for … | 2020-04-24 |
| Object Counting | RCN | TallyQA: Answering Complex Counting Questions | 2018-10-29 |
Recent papers with results on this dataset: