ActivityNet-QA
Introduced by Yu et al. in ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering
The ActivityNet-QA dataset contains 58,000 human-annotated QA pairs on 5,800 videos derived from the popular ActivityNet dataset. The dataset provides a benchmark for testing the performance of VideoQA models on long-term spatio-temporal reasoning.
Source: ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question AnsweringBenchmarks
| Trend | Task | Dataset Variant | Best Model | Paper | Code |
|---|---|---|---|---|---|
|
ActivityNet-QA
|
GPT-2 + CLIP-14 + CLIP-multilingual
|
|||
|
ActivityNet-QA
|
PLLaVA
|
Papers
| Paper | Code | Results | Date | Stars |
|---|
