Datasets › NExT-GQA
NExT-GQA
We study visually grounded VideoQA in response to the emerging trends of utilizing pretraining techniques for video-language understanding. Specifically, by forcing vision-language models (VLMs) to answer questions and simultaneously provide visual evidence, we seek to ascertain the extent to which the predictions of such techniques are genuinely anchored in relevant video content, versus spurious correlations from language or irrelevant visual context. Towards this, we construct NExT-GQA -- an extension of NExT-QA with 10.5K temporal grounding (or location) labels tied to the original QA pairs. With NExT-GQA, we scrutinize a variety of state-of-the-art VLMs. Through post-hoc attention analysis, we find that these models are weak in substantiating the answers despite their strong QA performance. This exposes a severe limitation of these models in making reliable predictions.
Benchmarks archive 2025-07-28
All 1 leaderboard whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.
| First row (archive order) | Paper | Code | ||||
|---|---|---|---|---|---|---|
| Zero-Shot Video Question Answer | NExT-GQA | DeVi (Gemini 2.0) Acc@GQA 28.9 | Question-Answering Dense Video Events | qhuni/deve-qa | 9 | Compare |
Papers archive 2025-07-28
6 shown of 6 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 23. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.
| Date | Samples run Syntology | |||
|---|---|---|---|---|
| VideoMind: A Chain-of-LoRA Agent for Long Video Reasoning | 1 | 2 | 17 Mar 2025 | ran 3 of 4 samples (1 unverified) |
| Question-Answering Dense Video Events | 1 | 2 | 6 Sep 2024 | not harvested |
| Streaming Long Video Understanding with Large Language Models | 0 | 1 | 25 May 2024 | not harvested |
| Language Repository for Long Video Understanding | 1 | 1 | 21 Mar 2024 | ran 9 of 9 samples (0 unverified) |
| A Simple LLM Framework for Long-Range Video Question-Answering | 1 | 2 | 28 Dec 2023 | ran 6 of 6 samples (0 unverified) |
| Mistral 7B | 6 | 1 | 10 Oct 2023 | ran 9 of 11 samples (2 unverified; 1 pointer-only for licence) |
Dataset loaders archive 2025-07-28
No loader listed in the archive.
Tasks archive 2025-07-28
License archive 2025-07-28
No licence recorded in the archive. Absence here is not a statement about the dataset's terms.
Modalities archive 2025-07-28
Languages archive 2025-07-28
No language tagged.
Variants archive 2025-07-28
- NExT-GQA
1 variant name, as the archive lists them.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections