# Frame Question Answering on TGIF-QA Source: [Frame Question Answering on TGIF-QA]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:29:07.771Z Evaluation of model performance on the TGIF-QA dataset specifically for the Frame Question Answering task, reporting accuracy metrics. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Frame-QA | | Dataset (including any stated split) | TGIF-QA | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 14 of 14 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | MERLOT | 69.5 | Not recorded | 68fa70821e209131cea4b98b | | VGT | 61.6 | Not recorded | 68fa70821e209131cea4b98b | | ATM | 61.6 | Not recorded | 68fa70821e209131cea4b98b | | PGAT | 61.1 | Not recorded | 68fa70821e209131cea4b98b | | ClipBERT | 60.3 | Not recorded | 68fa70821e209131cea4b98b | | HAIR | 60.2 | Not recorded | 68fa70821e209131cea4b98b | | SiaSRea | 60.2 | Not recorded | 68fa70821e209131cea4b98b | | MASN | 59.5 | Not recorded | 68fa70821e209131cea4b98b | | MHN | 58.1 | Not recorded | 68fa70821e209131cea4b98b | | HOSTR | 58 | Not recorded | 68fa70821e209131cea4b98b | | B2A | 57.5 | Not recorded | 68fa70821e209131cea4b98b | | LGCN | 56.3 | Not recorded | 68fa70821e209131cea4b98b | | HCRN | 55.9 | Not recorded | 68fa70821e209131cea4b98b | | HGA | 55.1 | Not recorded | 68fa70821e209131cea4b98b | ### MERLOT Accuracy: 69.5. Result ID: 699146253a6c31484906f7f8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-trained with large-scale external data":true}. This record does not assert independent reproduction. ### VGT Accuracy: 61.6. Result ID: 699146253a6c31484906f7f9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-trained with large-scale external data":false}. This record does not assert independent reproduction. ### ATM Accuracy: 61.6. Result ID: 699146253a6c31484906f7fa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-trained with large-scale external data":false}. This record does not assert independent reproduction. ### PGAT Accuracy: 61.1. Result ID: 699146253a6c31484906f7f4. [Reporting paper]() Recorded evaluation configuration: {"Pre-trained with large-scale external data":false}. This record does not assert independent reproduction. ### ClipBERT Accuracy: 60.3. Result ID: 699146253a6c31484906f7f6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-trained with large-scale external data":true}. This record does not assert independent reproduction. ### HAIR Accuracy: 60.2. Result ID: 699146253a6c31484906f7f2. [Reporting paper]() Recorded evaluation configuration: {"Pre-trained with large-scale external data":false}. This record does not assert independent reproduction. ### SiaSRea Accuracy: 60.2. Result ID: 699146253a6c31484906f7f7. [Reporting paper]() Recorded evaluation configuration: {"Pre-trained with large-scale external data":true}. This record does not assert independent reproduction. ### MASN Accuracy: 59.5. Result ID: 699146253a6c31484906f7f3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-trained with large-scale external data":false}. This record does not assert independent reproduction. ### MHN Accuracy: 58.1. Result ID: 699146253a6c31484906f7f5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-trained with large-scale external data":false}. This record does not assert independent reproduction. ### HOSTR Accuracy: 58. Result ID: 699146253a6c31484906f7f1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-trained with large-scale external data":false}. This record does not assert independent reproduction. ### B2A Accuracy: 57.5. Result ID: 699146253a6c31484906f7f0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-trained with large-scale external data":false}. This record does not assert independent reproduction. ### LGCN Accuracy: 56.3. Result ID: 699146253a6c31484906f7ed. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-trained with large-scale external data":false}. This record does not assert independent reproduction. ### HCRN Accuracy: 55.9. Result ID: 699146253a6c31484906f7ef. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-trained with large-scale external data":false}. This record does not assert independent reproduction. ### HGA Accuracy: 55.1. Result ID: 699146253a6c31484906f7ee. [Reporting paper]() Recorded evaluation configuration: {"Pre-trained with large-scale external data":false}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.