# Referring Expression Comprehension on RefCOCOg v1 (val) Source: [Referring Expression Comprehension on RefCOCOg v1 (val)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:06:44.008Z Evaluation of Referring Expression Comprehension performance on the validation split (v1) of the RefCOCOg dataset, typically measured using Top-1 accuracy. 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 | Referring Expression Comprehension | | Dataset (including any stated split) | RefCOCOg v1 (val) | | Metric | Top-1 Acc | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 13 of 13 | | 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 - [Top-1 Acc](): Higher is better; unit: PERCENT. ## Recorded results | Method | Top-1 Acc | Result date | Report paper | | --- | --- | --- | --- | | Grounding-DINO-T | 84.15 | Not recorded | 68fa72cd1e209131cea588c5 | | DQ-DETR | 82.76 | Not recorded | 68fa72cd1e209131cea588c5 | | HyperLearner | 82.53 | Not recorded | 68fa72cd1e209131cea588c5 | | MDETR | 81.64 | Not recorded | 68fa72cd1e209131cea588c5 | | RefTR | 79.25 | Not recorded | 68fa72cd1e209131cea588c5 | | HyperLearner | 77 | Not recorded | 68fa72cd1e209131cea588c5 | | Grounding-DINO-T | 71.06 | Not recorded | 68fa72cd1e209131cea588c5 | | Grounding-DINO-T | 67.46 | Not recorded | 68fa72cd1e209131cea588c5 | | HyperLearner | 67.02 | Not recorded | 68fa72cd1e209131cea588c5 | | MAttNet | 66.58 | Not recorded | 68fa72cd1e209131cea588c5 | | GLIP-T(C) | 66.09 | Not recorded | 68fa72cd1e209131cea588c5 | | GLIP-T(B) | 65.58 | Not recorded | 68fa72cd1e209131cea588c5 | | CNN-LSTM | 62.14 | Not recorded | 68fa72cd1e209131cea588c5 | ### Grounding-DINO-T Top-1 Acc: 84.15. Result ID: 69927c183a6c3148490f4859. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training Data":"O365, GoldG, RefC","Fine-tuning":true}. This record does not assert independent reproduction. ### DQ-DETR Top-1 Acc: 82.76. Result ID: 69927c183a6c3148490f4854. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-training Data":"GoldG, RefC","Fine-tuning":true}. This record does not assert independent reproduction. ### HyperLearner Top-1 Acc: 82.53. Result ID: 69927c183a6c3148490f485c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-training Data":"O365, GoldG, RefC","Fine-tuning":true}. This record does not assert independent reproduction. ### MDETR Top-1 Acc: 81.64. Result ID: 69927c183a6c3148490f4853. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training Data":"GoldG, RefC","Fine-tuning":true}. This record does not assert independent reproduction. ### RefTR Top-1 Acc: 79.25. Result ID: 69927c183a6c3148490f4852. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-training Data":"VG","Fine-tuning":true}. This record does not assert independent reproduction. ### HyperLearner Top-1 Acc: 77. Result ID: 69927c183a6c3148490f485b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-training Data":"O365, GoldG, RefC","Fine-tuning":false}. This record does not assert independent reproduction. ### Grounding-DINO-T Top-1 Acc: 71.06. Result ID: 69927c183a6c3148490f4858. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training Data":"O365, GoldG, RefC","Fine-tuning":false}. This record does not assert independent reproduction. ### Grounding-DINO-T Top-1 Acc: 67.46. Result ID: 69927c183a6c3148490f4857. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training Data":"O365, GoldG","Fine-tuning":false}. This record does not assert independent reproduction. ### HyperLearner Top-1 Acc: 67.02. Result ID: 69927c183a6c3148490f485a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-training Data":"O365, GoldG","Fine-tuning":false}. This record does not assert independent reproduction. ### MAttNet Top-1 Acc: 66.58. Result ID: 69927c183a6c3148490f4851. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training Data":"RefC","Fine-tuning":true}. This record does not assert independent reproduction. ### GLIP-T(C) Top-1 Acc: 66.09. Result ID: 69927c183a6c3148490f4856. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training Data":"O365, GoldG, Cap4M","Fine-tuning":false}. This record does not assert independent reproduction. ### GLIP-T(B) Top-1 Acc: 65.58. Result ID: 69927c183a6c3148490f4855. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training Data":"O365, GoldG","Fine-tuning":false}. This record does not assert independent reproduction. ### CNN-LSTM Top-1 Acc: 62.14. Result ID: 69927c183a6c3148490f4850. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-training Data":"RefC","Fine-tuning":true}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.