# Referring Expression Comprehension on RefCOCO+ v1 (testB) Source: [Referring Expression Comprehension on RefCOCO+ v1 (testB)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:06:43.990Z Evaluation of Referring Expression Comprehension performance on the test-B split of the RefCOCO+ v1 dataset, 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) | RefCOCO+ v1 (testB) | | Metric | Top-1 Acc | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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 | 74.71 | Not recorded | 68fa72cd1e209131cea588c5 | | DQ-DETR | 73.21 | Not recorded | 68fa72cd1e209131cea588c5 | | HyperLearner | 72.64 | Not recorded | 68fa72cd1e209131cea588c5 | | MDETR | 70.62 | Not recorded | 68fa72cd1e209131cea588c5 | | RefTR | 68.99 | Not recorded | 68fa72cd1e209131cea588c5 | | HyperLearner | 57.54 | Not recorded | 68fa72cd1e209131cea588c5 | | Grounding-DINO-T | 56.09 | Not recorded | 68fa72cd1e209131cea588c5 | | MAttNet | 56.02 | Not recorded | 68fa72cd1e209131cea588c5 | | Grounding-DINO-T | 45.81 | Not recorded | 68fa72cd1e209131cea588c5 | | HyperLearner | 45.43 | Not recorded | 68fa72cd1e209131cea588c5 | | GLIP-T(C) | 44.59 | Not recorded | 68fa72cd1e209131cea588c5 | | GLIP-T(B) | 43.42 | Not recorded | 68fa72cd1e209131cea588c5 | ### Grounding-DINO-T Top-1 Acc: 74.71. Result ID: 69927c183a6c3148490f484c. [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: 73.21. Result ID: 69927c183a6c3148490f4847. [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: 72.64. Result ID: 69927c183a6c3148490f484f. [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: 70.62. Result ID: 69927c183a6c3148490f4846. [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: 68.99. Result ID: 69927c183a6c3148490f4845. [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: 57.54. Result ID: 69927c183a6c3148490f484e. [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: 56.09. Result ID: 69927c183a6c3148490f484b. [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. ### MAttNet Top-1 Acc: 56.02. Result ID: 69927c183a6c3148490f4844. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training Data":"RefC","Fine-tuning":true}. This record does not assert independent reproduction. ### Grounding-DINO-T Top-1 Acc: 45.81. Result ID: 69927c183a6c3148490f484a. [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: 45.43. Result ID: 69927c183a6c3148490f484d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-training Data":"O365, GoldG","Fine-tuning":false}. This record does not assert independent reproduction. ### GLIP-T(C) Top-1 Acc: 44.59. Result ID: 69927c183a6c3148490f4849. [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: 43.42. Result ID: 69927c183a6c3148490f4848. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training Data":"O365, GoldG","Fine-tuning":false}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.