TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Datasets/RefCOCO

RefCOCO

ImagesTextsUnknownIntroduced 2014-10-01

The RefCOCO dataset is a referring expression generation (REG) dataset used for tasks related to understanding natural language expressions that refer to specific objects in images. Here are the key details about RefCOCO:

  1. Collection Method: The dataset was collected using the ReferitGame, a two-player game. In this game, the first player views an image with a segmented target object and writes a natural language expression referring to that object. The second player sees only the image and the referring expression and must click on the corresponding object. If both players perform correctly, they earn points and switch roles; otherwise, they receive a new object and image for description.

  2. Dataset Variants: RefCOCO: Contains 142,209 refer expressions for 50,000 objects across 19,994 images. RefCOCO+: Includes 141,564 expressions for 49,856 objects in 19,992 images. RefCOCOg: This variant has 25,799 images, 95,010 referring expressions, and 49,822 object instances.

  3. Language and Restrictions: RefCOCO allows any type of language in the referring expressions. RefCOCO+ disallows location words in expressions to focus purely on appearance-based descriptions (e.g., "the man in the yellow polka-dotted shirt") rather than viewer-dependent descriptions (e.g., "the second man from the left").

These datasets serve as valuable resources for tasks like referring expression segmentation, comprehension, and visual grounding in computer vision research.

Benchmarks

Instance Segmentation/IoUInstance Segmentation/IoU (%)Referring Expression Segmentation/IoUReferring Expression Segmentation/IoU (%)

Related Benchmarks

RefCOCO testA/Instance Segmentation/Mean IoURefCOCO testA/Instance Segmentation/Overall IoURefCOCO testA/Instance Segmentation/mIoURefCOCO testA/Referring Expression Segmentation/Mean IoURefCOCO testA/Referring Expression Segmentation/Overall IoURefCOCO testA/Referring Expression Segmentation/mIoURefCOCO testA/Visual Grounding/IoURefCOCO testB/Instance Segmentation/Mean IoURefCOCO testB/Instance Segmentation/Overall IoURefCOCO testB/Instance Segmentation/mIoURefCOCO testB/Referring Expression Segmentation/Mean IoURefCOCO testB/Referring Expression Segmentation/Overall IoURefCOCO testB/Referring Expression Segmentation/mIoURefCOCO+ test B/Instance Segmentation/Mean IoURefCOCO+ test B/Instance Segmentation/Overall IoURefCOCO+ test B/Instance Segmentation/mIoURefCOCO+ test B/Referring Expression Segmentation/Mean IoURefCOCO+ test B/Referring Expression Segmentation/Overall IoURefCOCO+ test B/Referring Expression Segmentation/mIoURefCOCO+ test B/Visual Grounding/Accuracy (%)RefCOCO+ testA/Instance Segmentation/Mean IoURefCOCO+ testA/Instance Segmentation/Overall IoURefCOCO+ testA/Instance Segmentation/mIoURefCOCO+ testA/Referring Expression Segmentation/Mean IoURefCOCO+ testA/Referring Expression Segmentation/Overall IoURefCOCO+ testA/Referring Expression Segmentation/mIoURefCOCO+ testA/Visual Grounding/Accuracy (%)RefCOCO+ testA/Visual Grounding/IoURefCOCO+ val/Instance Segmentation/Mean IoURefCOCO+ val/Instance Segmentation/Overall IoURefCOCO+ val/Referring Expression Segmentation/Mean IoURefCOCO+ val/Referring Expression Segmentation/Overall IoURefCOCO+ val/Visual Grounding/Accuracy (%)RefCOCOg-test/Instance Segmentation/Mean IoURefCOCOg-test/Instance Segmentation/Overall IoURefCOCOg-test/Instance Segmentation/mIoURefCOCOg-test/Referring Expression Segmentation/Mean IoURefCOCOg-test/Referring Expression Segmentation/Overall IoURefCOCOg-test/Referring Expression Segmentation/mIoURefCOCOg-val/Instance Segmentation/IoURefCOCOg-val/Instance Segmentation/Mean IoURefCOCOg-val/Instance Segmentation/Overall IoURefCOCOg-val/Instance Segmentation/mIoURefCOCOg-val/Referring Expression Segmentation/IoURefCOCOg-val/Referring Expression Segmentation/Mean IoURefCOCOg-val/Referring Expression Segmentation/Overall IoURefCOCOg-val/Referring Expression Segmentation/mIoURefCoCo val/Instance Segmentation/Mean IoURefCoCo val/Instance Segmentation/Overall IoURefCoCo val/Instance Segmentation/Precision@0.5RefCoCo val/Instance Segmentation/Precision@0.6RefCoCo val/Instance Segmentation/Precision@0.7RefCoCo val/Instance Segmentation/Precision@0.8RefCoCo val/Instance Segmentation/Precision@0.9RefCoCo val/Instance Segmentation/mIoURefCoCo val/Referring Expression Segmentation/Mean IoURefCoCo val/Referring Expression Segmentation/Overall IoURefCoCo val/Referring Expression Segmentation/Precision@0.5RefCoCo val/Referring Expression Segmentation/Precision@0.6RefCoCo val/Referring Expression Segmentation/Precision@0.7RefCoCo val/Referring Expression Segmentation/Precision@0.8RefCoCo val/Referring Expression Segmentation/Precision@0.9RefCoCo val/Referring Expression Segmentation/mIoU

Statistics

Papers
439
Benchmarks
4

Links

Homepage

Tasks

Instance SegmentationReferring Expression ComprehensionReferring Expression SegmentationRegion ProposalSemantic SegmentationVisual GroundingVisual ReasoningZero-Shot Region Description