{"task":"Referring Expression Segmentation","dataset":"RefCOCO+ testA","metric_names":["Overall IoU","Mean IoU","mIoU"],"rows":[{"id":86199,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO+ testA","model_name":"HyperSeg","metrics":{"Overall IoU":"83.5"},"paper_url":"https://arxiv.org/abs/2411.17606v2","paper_title":"HyperSeg: Towards Universal Visual Segmentation with Large Language Model","paper_date":"2024-11-26","code_links":[{"title":"congvvc/HyperSeg","url":"https://github.com/congvvc/HyperSeg"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":86200,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO+ testA","model_name":"MLCD-Seg-7B","metrics":{"Overall IoU":"82.9"},"paper_url":"https://arxiv.org/abs/2407.17331v2","paper_title":"Multi-label Cluster Discrimination for Visual Representation Learning","paper_date":"2024-07-24","code_links":[{"title":"deepglint/unicom","url":"https://github.com/deepglint/unicom"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":86201,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO+ testA","model_name":"DeRIS-L","metrics":{"Mean IoU":"83.74","Overall IoU":"82.34"},"paper_url":"https://arxiv.org/abs/2507.01738v1","paper_title":"DeRIS: Decoupling Perception and Cognition for Enhanced Referring Image Segmentation through Loopback Synergy","paper_date":"2025-07-02","code_links":[{"title":"Dmmm1997/DeRIS","url":"https://github.com/Dmmm1997/DeRIS"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86202,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO+ testA","model_name":"EVF-SAM","metrics":{"Overall IoU":"80"},"paper_url":"https://arxiv.org/abs/2406.20076v4","paper_title":"EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model","paper_date":"2024-06-28","code_links":[{"title":"hustvl/evf-sam","url":"https://github.com/hustvl/evf-sam"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":86203,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO+ testA","model_name":"DETRIS","metrics":{"Overall IoU":"78.6"},"paper_url":"https://arxiv.org/abs/2501.08580v1","paper_title":"Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation","paper_date":"2025-01-15","code_links":[{"title":"jiaqihuang01/detris","url":"https://github.com/jiaqihuang01/detris"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86204,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO+ testA","model_name":"UniLSeg-100","metrics":{"Overall IoU":"78.29"},"paper_url":"https://arxiv.org/abs/2312.01623v4","paper_title":"Universal Segmentation at Arbitrary Granularity with Language Instruction","paper_date":"2023-12-04","code_links":[{"title":"yongliu20/UniLSeg","url":"https://github.com/yongliu20/UniLSeg"},{"title":"workforai/UniLSeg","url":"https://github.com/workforai/UniLSeg"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":86205,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO+ testA","model_name":"C3VG","metrics":{"Overall IoU":"77.96"},"paper_url":"https://arxiv.org/abs/2501.06710v1","paper_title":"Multi-task Visual Grounding with Coarse-to-Fine Consistency Constraints","paper_date":"2025-01-12","code_links":[{"title":"dmmm1997/c3vg","url":"https://github.com/dmmm1997/c3vg"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86206,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO+ testA","model_name":"UniLSeg-20","metrics":{"Overall IoU":"77.02"},"paper_url":"https://arxiv.org/abs/2312.01623v4","paper_title":"Universal Segmentation at Arbitrary Granularity with Language Instruction","paper_date":"2023-12-04","code_links":[{"title":"yongliu20/UniLSeg","url":"https://github.com/yongliu20/UniLSeg"},{"title":"workforai/UniLSeg","url":"https://github.com/workforai/UniLSeg"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":86207,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO+ testA","model_name":"UNINEXT-H","metrics":{"Overall IoU":"76.42"},"paper_url":"https://arxiv.org/abs/2303.06674v2","paper_title":"Universal Instance Perception as Object Discovery and Retrieval","paper_date":"2023-03-12","code_links":[{"title":"MasterBin-IIAU/UNINEXT","url":"https://github.com/MasterBin-IIAU/UNINEXT"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":86208,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO+ testA","model_name":"MaskRIS (Swin-B, combined DB)","metrics":{"Overall IoU":"75.15"},"paper_url":"https://arxiv.org/abs/2411.19067v1","paper_title":"MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation","paper_date":"2024-11-28","code_links":[{"title":"naver-ai/maskris","url":"https://github.com/naver-ai/maskris"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86209,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO+ testA","model_name":"GROUNDHOG","metrics":{"Overall IoU":"75.0"},"paper_url":"https://arxiv.org/abs/2402.16846v2","paper_title":"GROUNDHOG: Grounding Large Language Models to Holistic Segmentation","paper_date":"2024-02-26","code_links":[],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":86210,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO+ testA","model_name":"PolyFormer-L","metrics":{"Mean IoU":"75.71","Overall IoU":"74.56"},"paper_url":"https://arxiv.org/abs/2302.07387v2","paper_title":"PolyFormer: Referring Image Segmentation as Sequential Polygon Generation","paper_date":"2023-02-14","code_links":[{"title":"amazon-science/polygon-transformer","url":"https://github.com/amazon-science/polygon-transformer"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":86211,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO+ testA","model_name":"SafaRi-B","metrics":{"Overall IoU":"74.53"},"paper_url":"https://arxiv.org/abs/2407.02389v1","paper_title":"SafaRi:Adaptive Sequence Transformer for Weakly Supervised Referring Expression Segmentation","paper_date":"2024-07-02","code_links":[],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86212,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO+ testA","model_name":"MaskRIS (Swin-B)","metrics":{"Mean IoU":"76.73","Overall IoU":"74.46"},"paper_url":"https://arxiv.org/abs/2411.19067v1","paper_title":"MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation","paper_date":"2024-11-28","code_links":[{"title":"naver-ai/maskris","url":"https://github.com/naver-ai/maskris"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86213,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO+ testA","model_name":"PolyFormer-B","metrics":{"Mean IoU":"74.51","Overall IoU":"72.89"},"paper_url":"https://arxiv.org/abs/2302.07387v2","paper_title":"PolyFormer: Referring Image Segmentation as Sequential Polygon Generation","paper_date":"2023-02-14","code_links":[{"title":"amazon-science/polygon-transformer","url":"https://github.com/amazon-science/polygon-transformer"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":86214,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO+ testA","model_name":"MagNet","metrics":{"Overall IoU":"71.32"},"paper_url":"https://arxiv.org/abs/2312.12198v2","paper_title":"Mask Grounding for Referring Image Segmentation","paper_date":"2023-12-19","code_links":[{"title":"yxchng/mask-grounding","url":"https://github.com/yxchng/mask-grounding"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86215,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO+ testA","model_name":"ReLA","metrics":{"Overall IoU":"71.02"},"paper_url":"https://arxiv.org/abs/2306.00968v1","paper_title":"GRES: Generalized Referring Expression Segmentation","paper_date":"2023-06-01","code_links":[{"title":"henghuiding/ReLA","url":"https://github.com/henghuiding/ReLA"},{"title":"henghuiding/grefcoco","url":"https://github.com/henghuiding/grefcoco"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86216,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO+ testA","model_name":"VLT","metrics":{"Overall IoU":"68.43"},"paper_url":"https://arxiv.org/abs/2210.15871v1","paper_title":"VLT: Vision-Language Transformer and Query Generation for Referring Segmentation","paper_date":"2022-10-28","code_links":[{"title":"henghuiding/Vision-Language-Transformer","url":"https://github.com/henghuiding/Vision-Language-Transformer"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86217,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO+ testA","model_name":"LAVT","metrics":{"Overall IoU":"68.38"},"paper_url":"https://arxiv.org/abs/2112.02244v2","paper_title":"LAVT: Language-Aware Vision Transformer for Referring Image Segmentation","paper_date":"2021-12-04","code_links":[{"title":"yz93/lavt-ris","url":"https://github.com/yz93/lavt-ris"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86218,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO+ testA","model_name":"CRIS","metrics":{"Overall IoU":"68.08"},"paper_url":"https://arxiv.org/abs/2111.15174v2","paper_title":"CRIS: CLIP-Driven Referring Image Segmentation","paper_date":"2021-11-30","code_links":[{"title":"DerrickWang005/CRIS.pytorch","url":"https://github.com/DerrickWang005/CRIS.pytorch"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86219,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO+ testA","model_name":"MaIL","metrics":{"Overall IoU":"65.92"},"paper_url":"https://arxiv.org/abs/2111.10747v2","paper_title":"MaIL: A Unified Mask-Image-Language Trimodal Network for Referring Image Segmentation","paper_date":"2021-11-21","code_links":[],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86220,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO+ testA","model_name":"VLT","metrics":{"Overall IoU":"59.20"},"paper_url":"https://arxiv.org/abs/2108.05565v1","paper_title":"Vision-Language Transformer and Query Generation for Referring Segmentation","paper_date":"2021-08-12","code_links":[{"title":"henghuiding/Vision-Language-Transformer","url":"https://github.com/henghuiding/Vision-Language-Transformer"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86221,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO+ testA","model_name":"SHNet","metrics":{"Overall IoU":"58.46"},"paper_url":"https://arxiv.org/abs/2104.10412v4","paper_title":"Comprehensive Multi-Modal Interactions for Referring Image Segmentation","paper_date":"2021-04-21","code_links":[{"title":"kanji95/SHNET","url":"https://github.com/kanji95/SHNET"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86222,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO+ testA","model_name":"CPMC","metrics":{"Overall IoU":"53.44"},"paper_url":"https://arxiv.org/abs/2010.00514v1","paper_title":"Referring Image Segmentation via Cross-Modal Progressive Comprehension","paper_date":"2020-10-01","code_links":[{"title":"spyflying/CMPC-Refseg","url":"https://github.com/spyflying/CMPC-Refseg"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86223,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO+ testA","model_name":"BRINet","metrics":{"Overall IoU":"52.87"},"paper_url":"http://openaccess.thecvf.com/content_CVPR_2020/html/Hu_Bi-Directional_Relationship_Inferring_Network_for_Referring_Image_Segmentation_CVPR_2020_paper.html","paper_title":"Bi-Directional Relationship Inferring Network for Referring Image Segmentation","paper_date":"2020-06-01","code_links":[],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86224,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO+ testA","model_name":"MattNet","metrics":{"Overall IoU":"52.39"},"paper_url":"http://arxiv.org/abs/1801.08186v3","paper_title":"MAttNet: Modular Attention Network for Referring Expression Comprehension","paper_date":"2018-01-24","code_links":[{"title":"lichengunc/MAttNet","url":"https://github.com/lichengunc/MAttNet"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86225,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO+ testA","model_name":"STEP (5-fold)","metrics":{"Overall IoU":"52.33"},"paper_url":"http://openaccess.thecvf.com/content_ICCV_2019/html/Chen_See-Through-Text_Grouping_for_Referring_Image_Segmentation_ICCV_2019_paper.html","paper_title":"See-Through-Text Grouping for Referring Image Segmentation","paper_date":"2019-10-01","code_links":[],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86226,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO+ testA","model_name":"RefVOS with BERT + MLM Loss","metrics":{"Overall IoU":"49.73"},"paper_url":"https://arxiv.org/abs/2010.00263v1","paper_title":"RefVOS: A Closer Look at Referring Expressions for Video Object Segmentation","paper_date":"2020-10-01","code_links":[{"title":"miriambellver/refvos","url":"https://github.com/miriambellver/refvos"},{"title":"imatge-upc/refvos","url":"https://github.com/imatge-upc/refvos"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86227,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO+ testA","model_name":"CMSA","metrics":{"Overall IoU":"47.60"},"paper_url":"http://arxiv.org/abs/1904.04745v1","paper_title":"Cross-Modal Self-Attention Network for Referring Image Segmentation","paper_date":"2019-04-09","code_links":[{"title":"lwye/CMSA-Net","url":"https://github.com/lwye/CMSA-Net"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86228,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO+ testA","model_name":"VATEX","metrics":{"mIoU":"74.41"},"paper_url":"https://arxiv.org/abs/2404.08590v2","paper_title":"Vision-Aware Text Features in Referring Image Segmentation: From Object Understanding to Context Understanding","paper_date":"2024-04-12","code_links":[{"title":"nero1342/VATEX","url":"https://github.com/nero1342/VATEX"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":106798,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO+ testA","model_name":"HyperSeg","metrics":{"Overall IoU":"83.5"},"paper_url":"https://arxiv.org/abs/2411.17606v2","paper_title":"HyperSeg: Towards Universal Visual Segmentation with Large Language Model","paper_date":"2024-11-26","code_links":[{"title":"congvvc/HyperSeg","url":"https://github.com/congvvc/HyperSeg"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":106799,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO+ testA","model_name":"MLCD-Seg-7B","metrics":{"Overall IoU":"82.9"},"paper_url":"https://arxiv.org/abs/2407.17331v2","paper_title":"Multi-label Cluster Discrimination for Visual Representation Learning","paper_date":"2024-07-24","code_links":[{"title":"deepglint/unicom","url":"https://github.com/deepglint/unicom"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":106800,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO+ testA","model_name":"DeRIS-L","metrics":{"Mean IoU":"83.74","Overall IoU":"82.34"},"paper_url":"https://arxiv.org/abs/2507.01738v1","paper_title":"DeRIS: Decoupling Perception and Cognition for Enhanced Referring Image Segmentation through Loopback Synergy","paper_date":"2025-07-02","code_links":[{"title":"Dmmm1997/DeRIS","url":"https://github.com/Dmmm1997/DeRIS"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":106801,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO+ testA","model_name":"EVF-SAM","metrics":{"Overall IoU":"80"},"paper_url":"https://arxiv.org/abs/2406.20076v4","paper_title":"EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model","paper_date":"2024-06-28","code_links":[{"title":"hustvl/evf-sam","url":"https://github.com/hustvl/evf-sam"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":106802,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO+ testA","model_name":"DETRIS","metrics":{"Overall IoU":"78.6"},"paper_url":"https://arxiv.org/abs/2501.08580v1","paper_title":"Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation","paper_date":"2025-01-15","code_links":[{"title":"jiaqihuang01/detris","url":"https://github.com/jiaqihuang01/detris"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":106803,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO+ testA","model_name":"UniLSeg-100","metrics":{"Overall IoU":"78.29"},"paper_url":"https://arxiv.org/abs/2312.01623v4","paper_title":"Universal Segmentation at Arbitrary Granularity with Language Instruction","paper_date":"2023-12-04","code_links":[{"title":"yongliu20/UniLSeg","url":"https://github.com/yongliu20/UniLSeg"},{"title":"workforai/UniLSeg","url":"https://github.com/workforai/UniLSeg"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":106804,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO+ testA","model_name":"C3VG","metrics":{"Overall IoU":"77.96"},"paper_url":"https://arxiv.org/abs/2501.06710v1","paper_title":"Multi-task Visual Grounding with Coarse-to-Fine Consistency Constraints","paper_date":"2025-01-12","code_links":[{"title":"dmmm1997/c3vg","url":"https://github.com/dmmm1997/c3vg"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":106805,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO+ testA","model_name":"UniLSeg-20","metrics":{"Overall IoU":"77.02"},"paper_url":"https://arxiv.org/abs/2312.01623v4","paper_title":"Universal Segmentation at Arbitrary Granularity with Language Instruction","paper_date":"2023-12-04","code_links":[{"title":"yongliu20/UniLSeg","url":"https://github.com/yongliu20/UniLSeg"},{"title":"workforai/UniLSeg","url":"https://github.com/workforai/UniLSeg"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":106806,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO+ testA","model_name":"UNINEXT-H","metrics":{"Overall IoU":"76.42"},"paper_url":"https://arxiv.org/abs/2303.06674v2","paper_title":"Universal Instance Perception as Object Discovery and Retrieval","paper_date":"2023-03-12","code_links":[{"title":"MasterBin-IIAU/UNINEXT","url":"https://github.com/MasterBin-IIAU/UNINEXT"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":106807,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO+ testA","model_name":"MaskRIS (Swin-B, combined DB)","metrics":{"Overall IoU":"75.15"},"paper_url":"https://arxiv.org/abs/2411.19067v1","paper_title":"MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation","paper_date":"2024-11-28","code_links":[{"title":"naver-ai/maskris","url":"https://github.com/naver-ai/maskris"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":106808,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO+ testA","model_name":"GROUNDHOG","metrics":{"Overall IoU":"75.0"},"paper_url":"https://arxiv.org/abs/2402.16846v2","paper_title":"GROUNDHOG: Grounding Large Language Models to Holistic Segmentation","paper_date":"2024-02-26","code_links":[],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":106809,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO+ testA","model_name":"PolyFormer-L","metrics":{"Mean IoU":"75.71","Overall IoU":"74.56"},"paper_url":"https://arxiv.org/abs/2302.07387v2","paper_title":"PolyFormer: Referring Image Segmentation as Sequential Polygon Generation","paper_date":"2023-02-14","code_links":[{"title":"amazon-science/polygon-transformer","url":"https://github.com/amazon-science/polygon-transformer"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":106810,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO+ testA","model_name":"SafaRi-B","metrics":{"Overall IoU":"74.53"},"paper_url":"https://arxiv.org/abs/2407.02389v1","paper_title":"SafaRi:Adaptive Sequence Transformer for Weakly Supervised Referring Expression Segmentation","paper_date":"2024-07-02","code_links":[],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":106811,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO+ testA","model_name":"MaskRIS (Swin-B)","metrics":{"Mean IoU":"76.73","Overall IoU":"74.46"},"paper_url":"https://arxiv.org/abs/2411.19067v1","paper_title":"MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation","paper_date":"2024-11-28","code_links":[{"title":"naver-ai/maskris","url":"https://github.com/naver-ai/maskris"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":106812,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO+ testA","model_name":"PolyFormer-B","metrics":{"Mean IoU":"74.51","Overall IoU":"72.89"},"paper_url":"https://arxiv.org/abs/2302.07387v2","paper_title":"PolyFormer: Referring Image Segmentation as Sequential Polygon Generation","paper_date":"2023-02-14","code_links":[{"title":"amazon-science/polygon-transformer","url":"https://github.com/amazon-science/polygon-transformer"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":106813,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO+ testA","model_name":"MagNet","metrics":{"Overall IoU":"71.32"},"paper_url":"https://arxiv.org/abs/2312.12198v2","paper_title":"Mask Grounding for Referring Image Segmentation","paper_date":"2023-12-19","code_links":[{"title":"yxchng/mask-grounding","url":"https://github.com/yxchng/mask-grounding"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":106814,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO+ testA","model_name":"ReLA","metrics":{"Overall IoU":"71.02"},"paper_url":"https://arxiv.org/abs/2306.00968v1","paper_title":"GRES: Generalized Referring Expression Segmentation","paper_date":"2023-06-01","code_links":[{"title":"henghuiding/ReLA","url":"https://github.com/henghuiding/ReLA"},{"title":"henghuiding/grefcoco","url":"https://github.com/henghuiding/grefcoco"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":106815,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO+ testA","model_name":"VLT","metrics":{"Overall IoU":"68.43"},"paper_url":"https://arxiv.org/abs/2210.15871v1","paper_title":"VLT: Vision-Language Transformer and Query Generation for Referring Segmentation","paper_date":"2022-10-28","code_links":[{"title":"henghuiding/Vision-Language-Transformer","url":"https://github.com/henghuiding/Vision-Language-Transformer"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":106816,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO+ testA","model_name":"LAVT","metrics":{"Overall IoU":"68.38"},"paper_url":"https://arxiv.org/abs/2112.02244v2","paper_title":"LAVT: Language-Aware Vision Transformer for Referring Image Segmentation","paper_date":"2021-12-04","code_links":[{"title":"yz93/lavt-ris","url":"https://github.com/yz93/lavt-ris"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":106817,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO+ testA","model_name":"CRIS","metrics":{"Overall IoU":"68.08"},"paper_url":"https://arxiv.org/abs/2111.15174v2","paper_title":"CRIS: CLIP-Driven Referring Image Segmentation","paper_date":"2021-11-30","code_links":[{"title":"DerrickWang005/CRIS.pytorch","url":"https://github.com/DerrickWang005/CRIS.pytorch"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":106818,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO+ testA","model_name":"MaIL","metrics":{"Overall IoU":"65.92"},"paper_url":"https://arxiv.org/abs/2111.10747v2","paper_title":"MaIL: A Unified Mask-Image-Language Trimodal Network for Referring Image Segmentation","paper_date":"2021-11-21","code_links":[],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":106819,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO+ testA","model_name":"VLT","metrics":{"Overall IoU":"59.20"},"paper_url":"https://arxiv.org/abs/2108.05565v1","paper_title":"Vision-Language Transformer and Query Generation for Referring Segmentation","paper_date":"2021-08-12","code_links":[{"title":"henghuiding/Vision-Language-Transformer","url":"https://github.com/henghuiding/Vision-Language-Transformer"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":106820,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO+ testA","model_name":"SHNet","metrics":{"Overall IoU":"58.46"},"paper_url":"https://arxiv.org/abs/2104.10412v4","paper_title":"Comprehensive Multi-Modal Interactions for Referring Image Segmentation","paper_date":"2021-04-21","code_links":[{"title":"kanji95/SHNET","url":"https://github.com/kanji95/SHNET"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":106821,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO+ testA","model_name":"CPMC","metrics":{"Overall IoU":"53.44"},"paper_url":"https://arxiv.org/abs/2010.00514v1","paper_title":"Referring Image Segmentation via Cross-Modal Progressive Comprehension","paper_date":"2020-10-01","code_links":[{"title":"spyflying/CMPC-Refseg","url":"https://github.com/spyflying/CMPC-Refseg"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":106822,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO+ testA","model_name":"BRINet","metrics":{"Overall IoU":"52.87"},"paper_url":"http://openaccess.thecvf.com/content_CVPR_2020/html/Hu_Bi-Directional_Relationship_Inferring_Network_for_Referring_Image_Segmentation_CVPR_2020_paper.html","paper_title":"Bi-Directional Relationship Inferring Network for Referring Image Segmentation","paper_date":"2020-06-01","code_links":[],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":106823,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO+ testA","model_name":"MattNet","metrics":{"Overall IoU":"52.39"},"paper_url":"http://arxiv.org/abs/1801.08186v3","paper_title":"MAttNet: Modular Attention Network for Referring Expression Comprehension","paper_date":"2018-01-24","code_links":[{"title":"lichengunc/MAttNet","url":"https://github.com/lichengunc/MAttNet"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":106824,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO+ testA","model_name":"STEP (5-fold)","metrics":{"Overall IoU":"52.33"},"paper_url":"http://openaccess.thecvf.com/content_ICCV_2019/html/Chen_See-Through-Text_Grouping_for_Referring_Image_Segmentation_ICCV_2019_paper.html","paper_title":"See-Through-Text Grouping for Referring Image Segmentation","paper_date":"2019-10-01","code_links":[],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":106825,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO+ testA","model_name":"RefVOS with BERT + MLM Loss","metrics":{"Overall IoU":"49.73"},"paper_url":"https://arxiv.org/abs/2010.00263v1","paper_title":"RefVOS: A Closer Look at Referring Expressions for Video Object Segmentation","paper_date":"2020-10-01","code_links":[{"title":"miriambellver/refvos","url":"https://github.com/miriambellver/refvos"},{"title":"imatge-upc/refvos","url":"https://github.com/imatge-upc/refvos"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":106826,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO+ testA","model_name":"CMSA","metrics":{"Overall IoU":"47.60"},"paper_url":"http://arxiv.org/abs/1904.04745v1","paper_title":"Cross-Modal Self-Attention Network for Referring Image Segmentation","paper_date":"2019-04-09","code_links":[{"title":"lwye/CMSA-Net","url":"https://github.com/lwye/CMSA-Net"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":106827,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO+ testA","model_name":"VATEX","metrics":{"mIoU":"74.41"},"paper_url":"https://arxiv.org/abs/2404.08590v2","paper_title":"Vision-Aware Text Features in Referring Image Segmentation: From Object Understanding to Context Understanding","paper_date":"2024-04-12","code_links":[{"title":"nero1342/VATEX","url":"https://github.com/nero1342/VATEX"}],"metrics_order":"[\"Overall IoU\", \"Mean IoU\", \"mIoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]}]}