{"task":"Referring Expression Segmentation","dataset":"RefCOCO testB","metric_names":["Overall IoU","mIoU","Mean IoU"],"rows":[{"id":86000,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO testB","model_name":"HyperSeg","metrics":{"Overall IoU":"83.4"},"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\", \"mIoU\", \"Mean IoU\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":86001,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO testB","model_name":"DeRIS-L","metrics":{"Mean IoU":"84.52","Overall IoU":"82.87"},"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\", \"mIoU\", \"Mean IoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86002,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO testB","model_name":"MLCD-Seg-7B","metrics":{"Overall IoU":"81.5"},"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\", \"mIoU\", \"Mean IoU\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":86003,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO testB","model_name":"EVF-SAM","metrics":{"Overall IoU":"80.2"},"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\", \"mIoU\", \"Mean IoU\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":86004,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO testB","model_name":"DETRIS","metrics":{"Overall IoU":"79.0"},"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\", \"mIoU\", \"Mean IoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86005,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO testB","model_name":"C3VG","metrics":{"Overall IoU":"77.86"},"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\", \"mIoU\", \"Mean IoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86006,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO testB","model_name":"MaskRIS (Swin-B, combined DB)","metrics":{"Overall IoU":"75.1"},"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\", \"mIoU\", \"Mean IoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86007,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO testB","model_name":"MaskRIS (Swin-B)","metrics":{"Mean IoU":"76.06","Overall IoU":"73.96"},"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\", \"mIoU\", \"Mean IoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86008,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO testB","model_name":"EVP","metrics":{"Overall IoU":"72.94"},"paper_url":"https://arxiv.org/abs/2312.08548v1","paper_title":"EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment","paper_date":"2023-12-13","code_links":[{"title":"lavreniuk/evp","url":"https://github.com/lavreniuk/evp"}],"metrics_order":"[\"Overall IoU\", \"mIoU\", \"Mean IoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86009,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO testB","model_name":"MagNet","metrics":{"Overall IoU":"71.05"},"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\", \"mIoU\", \"Mean IoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86010,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO testB","model_name":"SafaRi","metrics":{"Overall IoU":"70.71"},"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\", \"mIoU\", \"Mean IoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86011,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO testB","model_name":"SeqTR","metrics":{"Overall IoU":" 64.12"},"paper_url":"https://arxiv.org/abs/2203.16265v2","paper_title":"SeqTR: A Simple yet Universal Network for Visual Grounding","paper_date":"2022-03-30","code_links":[{"title":"seanzhuh/seqtr","url":"https://github.com/seanzhuh/seqtr"},{"title":"sean-zhuh/seqtr","url":"https://github.com/sean-zhuh/seqtr"},{"title":"luogen1996/simrec","url":"https://github.com/luogen1996/simrec"}],"metrics_order":"[\"Overall IoU\", \"mIoU\", \"Mean IoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":86012,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO testB","model_name":"VATEX","metrics":{"mIoU":"75.64"},"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\", \"mIoU\", \"Mean IoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":106599,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO testB","model_name":"HyperSeg","metrics":{"Overall IoU":"83.4"},"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\", \"mIoU\", \"Mean IoU\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":106600,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO testB","model_name":"DeRIS-L","metrics":{"Mean IoU":"84.52","Overall IoU":"82.87"},"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\", \"mIoU\", \"Mean IoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":106601,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO testB","model_name":"MLCD-Seg-7B","metrics":{"Overall IoU":"81.5"},"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\", \"mIoU\", \"Mean IoU\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":106602,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO testB","model_name":"EVF-SAM","metrics":{"Overall IoU":"80.2"},"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\", \"mIoU\", \"Mean IoU\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":106603,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO testB","model_name":"DETRIS","metrics":{"Overall IoU":"79.0"},"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\", \"mIoU\", \"Mean IoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":106604,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO testB","model_name":"C3VG","metrics":{"Overall IoU":"77.86"},"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\", \"mIoU\", \"Mean IoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":106605,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO testB","model_name":"MaskRIS (Swin-B, combined DB)","metrics":{"Overall IoU":"75.1"},"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\", \"mIoU\", \"Mean IoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":106606,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO testB","model_name":"MaskRIS (Swin-B)","metrics":{"Mean IoU":"76.06","Overall IoU":"73.96"},"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\", \"mIoU\", \"Mean IoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":106607,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO testB","model_name":"EVP","metrics":{"Overall IoU":"72.94"},"paper_url":"https://arxiv.org/abs/2312.08548v1","paper_title":"EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment","paper_date":"2023-12-13","code_links":[{"title":"lavreniuk/evp","url":"https://github.com/lavreniuk/evp"}],"metrics_order":"[\"Overall IoU\", \"mIoU\", \"Mean IoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":106608,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO testB","model_name":"MagNet","metrics":{"Overall IoU":"71.05"},"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\", \"mIoU\", \"Mean IoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":106609,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO testB","model_name":"SafaRi","metrics":{"Overall IoU":"70.71"},"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\", \"mIoU\", \"Mean IoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":106610,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO testB","model_name":"SeqTR","metrics":{"Overall IoU":" 64.12"},"paper_url":"https://arxiv.org/abs/2203.16265v2","paper_title":"SeqTR: A Simple yet Universal Network for Visual Grounding","paper_date":"2022-03-30","code_links":[{"title":"seanzhuh/seqtr","url":"https://github.com/seanzhuh/seqtr"},{"title":"sean-zhuh/seqtr","url":"https://github.com/sean-zhuh/seqtr"},{"title":"luogen1996/simrec","url":"https://github.com/luogen1996/simrec"}],"metrics_order":"[\"Overall IoU\", \"mIoU\", \"Mean IoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":106611,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO testB","model_name":"VATEX","metrics":{"mIoU":"75.64"},"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\", \"mIoU\", \"Mean IoU\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]}]}