{"task":"Referring Expression Segmentation","dataset":"RefCOCO","metric_names":["IoU","IoU (%)"],"rows":[{"id":85938,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO","model_name":"DETRIS","metrics":{"IoU":"81.0"},"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":"[\"IoU\", \"IoU (%)\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85939,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO","model_name":"GLEE-Pro","metrics":{"IoU":"80.0"},"paper_url":"https://arxiv.org/abs/2312.09158v1","paper_title":"General Object Foundation Model for Images and Videos at Scale","paper_date":"2023-12-14","code_links":[{"title":"FoundationVision/GLEE","url":"https://github.com/FoundationVision/GLEE"}],"metrics_order":"[\"IoU\", \"IoU (%)\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85940,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO","model_name":"EVP","metrics":{"IoU":"77.61","IoU (%)":"77.61"},"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":"[\"IoU\", \"IoU (%)\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85941,"task":"Referring Expression Segmentation","parent_task":"Instance Segmentation","dataset":"RefCOCO","model_name":"ETRIS","metrics":{"IoU":"71.06"},"paper_url":"https://arxiv.org/abs/2307.11545v1","paper_title":"Bridging Vision and Language Encoders: Parameter-Efficient Tuning for Referring Image Segmentation","paper_date":"2023-07-21","code_links":[{"title":"kkakkkka/etris","url":"https://github.com/kkakkkka/etris"}],"metrics_order":"[\"IoU\", \"IoU (%)\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":106537,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO","model_name":"DETRIS","metrics":{"IoU":"81.0"},"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":"[\"IoU\", \"IoU (%)\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":106538,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO","model_name":"GLEE-Pro","metrics":{"IoU":"80.0"},"paper_url":"https://arxiv.org/abs/2312.09158v1","paper_title":"General Object Foundation Model for Images and Videos at Scale","paper_date":"2023-12-14","code_links":[{"title":"FoundationVision/GLEE","url":"https://github.com/FoundationVision/GLEE"}],"metrics_order":"[\"IoU\", \"IoU (%)\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":106539,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO","model_name":"EVP","metrics":{"IoU":"77.61","IoU (%)":"77.61"},"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":"[\"IoU\", \"IoU (%)\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":106540,"task":"Referring Expression Segmentation","parent_task":null,"dataset":"RefCOCO","model_name":"ETRIS","metrics":{"IoU":"71.06"},"paper_url":"https://arxiv.org/abs/2307.11545v1","paper_title":"Bridging Vision and Language Encoders: Parameter-Efficient Tuning for Referring Image Segmentation","paper_date":"2023-07-21","code_links":[{"title":"kkakkkka/etris","url":"https://github.com/kkakkkka/etris"}],"metrics_order":"[\"IoU\", \"IoU (%)\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]}]}