📊 Showing 5 results | 📏 Metric: Precision@(F1=1, IoU≥0.5)
| Rank | Model | Paper | Precision@(F1=1, IoU≥0.5) | Date | Code |
|---|---|---|---|---|---|
| 1 | SimVG-DB | SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion | 54.70 | 2024-09-26 | 📦 dmmm1997/simvg |
| 2 | UNINEXT | Universal Instance Perception as Object Discovery and Retrieval | 50.60 | 2023-03-12 | 📦 MasterBin-IIAU/UNINEXT |
| 3 | MDETR | MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding | 36.10 | 2021-04-26 | 📦 facebookresearch/multimodal 📦 ashkamath/mdetr 📦 thunlp/pevl 📦 b-faye/lightmdetr 📦 AleDella/mdter_eval |
| 4 | VLT | Vision-Language Transformer and Query Generation for Referring Segmentation | 35.20 | 2021-08-12 | 📦 henghuiding/Vision-Language-Transformer |
| 5 | MCN | Multi-task Collaborative Network for Joint Referring Expression Comprehension and Segmentation | 30.60 | 2020-03-19 | 📦 luogen1996/MCN 📦 xurige1995/3shnet |