{"task":"Multispectral Object Detection","dataset":"FLIR","metric_names":["mAP50","mAP"],"rows":[{"id":127872,"task":"Multispectral Object Detection","parent_task":null,"dataset":"FLIR","model_name":"MMPedestron","metrics":{"mAP50":"86.4%"},"paper_url":"https://arxiv.org/abs/2407.10125v1","paper_title":"When Pedestrian Detection Meets Multi-Modal Learning: Generalist Model and Benchmark Dataset","paper_date":"2024-07-14","code_links":[{"title":"BubblyYi/MMPedestron","url":"https://github.com/BubblyYi/MMPedestron"}],"metrics_order":"[\"mAP50\", \"mAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":127873,"task":"Multispectral Object Detection","parent_task":null,"dataset":"FLIR","model_name":"RGB-X Scene Adaptive CBAM","metrics":{"mAP":"47.1%","mAP50":"86.16%"},"paper_url":"https://arxiv.org/abs/2310.19372v1","paper_title":"RGB-X Object Detection via Scene-Specific Fusion Modules","paper_date":"2023-10-30","code_links":[{"title":"dsriaditya999/rgbxfusion","url":"https://github.com/dsriaditya999/rgbxfusion"}],"metrics_order":"[\"mAP50\", \"mAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":127874,"task":"Multispectral Object Detection","parent_task":null,"dataset":"FLIR","model_name":"CAFF-DINO","metrics":{"mAP":"50.5%","mAP50":"85.5%"},"paper_url":"https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=10678534","paper_title":"CAFF-DINO: Multi-spectral object detection transformers with cross-attention features fusion","paper_date":"2024-09-27","code_links":[],"metrics_order":"[\"mAP50\", \"mAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":127875,"task":"Multispectral Object Detection","parent_task":null,"dataset":"FLIR","model_name":"RSDet","metrics":{"mAP":"43.8%","mAP50":"83.9%"},"paper_url":"https://arxiv.org/abs/2401.10731v6","paper_title":"Removal then Selection: A Coarse-to-Fine Fusion Perspective for RGB-Infrared Object Detection","paper_date":"2024-01-19","code_links":[{"title":"Zhao-Tian-yi/RSDet","url":"https://github.com/Zhao-Tian-yi/RSDet"}],"metrics_order":"[\"mAP50\", \"mAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":127876,"task":"Multispectral Object Detection","parent_task":null,"dataset":"FLIR","model_name":"CMX","metrics":{"mAP50":"82.2%"},"paper_url":"https://arxiv.org/abs/2203.04838v5","paper_title":"CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers","paper_date":"2022-03-09","code_links":[{"title":"huaaaliu/rgbx_semantic_segmentation","url":"https://github.com/huaaaliu/rgbx_semantic_segmentation"}],"metrics_order":"[\"mAP50\", \"mAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":127877,"task":"Multispectral Object Detection","parent_task":null,"dataset":"FLIR","model_name":"UniRGB-IR","metrics":{"mAP":"44.1%","mAP50":"81.4%"},"paper_url":"https://arxiv.org/abs/2404.17360v2","paper_title":"UniRGB-IR: A Unified Framework for RGB-Infrared Semantic Tasks via Adapter Tuning","paper_date":"2024-04-26","code_links":[{"title":"potsui99/unirgb-ir","url":"https://github.com/potsui99/unirgb-ir"}],"metrics_order":"[\"mAP50\", \"mAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":127878,"task":"Multispectral Object Detection","parent_task":null,"dataset":"FLIR","model_name":"MiPa","metrics":{"mAP":"44.8%","mAP50":"81.3%"},"paper_url":"https://arxiv.org/abs/2404.18849v2","paper_title":"MiPa: Mixed Patch Infrared-Visible Modality Agnostic Object Detection","paper_date":"2024-04-29","code_links":[{"title":"heitorrapela/mipa","url":"https://github.com/heitorrapela/mipa"}],"metrics_order":"[\"mAP50\", \"mAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":127879,"task":"Multispectral Object Detection","parent_task":null,"dataset":"FLIR","model_name":"CSSA","metrics":{"mAP":"41.3%","mAP50":"79.2%"},"paper_url":"https://openaccess.thecvf.com/content/CVPR2023W/PBVS/html/Cao_Multimodal_Object_Detection_by_Channel_Switching_and_Spatial_Attention_CVPRW_2023_paper.html","paper_title":"Multimodal Object Detection by Channel Switching and Spatial Attention","paper_date":"2023-06-18","code_links":[],"metrics_order":"[\"mAP50\", \"mAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":127880,"task":"Multispectral Object Detection","parent_task":null,"dataset":"FLIR","model_name":"CFT","metrics":{"mAP50":"77.7%"},"paper_url":"https://arxiv.org/abs/2111.00273v4","paper_title":"Cross-Modality Fusion Transformer for Multispectral Object Detection","paper_date":"2021-10-30","code_links":[{"title":"docf/multispectral-object-detection","url":"https://github.com/docf/multispectral-object-detection"}],"metrics_order":"[\"mAP50\", \"mAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":127881,"task":"Multispectral Object Detection","parent_task":null,"dataset":"FLIR","model_name":"ProbEn","metrics":{"mAP":"37.9%","mAP50":"75.5%"},"paper_url":"https://openaccess.thecvf.com/content/CVPR2023W/PBVS/html/Cao_Multimodal_Object_Detection_by_Channel_Switching_and_Spatial_Attention_CVPRW_2023_paper.html","paper_title":"Multimodal Object Detection by Channel Switching and Spatial Attention","paper_date":"2023-06-18","code_links":[],"metrics_order":"[\"mAP50\", \"mAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":127882,"task":"Multispectral Object Detection","parent_task":null,"dataset":"FLIR","model_name":"GAFF","metrics":{"mAP":"37.4%","mAP50":"74.6%"},"paper_url":"https://openaccess.thecvf.com/content/CVPR2023W/PBVS/html/Cao_Multimodal_Object_Detection_by_Channel_Switching_and_Spatial_Attention_CVPRW_2023_paper.html","paper_title":"Multimodal Object Detection by Channel Switching and Spatial Attention","paper_date":"2023-06-18","code_links":[],"metrics_order":"[\"mAP50\", \"mAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":127883,"task":"Multispectral Object Detection","parent_task":null,"dataset":"FLIR","model_name":"YOLOv5 (T)","metrics":{"mAP50":"73.9%"},"paper_url":"https://arxiv.org/abs/2111.00273v4","paper_title":"Cross-Modality Fusion Transformer for Multispectral Object Detection","paper_date":"2021-10-30","code_links":[{"title":"docf/multispectral-object-detection","url":"https://github.com/docf/multispectral-object-detection"}],"metrics_order":"[\"mAP50\", \"mAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":127884,"task":"Multispectral Object Detection","parent_task":null,"dataset":"FLIR","model_name":"GAFF (ResNet18)","metrics":{"mAP50":"72.9%"},"paper_url":"https://openaccess.thecvf.com/content/WACV2021/papers/Zhang_Guided_Attentive_Feature_Fusion_for_Multispectral_Pedestrian_Detection_WACV_2021_paper.pdf","paper_title":"Guided Attentive Feature Fusion for Multispectral Pedestrian Detection","paper_date":"2021-01-03","code_links":[{"title":"ZHANGHeng19931123/GAFF","url":"https://github.com/ZHANGHeng19931123/GAFF"}],"metrics_order":"[\"mAP50\", \"mAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":127885,"task":"Multispectral Object Detection","parent_task":null,"dataset":"FLIR","model_name":"GAFF (VGG16)","metrics":{"mAP50":"72.7%"},"paper_url":"https://openaccess.thecvf.com/content/WACV2021/papers/Zhang_Guided_Attentive_Feature_Fusion_for_Multispectral_Pedestrian_Detection_WACV_2021_paper.pdf","paper_title":"Guided Attentive Feature Fusion for Multispectral Pedestrian Detection","paper_date":"2021-01-03","code_links":[{"title":"ZHANGHeng19931123/GAFF","url":"https://github.com/ZHANGHeng19931123/GAFF"}],"metrics_order":"[\"mAP50\", \"mAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":127886,"task":"Multispectral Object Detection","parent_task":null,"dataset":"FLIR","model_name":"CFR_3 (VGG16)","metrics":{"mAP50":"72.4%"},"paper_url":"https://arxiv.org/abs/2009.12664v1","paper_title":"Multispectral Fusion for Object Detection with Cyclic Fuse-and-Refine Blocks","paper_date":"2020-09-26","code_links":[{"title":"ZHANGHeng19931123/CFR","url":"https://github.com/ZHANGHeng19931123/CFR"}],"metrics_order":"[\"mAP50\", \"mAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":127887,"task":"Multispectral Object Detection","parent_task":null,"dataset":"FLIR","model_name":"Halfway Fusion (VGG16)","metrics":{"mAP50":"71.2%"},"paper_url":"https://arxiv.org/abs/2009.12664v1","paper_title":"Multispectral Fusion for Object Detection with Cyclic Fuse-and-Refine Blocks","paper_date":"2020-09-26","code_links":[{"title":"ZHANGHeng19931123/CFR","url":"https://github.com/ZHANGHeng19931123/CFR"}],"metrics_order":"[\"mAP50\", \"mAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":127888,"task":"Multispectral Object Detection","parent_task":null,"dataset":"FLIR","model_name":"YOLOv5 (RGB)","metrics":{"mAP50":"67.8%"},"paper_url":"https://arxiv.org/abs/2111.00273v4","paper_title":"Cross-Modality Fusion Transformer for Multispectral Object Detection","paper_date":"2021-10-30","code_links":[{"title":"docf/multispectral-object-detection","url":"https://github.com/docf/multispectral-object-detection"}],"metrics_order":"[\"mAP50\", \"mAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":127889,"task":"Multispectral Object Detection","parent_task":null,"dataset":"FLIR","model_name":"Halfway Fusion","metrics":{"mAP":"35.8%"},"paper_url":"https://openaccess.thecvf.com/content/CVPR2023W/PBVS/html/Cao_Multimodal_Object_Detection_by_Channel_Switching_and_Spatial_Attention_CVPRW_2023_paper.html","paper_title":"Multimodal Object Detection by Channel Switching and Spatial Attention","paper_date":"2023-06-18","code_links":[],"metrics_order":"[\"mAP50\", \"mAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]}]}