{"task":"Object Detection","dataset":"STCrowd","metric_names":["AP"],"rows":[{"id":62657,"task":"Object Detection","parent_task":null,"dataset":"STCrowd","model_name":"MMPedestron","metrics":{"AP":"74.9"},"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":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":62658,"task":"Object Detection","parent_task":null,"dataset":"STCrowd","model_name":"FPN-Fusion","metrics":{"AP":"61.5"},"paper_url":"https://hal.archives-ouvertes.fr/hal-03591717/","paper_title":"Fusing Event-based and RGB camera for Robust Object Detection in Adverse Conditions","paper_date":"2022-03-30","code_links":[{"title":"abhishek1411/event-rgb-fusion","url":"https://github.com/abhishek1411/event-rgb-fusion"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":62659,"task":"Object Detection","parent_task":null,"dataset":"STCrowd","model_name":"CMX","metrics":{"AP":"61.0"},"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":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":62660,"task":"Object Detection","parent_task":null,"dataset":"STCrowd","model_name":"ProbEN","metrics":{"AP":"60.0"},"paper_url":"https://arxiv.org/abs/2104.02904v3","paper_title":"Multimodal Object Detection via Probabilistic Ensembling","paper_date":"2021-04-07","code_links":[{"title":"Jamie725/Multimodal-Object-Detection-via-Probabilistic-Ensembling","url":"https://github.com/Jamie725/Multimodal-Object-Detection-via-Probabilistic-Ensembling"},{"title":"Jamie725/RGBT-detection","url":"https://github.com/Jamie725/RGBT-detection"},{"title":"aimerykong/RGBT-detection","url":"https://github.com/aimerykong/RGBT-detection"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":62661,"task":"Object Detection","parent_task":null,"dataset":"STCrowd","model_name":"Early-Fusion","metrics":{"AP":"54.4"},"paper_url":"http://arxiv.org/abs/1611.02644v1","paper_title":"Multispectral Deep Neural Networks for Pedestrian Detection","paper_date":"2016-11-08","code_links":[{"title":"SoonminHwang/rgbt-ped-detection","url":"https://github.com/SoonminHwang/rgbt-ped-detection"},{"title":"xuez-phd/tfdet","url":"https://github.com/xuez-phd/tfdet"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":62662,"task":"Object Detection","parent_task":null,"dataset":"STCrowd","model_name":"HRFuser","metrics":{"AP":"49.0"},"paper_url":"https://arxiv.org/abs/2206.15157v3","paper_title":"HRFuser: A Multi-resolution Sensor Fusion Architecture for 2D Object Detection","paper_date":"2022-06-30","code_links":[{"title":"timbroed/hrfuser","url":"https://github.com/timbroed/hrfuser"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":76636,"task":"Object Detection","parent_task":"3D","dataset":"STCrowd","model_name":"MMPedestron","metrics":{"AP":"74.9"},"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":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":76637,"task":"Object Detection","parent_task":"3D","dataset":"STCrowd","model_name":"FPN-Fusion","metrics":{"AP":"61.5"},"paper_url":"https://hal.archives-ouvertes.fr/hal-03591717/","paper_title":"Fusing Event-based and RGB camera for Robust Object Detection in Adverse Conditions","paper_date":"2022-03-30","code_links":[{"title":"abhishek1411/event-rgb-fusion","url":"https://github.com/abhishek1411/event-rgb-fusion"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":76638,"task":"Object Detection","parent_task":"3D","dataset":"STCrowd","model_name":"CMX","metrics":{"AP":"61.0"},"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":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":76639,"task":"Object Detection","parent_task":"3D","dataset":"STCrowd","model_name":"ProbEN","metrics":{"AP":"60.0"},"paper_url":"https://arxiv.org/abs/2104.02904v3","paper_title":"Multimodal Object Detection via Probabilistic Ensembling","paper_date":"2021-04-07","code_links":[{"title":"Jamie725/Multimodal-Object-Detection-via-Probabilistic-Ensembling","url":"https://github.com/Jamie725/Multimodal-Object-Detection-via-Probabilistic-Ensembling"},{"title":"Jamie725/RGBT-detection","url":"https://github.com/Jamie725/RGBT-detection"},{"title":"aimerykong/RGBT-detection","url":"https://github.com/aimerykong/RGBT-detection"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":76640,"task":"Object Detection","parent_task":"3D","dataset":"STCrowd","model_name":"Early-Fusion","metrics":{"AP":"54.4"},"paper_url":"http://arxiv.org/abs/1611.02644v1","paper_title":"Multispectral Deep Neural Networks for Pedestrian Detection","paper_date":"2016-11-08","code_links":[{"title":"SoonminHwang/rgbt-ped-detection","url":"https://github.com/SoonminHwang/rgbt-ped-detection"},{"title":"xuez-phd/tfdet","url":"https://github.com/xuez-phd/tfdet"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":76641,"task":"Object Detection","parent_task":"3D","dataset":"STCrowd","model_name":"HRFuser","metrics":{"AP":"49.0"},"paper_url":"https://arxiv.org/abs/2206.15157v3","paper_title":"HRFuser: A Multi-resolution Sensor Fusion Architecture for 2D Object Detection","paper_date":"2022-06-30","code_links":[{"title":"timbroed/hrfuser","url":"https://github.com/timbroed/hrfuser"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":117163,"task":"Object Detection","parent_task":"2D Classification","dataset":"STCrowd","model_name":"MMPedestron","metrics":{"AP":"74.9"},"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":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":117164,"task":"Object Detection","parent_task":"2D Classification","dataset":"STCrowd","model_name":"FPN-Fusion","metrics":{"AP":"61.5"},"paper_url":"https://hal.archives-ouvertes.fr/hal-03591717/","paper_title":"Fusing Event-based and RGB camera for Robust Object Detection in Adverse Conditions","paper_date":"2022-03-30","code_links":[{"title":"abhishek1411/event-rgb-fusion","url":"https://github.com/abhishek1411/event-rgb-fusion"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":117165,"task":"Object Detection","parent_task":"2D Classification","dataset":"STCrowd","model_name":"CMX","metrics":{"AP":"61.0"},"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":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":117166,"task":"Object Detection","parent_task":"2D Classification","dataset":"STCrowd","model_name":"ProbEN","metrics":{"AP":"60.0"},"paper_url":"https://arxiv.org/abs/2104.02904v3","paper_title":"Multimodal Object Detection via Probabilistic Ensembling","paper_date":"2021-04-07","code_links":[{"title":"Jamie725/Multimodal-Object-Detection-via-Probabilistic-Ensembling","url":"https://github.com/Jamie725/Multimodal-Object-Detection-via-Probabilistic-Ensembling"},{"title":"Jamie725/RGBT-detection","url":"https://github.com/Jamie725/RGBT-detection"},{"title":"aimerykong/RGBT-detection","url":"https://github.com/aimerykong/RGBT-detection"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":117167,"task":"Object Detection","parent_task":"2D Classification","dataset":"STCrowd","model_name":"Early-Fusion","metrics":{"AP":"54.4"},"paper_url":"http://arxiv.org/abs/1611.02644v1","paper_title":"Multispectral Deep Neural Networks for Pedestrian Detection","paper_date":"2016-11-08","code_links":[{"title":"SoonminHwang/rgbt-ped-detection","url":"https://github.com/SoonminHwang/rgbt-ped-detection"},{"title":"xuez-phd/tfdet","url":"https://github.com/xuez-phd/tfdet"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":117168,"task":"Object Detection","parent_task":"2D Classification","dataset":"STCrowd","model_name":"HRFuser","metrics":{"AP":"49.0"},"paper_url":"https://arxiv.org/abs/2206.15157v3","paper_title":"HRFuser: A Multi-resolution Sensor Fusion Architecture for 2D Object Detection","paper_date":"2022-06-30","code_links":[{"title":"timbroed/hrfuser","url":"https://github.com/timbroed/hrfuser"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":124239,"task":"Object Detection","parent_task":"2D Object Detection","dataset":"STCrowd","model_name":"MMPedestron","metrics":{"AP":"74.9"},"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":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":124240,"task":"Object Detection","parent_task":"2D Object Detection","dataset":"STCrowd","model_name":"FPN-Fusion","metrics":{"AP":"61.5"},"paper_url":"https://hal.archives-ouvertes.fr/hal-03591717/","paper_title":"Fusing Event-based and RGB camera for Robust Object Detection in Adverse Conditions","paper_date":"2022-03-30","code_links":[{"title":"abhishek1411/event-rgb-fusion","url":"https://github.com/abhishek1411/event-rgb-fusion"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":124241,"task":"Object Detection","parent_task":"2D Object Detection","dataset":"STCrowd","model_name":"CMX","metrics":{"AP":"61.0"},"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":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":124242,"task":"Object Detection","parent_task":"2D Object Detection","dataset":"STCrowd","model_name":"ProbEN","metrics":{"AP":"60.0"},"paper_url":"https://arxiv.org/abs/2104.02904v3","paper_title":"Multimodal Object Detection via Probabilistic Ensembling","paper_date":"2021-04-07","code_links":[{"title":"Jamie725/Multimodal-Object-Detection-via-Probabilistic-Ensembling","url":"https://github.com/Jamie725/Multimodal-Object-Detection-via-Probabilistic-Ensembling"},{"title":"Jamie725/RGBT-detection","url":"https://github.com/Jamie725/RGBT-detection"},{"title":"aimerykong/RGBT-detection","url":"https://github.com/aimerykong/RGBT-detection"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":124243,"task":"Object Detection","parent_task":"2D Object Detection","dataset":"STCrowd","model_name":"Early-Fusion","metrics":{"AP":"54.4"},"paper_url":"http://arxiv.org/abs/1611.02644v1","paper_title":"Multispectral Deep Neural Networks for Pedestrian Detection","paper_date":"2016-11-08","code_links":[{"title":"SoonminHwang/rgbt-ped-detection","url":"https://github.com/SoonminHwang/rgbt-ped-detection"},{"title":"xuez-phd/tfdet","url":"https://github.com/xuez-phd/tfdet"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":124244,"task":"Object Detection","parent_task":"2D Object Detection","dataset":"STCrowd","model_name":"HRFuser","metrics":{"AP":"49.0"},"paper_url":"https://arxiv.org/abs/2206.15157v3","paper_title":"HRFuser: A Multi-resolution Sensor Fusion Architecture for 2D Object Detection","paper_date":"2022-06-30","code_links":[{"title":"timbroed/hrfuser","url":"https://github.com/timbroed/hrfuser"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":149958,"task":"Object Detection","parent_task":"16k","dataset":"STCrowd","model_name":"MMPedestron","metrics":{"AP":"74.9"},"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":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":149959,"task":"Object Detection","parent_task":"16k","dataset":"STCrowd","model_name":"FPN-Fusion","metrics":{"AP":"61.5"},"paper_url":"https://hal.archives-ouvertes.fr/hal-03591717/","paper_title":"Fusing Event-based and RGB camera for Robust Object Detection in Adverse Conditions","paper_date":"2022-03-30","code_links":[{"title":"abhishek1411/event-rgb-fusion","url":"https://github.com/abhishek1411/event-rgb-fusion"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":149960,"task":"Object Detection","parent_task":"16k","dataset":"STCrowd","model_name":"CMX","metrics":{"AP":"61.0"},"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":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":149961,"task":"Object Detection","parent_task":"16k","dataset":"STCrowd","model_name":"ProbEN","metrics":{"AP":"60.0"},"paper_url":"https://arxiv.org/abs/2104.02904v3","paper_title":"Multimodal Object Detection via Probabilistic Ensembling","paper_date":"2021-04-07","code_links":[{"title":"Jamie725/Multimodal-Object-Detection-via-Probabilistic-Ensembling","url":"https://github.com/Jamie725/Multimodal-Object-Detection-via-Probabilistic-Ensembling"},{"title":"Jamie725/RGBT-detection","url":"https://github.com/Jamie725/RGBT-detection"},{"title":"aimerykong/RGBT-detection","url":"https://github.com/aimerykong/RGBT-detection"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":149962,"task":"Object Detection","parent_task":"16k","dataset":"STCrowd","model_name":"Early-Fusion","metrics":{"AP":"54.4"},"paper_url":"http://arxiv.org/abs/1611.02644v1","paper_title":"Multispectral Deep Neural Networks for Pedestrian Detection","paper_date":"2016-11-08","code_links":[{"title":"SoonminHwang/rgbt-ped-detection","url":"https://github.com/SoonminHwang/rgbt-ped-detection"},{"title":"xuez-phd/tfdet","url":"https://github.com/xuez-phd/tfdet"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":149963,"task":"Object Detection","parent_task":"16k","dataset":"STCrowd","model_name":"HRFuser","metrics":{"AP":"49.0"},"paper_url":"https://arxiv.org/abs/2206.15157v3","paper_title":"HRFuser: A Multi-resolution Sensor Fusion Architecture for 2D Object Detection","paper_date":"2022-06-30","code_links":[{"title":"timbroed/hrfuser","url":"https://github.com/timbroed/hrfuser"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]}]}