{"task":"Zero-Shot Object Detection","dataset":"MSCOCO","metric_names":["AP"],"rows":[{"id":65025,"task":"Zero-Shot Object Detection","parent_task":"Object Detection","dataset":"MSCOCO","model_name":"Grounding DINO 1.6 Pro (without COCO data)","metrics":{"AP":"55.4"},"paper_url":"https://arxiv.org/abs/2405.10300v2","paper_title":"Grounding DINO 1.5: Advance the \"Edge\" of Open-Set Object Detection","paper_date":"2024-05-16","code_links":[{"title":"mit-han-lab/efficientvit","url":"https://github.com/mit-han-lab/efficientvit"},{"title":"idea-research/grounded-sam-2","url":"https://github.com/idea-research/grounded-sam-2"},{"title":"idea-research/grounding-dino-1.5-api","url":"https://github.com/idea-research/grounding-dino-1.5-api"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":65026,"task":"Zero-Shot Object Detection","parent_task":"Object Detection","dataset":"MSCOCO","model_name":"CP-DETR-Pro((without COCO data))","metrics":{"AP":"55.4"},"paper_url":"https://arxiv.org/abs/2412.09799v1","paper_title":"CP-DETR: Concept Prompt Guide DETR Toward Stronger Universal Object Detection","paper_date":"2024-12-13","code_links":[],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":65027,"task":"Zero-Shot Object Detection","parent_task":"Object Detection","dataset":"MSCOCO","model_name":"Grounding DINO 1.5 Pro (without COCO data)","metrics":{"AP":"54.3"},"paper_url":"https://arxiv.org/abs/2405.10300v2","paper_title":"Grounding DINO 1.5: Advance the \"Edge\" of Open-Set Object Detection","paper_date":"2024-05-16","code_links":[{"title":"mit-han-lab/efficientvit","url":"https://github.com/mit-han-lab/efficientvit"},{"title":"idea-research/grounded-sam-2","url":"https://github.com/idea-research/grounded-sam-2"},{"title":"idea-research/grounding-dino-1.5-api","url":"https://github.com/idea-research/grounding-dino-1.5-api"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":65028,"task":"Zero-Shot Object Detection","parent_task":"Object Detection","dataset":"MSCOCO","model_name":"Grounding DINO-L (without COCO data)","metrics":{"AP":"52.5"},"paper_url":"https://arxiv.org/abs/2303.05499v5","paper_title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","paper_date":"2023-03-09","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"IDEA-Research/Grounded-Segment-Anything","url":"https://github.com/IDEA-Research/Grounded-Segment-Anything"},{"title":"idea-research/groundingdino","url":"https://github.com/idea-research/groundingdino"},{"title":"idea-research/grounded-sam-2","url":"https://github.com/idea-research/grounded-sam-2"},{"title":"idea-research/dino-x-api","url":"https://github.com/idea-research/dino-x-api"},{"title":"PaddlePaddle/PaddleMIX","url":"https://github.com/PaddlePaddle/PaddleMIX"},{"title":"longzw1997/Open-GroundingDino","url":"https://github.com/longzw1997/Open-GroundingDino"},{"title":"camenduru/grounded-segment-anything-colab","url":"https://github.com/camenduru/grounded-segment-anything-colab"},{"title":"hzlbbfrog/generative-bim","url":"https://github.com/hzlbbfrog/generative-bim"},{"title":"anthonyhuo/sam-dam-for-compositional-reasoning","url":"https://github.com/anthonyhuo/sam-dam-for-compositional-reasoning"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":65029,"task":"Zero-Shot Object Detection","parent_task":"Object Detection","dataset":"MSCOCO","model_name":"OV-DINO-T (without COCO data)","metrics":{"AP":"50.6"},"paper_url":"https://arxiv.org/abs/2407.07844v2","paper_title":"OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion","paper_date":"2024-07-10","code_links":[{"title":"wanghao9610/ov-dino","url":"https://github.com/wanghao9610/ov-dino"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":65030,"task":"Zero-Shot Object Detection","parent_task":"Object Detection","dataset":"MSCOCO","model_name":"YOLO-World-L(without COCO data)","metrics":{"AP":"45.1"},"paper_url":"https://arxiv.org/abs/2401.17270v3","paper_title":"YOLO-World: Real-Time Open-Vocabulary Object Detection","paper_date":"2024-01-30","code_links":[{"title":"ailab-cvc/yolo-world","url":"https://github.com/ailab-cvc/yolo-world"},{"title":"d-robotics-ai-lab/dosod","url":"https://github.com/d-robotics-ai-lab/dosod"},{"title":"ibaiGorordo/ONNX-YOLO-World-Open-Vocabulary-Object-Detection","url":"https://github.com/ibaiGorordo/ONNX-YOLO-World-Open-Vocabulary-Object-Detection"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":65031,"task":"Zero-Shot Object Detection","parent_task":"Object Detection","dataset":"MSCOCO","model_name":"Object-Centric-OVD","metrics":{"AP":"40.5"},"paper_url":"https://arxiv.org/abs/2207.03482v3","paper_title":"Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection","paper_date":"2022-07-07","code_links":[{"title":"mmaaz60/mvits_for_class_agnostic_od","url":"https://github.com/mmaaz60/mvits_for_class_agnostic_od"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":79004,"task":"Zero-Shot Object Detection","parent_task":"Object Detection","dataset":"MSCOCO","model_name":"Grounding DINO 1.6 Pro (without COCO data)","metrics":{"AP":"55.4"},"paper_url":"https://arxiv.org/abs/2405.10300v2","paper_title":"Grounding DINO 1.5: Advance the \"Edge\" of Open-Set Object Detection","paper_date":"2024-05-16","code_links":[{"title":"mit-han-lab/efficientvit","url":"https://github.com/mit-han-lab/efficientvit"},{"title":"idea-research/grounded-sam-2","url":"https://github.com/idea-research/grounded-sam-2"},{"title":"idea-research/grounding-dino-1.5-api","url":"https://github.com/idea-research/grounding-dino-1.5-api"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":79005,"task":"Zero-Shot Object Detection","parent_task":"Object Detection","dataset":"MSCOCO","model_name":"CP-DETR-Pro((without COCO data))","metrics":{"AP":"55.4"},"paper_url":"https://arxiv.org/abs/2412.09799v1","paper_title":"CP-DETR: Concept Prompt Guide DETR Toward Stronger Universal Object Detection","paper_date":"2024-12-13","code_links":[],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":79006,"task":"Zero-Shot Object Detection","parent_task":"Object Detection","dataset":"MSCOCO","model_name":"Grounding DINO 1.5 Pro (without COCO data)","metrics":{"AP":"54.3"},"paper_url":"https://arxiv.org/abs/2405.10300v2","paper_title":"Grounding DINO 1.5: Advance the \"Edge\" of Open-Set Object Detection","paper_date":"2024-05-16","code_links":[{"title":"mit-han-lab/efficientvit","url":"https://github.com/mit-han-lab/efficientvit"},{"title":"idea-research/grounded-sam-2","url":"https://github.com/idea-research/grounded-sam-2"},{"title":"idea-research/grounding-dino-1.5-api","url":"https://github.com/idea-research/grounding-dino-1.5-api"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":79007,"task":"Zero-Shot Object Detection","parent_task":"Object Detection","dataset":"MSCOCO","model_name":"Grounding DINO-L (without COCO data)","metrics":{"AP":"52.5"},"paper_url":"https://arxiv.org/abs/2303.05499v5","paper_title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","paper_date":"2023-03-09","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"IDEA-Research/Grounded-Segment-Anything","url":"https://github.com/IDEA-Research/Grounded-Segment-Anything"},{"title":"idea-research/groundingdino","url":"https://github.com/idea-research/groundingdino"},{"title":"idea-research/grounded-sam-2","url":"https://github.com/idea-research/grounded-sam-2"},{"title":"idea-research/dino-x-api","url":"https://github.com/idea-research/dino-x-api"},{"title":"PaddlePaddle/PaddleMIX","url":"https://github.com/PaddlePaddle/PaddleMIX"},{"title":"longzw1997/Open-GroundingDino","url":"https://github.com/longzw1997/Open-GroundingDino"},{"title":"camenduru/grounded-segment-anything-colab","url":"https://github.com/camenduru/grounded-segment-anything-colab"},{"title":"hzlbbfrog/generative-bim","url":"https://github.com/hzlbbfrog/generative-bim"},{"title":"anthonyhuo/sam-dam-for-compositional-reasoning","url":"https://github.com/anthonyhuo/sam-dam-for-compositional-reasoning"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":79008,"task":"Zero-Shot Object Detection","parent_task":"Object Detection","dataset":"MSCOCO","model_name":"OV-DINO-T (without COCO data)","metrics":{"AP":"50.6"},"paper_url":"https://arxiv.org/abs/2407.07844v2","paper_title":"OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion","paper_date":"2024-07-10","code_links":[{"title":"wanghao9610/ov-dino","url":"https://github.com/wanghao9610/ov-dino"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":79009,"task":"Zero-Shot Object Detection","parent_task":"Object Detection","dataset":"MSCOCO","model_name":"YOLO-World-L(without COCO data)","metrics":{"AP":"45.1"},"paper_url":"https://arxiv.org/abs/2401.17270v3","paper_title":"YOLO-World: Real-Time Open-Vocabulary Object Detection","paper_date":"2024-01-30","code_links":[{"title":"ailab-cvc/yolo-world","url":"https://github.com/ailab-cvc/yolo-world"},{"title":"d-robotics-ai-lab/dosod","url":"https://github.com/d-robotics-ai-lab/dosod"},{"title":"ibaiGorordo/ONNX-YOLO-World-Open-Vocabulary-Object-Detection","url":"https://github.com/ibaiGorordo/ONNX-YOLO-World-Open-Vocabulary-Object-Detection"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":79010,"task":"Zero-Shot Object Detection","parent_task":"Object Detection","dataset":"MSCOCO","model_name":"Object-Centric-OVD","metrics":{"AP":"40.5"},"paper_url":"https://arxiv.org/abs/2207.03482v3","paper_title":"Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection","paper_date":"2022-07-07","code_links":[{"title":"mmaaz60/mvits_for_class_agnostic_od","url":"https://github.com/mmaaz60/mvits_for_class_agnostic_od"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":119531,"task":"Zero-Shot Object Detection","parent_task":"Object Detection","dataset":"MSCOCO","model_name":"Grounding DINO 1.6 Pro (without COCO data)","metrics":{"AP":"55.4"},"paper_url":"https://arxiv.org/abs/2405.10300v2","paper_title":"Grounding DINO 1.5: Advance the \"Edge\" of Open-Set Object Detection","paper_date":"2024-05-16","code_links":[{"title":"mit-han-lab/efficientvit","url":"https://github.com/mit-han-lab/efficientvit"},{"title":"idea-research/grounded-sam-2","url":"https://github.com/idea-research/grounded-sam-2"},{"title":"idea-research/grounding-dino-1.5-api","url":"https://github.com/idea-research/grounding-dino-1.5-api"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":119532,"task":"Zero-Shot Object Detection","parent_task":"Object Detection","dataset":"MSCOCO","model_name":"CP-DETR-Pro((without COCO data))","metrics":{"AP":"55.4"},"paper_url":"https://arxiv.org/abs/2412.09799v1","paper_title":"CP-DETR: Concept Prompt Guide DETR Toward Stronger Universal Object Detection","paper_date":"2024-12-13","code_links":[],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":119533,"task":"Zero-Shot Object Detection","parent_task":"Object Detection","dataset":"MSCOCO","model_name":"Grounding DINO 1.5 Pro (without COCO data)","metrics":{"AP":"54.3"},"paper_url":"https://arxiv.org/abs/2405.10300v2","paper_title":"Grounding DINO 1.5: Advance the \"Edge\" of Open-Set Object Detection","paper_date":"2024-05-16","code_links":[{"title":"mit-han-lab/efficientvit","url":"https://github.com/mit-han-lab/efficientvit"},{"title":"idea-research/grounded-sam-2","url":"https://github.com/idea-research/grounded-sam-2"},{"title":"idea-research/grounding-dino-1.5-api","url":"https://github.com/idea-research/grounding-dino-1.5-api"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":119534,"task":"Zero-Shot Object Detection","parent_task":"Object Detection","dataset":"MSCOCO","model_name":"Grounding DINO-L (without COCO data)","metrics":{"AP":"52.5"},"paper_url":"https://arxiv.org/abs/2303.05499v5","paper_title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","paper_date":"2023-03-09","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"IDEA-Research/Grounded-Segment-Anything","url":"https://github.com/IDEA-Research/Grounded-Segment-Anything"},{"title":"idea-research/groundingdino","url":"https://github.com/idea-research/groundingdino"},{"title":"idea-research/grounded-sam-2","url":"https://github.com/idea-research/grounded-sam-2"},{"title":"idea-research/dino-x-api","url":"https://github.com/idea-research/dino-x-api"},{"title":"PaddlePaddle/PaddleMIX","url":"https://github.com/PaddlePaddle/PaddleMIX"},{"title":"longzw1997/Open-GroundingDino","url":"https://github.com/longzw1997/Open-GroundingDino"},{"title":"camenduru/grounded-segment-anything-colab","url":"https://github.com/camenduru/grounded-segment-anything-colab"},{"title":"hzlbbfrog/generative-bim","url":"https://github.com/hzlbbfrog/generative-bim"},{"title":"anthonyhuo/sam-dam-for-compositional-reasoning","url":"https://github.com/anthonyhuo/sam-dam-for-compositional-reasoning"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":119535,"task":"Zero-Shot Object Detection","parent_task":"Object Detection","dataset":"MSCOCO","model_name":"OV-DINO-T (without COCO data)","metrics":{"AP":"50.6"},"paper_url":"https://arxiv.org/abs/2407.07844v2","paper_title":"OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion","paper_date":"2024-07-10","code_links":[{"title":"wanghao9610/ov-dino","url":"https://github.com/wanghao9610/ov-dino"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":119536,"task":"Zero-Shot Object Detection","parent_task":"Object Detection","dataset":"MSCOCO","model_name":"YOLO-World-L(without COCO data)","metrics":{"AP":"45.1"},"paper_url":"https://arxiv.org/abs/2401.17270v3","paper_title":"YOLO-World: Real-Time Open-Vocabulary Object Detection","paper_date":"2024-01-30","code_links":[{"title":"ailab-cvc/yolo-world","url":"https://github.com/ailab-cvc/yolo-world"},{"title":"d-robotics-ai-lab/dosod","url":"https://github.com/d-robotics-ai-lab/dosod"},{"title":"ibaiGorordo/ONNX-YOLO-World-Open-Vocabulary-Object-Detection","url":"https://github.com/ibaiGorordo/ONNX-YOLO-World-Open-Vocabulary-Object-Detection"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":119537,"task":"Zero-Shot Object Detection","parent_task":"Object Detection","dataset":"MSCOCO","model_name":"Object-Centric-OVD","metrics":{"AP":"40.5"},"paper_url":"https://arxiv.org/abs/2207.03482v3","paper_title":"Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection","paper_date":"2022-07-07","code_links":[{"title":"mmaaz60/mvits_for_class_agnostic_od","url":"https://github.com/mmaaz60/mvits_for_class_agnostic_od"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":126607,"task":"Zero-Shot Object Detection","parent_task":"Object Detection","dataset":"MSCOCO","model_name":"Grounding DINO 1.6 Pro (without COCO data)","metrics":{"AP":"55.4"},"paper_url":"https://arxiv.org/abs/2405.10300v2","paper_title":"Grounding DINO 1.5: Advance the \"Edge\" of Open-Set Object Detection","paper_date":"2024-05-16","code_links":[{"title":"mit-han-lab/efficientvit","url":"https://github.com/mit-han-lab/efficientvit"},{"title":"idea-research/grounded-sam-2","url":"https://github.com/idea-research/grounded-sam-2"},{"title":"idea-research/grounding-dino-1.5-api","url":"https://github.com/idea-research/grounding-dino-1.5-api"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":126608,"task":"Zero-Shot Object Detection","parent_task":"Object Detection","dataset":"MSCOCO","model_name":"CP-DETR-Pro((without COCO data))","metrics":{"AP":"55.4"},"paper_url":"https://arxiv.org/abs/2412.09799v1","paper_title":"CP-DETR: Concept Prompt Guide DETR Toward Stronger Universal Object Detection","paper_date":"2024-12-13","code_links":[],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":126609,"task":"Zero-Shot Object Detection","parent_task":"Object Detection","dataset":"MSCOCO","model_name":"Grounding DINO 1.5 Pro (without COCO data)","metrics":{"AP":"54.3"},"paper_url":"https://arxiv.org/abs/2405.10300v2","paper_title":"Grounding DINO 1.5: Advance the \"Edge\" of Open-Set Object Detection","paper_date":"2024-05-16","code_links":[{"title":"mit-han-lab/efficientvit","url":"https://github.com/mit-han-lab/efficientvit"},{"title":"idea-research/grounded-sam-2","url":"https://github.com/idea-research/grounded-sam-2"},{"title":"idea-research/grounding-dino-1.5-api","url":"https://github.com/idea-research/grounding-dino-1.5-api"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":126610,"task":"Zero-Shot Object Detection","parent_task":"Object Detection","dataset":"MSCOCO","model_name":"Grounding DINO-L (without COCO data)","metrics":{"AP":"52.5"},"paper_url":"https://arxiv.org/abs/2303.05499v5","paper_title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","paper_date":"2023-03-09","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"IDEA-Research/Grounded-Segment-Anything","url":"https://github.com/IDEA-Research/Grounded-Segment-Anything"},{"title":"idea-research/groundingdino","url":"https://github.com/idea-research/groundingdino"},{"title":"idea-research/grounded-sam-2","url":"https://github.com/idea-research/grounded-sam-2"},{"title":"idea-research/dino-x-api","url":"https://github.com/idea-research/dino-x-api"},{"title":"PaddlePaddle/PaddleMIX","url":"https://github.com/PaddlePaddle/PaddleMIX"},{"title":"longzw1997/Open-GroundingDino","url":"https://github.com/longzw1997/Open-GroundingDino"},{"title":"camenduru/grounded-segment-anything-colab","url":"https://github.com/camenduru/grounded-segment-anything-colab"},{"title":"hzlbbfrog/generative-bim","url":"https://github.com/hzlbbfrog/generative-bim"},{"title":"anthonyhuo/sam-dam-for-compositional-reasoning","url":"https://github.com/anthonyhuo/sam-dam-for-compositional-reasoning"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":126611,"task":"Zero-Shot Object Detection","parent_task":"Object Detection","dataset":"MSCOCO","model_name":"OV-DINO-T (without COCO data)","metrics":{"AP":"50.6"},"paper_url":"https://arxiv.org/abs/2407.07844v2","paper_title":"OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion","paper_date":"2024-07-10","code_links":[{"title":"wanghao9610/ov-dino","url":"https://github.com/wanghao9610/ov-dino"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":126612,"task":"Zero-Shot Object Detection","parent_task":"Object Detection","dataset":"MSCOCO","model_name":"YOLO-World-L(without COCO data)","metrics":{"AP":"45.1"},"paper_url":"https://arxiv.org/abs/2401.17270v3","paper_title":"YOLO-World: Real-Time Open-Vocabulary Object Detection","paper_date":"2024-01-30","code_links":[{"title":"ailab-cvc/yolo-world","url":"https://github.com/ailab-cvc/yolo-world"},{"title":"d-robotics-ai-lab/dosod","url":"https://github.com/d-robotics-ai-lab/dosod"},{"title":"ibaiGorordo/ONNX-YOLO-World-Open-Vocabulary-Object-Detection","url":"https://github.com/ibaiGorordo/ONNX-YOLO-World-Open-Vocabulary-Object-Detection"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":126613,"task":"Zero-Shot Object Detection","parent_task":"Object Detection","dataset":"MSCOCO","model_name":"Object-Centric-OVD","metrics":{"AP":"40.5"},"paper_url":"https://arxiv.org/abs/2207.03482v3","paper_title":"Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection","paper_date":"2022-07-07","code_links":[{"title":"mmaaz60/mvits_for_class_agnostic_od","url":"https://github.com/mmaaz60/mvits_for_class_agnostic_od"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":152326,"task":"Zero-Shot Object Detection","parent_task":"Object Detection","dataset":"MSCOCO","model_name":"Grounding DINO 1.6 Pro (without COCO data)","metrics":{"AP":"55.4"},"paper_url":"https://arxiv.org/abs/2405.10300v2","paper_title":"Grounding DINO 1.5: Advance the \"Edge\" of Open-Set Object Detection","paper_date":"2024-05-16","code_links":[{"title":"mit-han-lab/efficientvit","url":"https://github.com/mit-han-lab/efficientvit"},{"title":"idea-research/grounded-sam-2","url":"https://github.com/idea-research/grounded-sam-2"},{"title":"idea-research/grounding-dino-1.5-api","url":"https://github.com/idea-research/grounding-dino-1.5-api"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":152327,"task":"Zero-Shot Object Detection","parent_task":"Object Detection","dataset":"MSCOCO","model_name":"CP-DETR-Pro((without COCO data))","metrics":{"AP":"55.4"},"paper_url":"https://arxiv.org/abs/2412.09799v1","paper_title":"CP-DETR: Concept Prompt Guide DETR Toward Stronger Universal Object Detection","paper_date":"2024-12-13","code_links":[],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":152328,"task":"Zero-Shot Object Detection","parent_task":"Object Detection","dataset":"MSCOCO","model_name":"Grounding DINO 1.5 Pro (without COCO data)","metrics":{"AP":"54.3"},"paper_url":"https://arxiv.org/abs/2405.10300v2","paper_title":"Grounding DINO 1.5: Advance the \"Edge\" of Open-Set Object Detection","paper_date":"2024-05-16","code_links":[{"title":"mit-han-lab/efficientvit","url":"https://github.com/mit-han-lab/efficientvit"},{"title":"idea-research/grounded-sam-2","url":"https://github.com/idea-research/grounded-sam-2"},{"title":"idea-research/grounding-dino-1.5-api","url":"https://github.com/idea-research/grounding-dino-1.5-api"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":152329,"task":"Zero-Shot Object Detection","parent_task":"Object Detection","dataset":"MSCOCO","model_name":"Grounding DINO-L (without COCO data)","metrics":{"AP":"52.5"},"paper_url":"https://arxiv.org/abs/2303.05499v5","paper_title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","paper_date":"2023-03-09","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"IDEA-Research/Grounded-Segment-Anything","url":"https://github.com/IDEA-Research/Grounded-Segment-Anything"},{"title":"idea-research/groundingdino","url":"https://github.com/idea-research/groundingdino"},{"title":"idea-research/grounded-sam-2","url":"https://github.com/idea-research/grounded-sam-2"},{"title":"idea-research/dino-x-api","url":"https://github.com/idea-research/dino-x-api"},{"title":"PaddlePaddle/PaddleMIX","url":"https://github.com/PaddlePaddle/PaddleMIX"},{"title":"longzw1997/Open-GroundingDino","url":"https://github.com/longzw1997/Open-GroundingDino"},{"title":"camenduru/grounded-segment-anything-colab","url":"https://github.com/camenduru/grounded-segment-anything-colab"},{"title":"hzlbbfrog/generative-bim","url":"https://github.com/hzlbbfrog/generative-bim"},{"title":"anthonyhuo/sam-dam-for-compositional-reasoning","url":"https://github.com/anthonyhuo/sam-dam-for-compositional-reasoning"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":152330,"task":"Zero-Shot Object Detection","parent_task":"Object Detection","dataset":"MSCOCO","model_name":"OV-DINO-T (without COCO data)","metrics":{"AP":"50.6"},"paper_url":"https://arxiv.org/abs/2407.07844v2","paper_title":"OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion","paper_date":"2024-07-10","code_links":[{"title":"wanghao9610/ov-dino","url":"https://github.com/wanghao9610/ov-dino"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":152331,"task":"Zero-Shot Object Detection","parent_task":"Object Detection","dataset":"MSCOCO","model_name":"YOLO-World-L(without COCO data)","metrics":{"AP":"45.1"},"paper_url":"https://arxiv.org/abs/2401.17270v3","paper_title":"YOLO-World: Real-Time Open-Vocabulary Object Detection","paper_date":"2024-01-30","code_links":[{"title":"ailab-cvc/yolo-world","url":"https://github.com/ailab-cvc/yolo-world"},{"title":"d-robotics-ai-lab/dosod","url":"https://github.com/d-robotics-ai-lab/dosod"},{"title":"ibaiGorordo/ONNX-YOLO-World-Open-Vocabulary-Object-Detection","url":"https://github.com/ibaiGorordo/ONNX-YOLO-World-Open-Vocabulary-Object-Detection"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":152332,"task":"Zero-Shot Object Detection","parent_task":"Object Detection","dataset":"MSCOCO","model_name":"Object-Centric-OVD","metrics":{"AP":"40.5"},"paper_url":"https://arxiv.org/abs/2207.03482v3","paper_title":"Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection","paper_date":"2022-07-07","code_links":[{"title":"mmaaz60/mvits_for_class_agnostic_od","url":"https://github.com/mmaaz60/mvits_for_class_agnostic_od"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]}]}