{"task":"Image Retrieval","dataset":"COCO (Common Objects in Context)","metric_names":["recall@1","recall@5","Recall@10","QPS"],"rows":[{"id":48666,"task":"Image Retrieval","parent_task":null,"dataset":"COCO (Common Objects in Context)","model_name":"BLIP-2 ViT-G (fine-tuned)","metrics":{"Recall@10":"92.6","recall@1":"68.3","recall@5":"87.7"},"paper_url":"https://arxiv.org/abs/2301.12597v3","paper_title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","paper_date":"2023-01-30","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"salesforce/lavis","url":"https://github.com/salesforce/lavis"},{"title":"thudm/visualglm-6b","url":"https://github.com/thudm/visualglm-6b"},{"title":"baaivision/eva","url":"https://github.com/baaivision/eva"},{"title":"junshutang/Make-It-3D","url":"https://github.com/junshutang/Make-It-3D"},{"title":"facebookresearch/multimodal","url":"https://github.com/facebookresearch/multimodal"},{"title":"unispac/visual-adversarial-examples-jailbreak-large-language-models","url":"https://github.com/unispac/visual-adversarial-examples-jailbreak-large-language-models"},{"title":"yukw777/videoblip","url":"https://github.com/yukw777/videoblip"},{"title":"alibaba/graphtranslator","url":"https://github.com/alibaba/graphtranslator"},{"title":"gregor-ge/mblip","url":"https://github.com/gregor-ge/mblip"},{"title":"linzhiqiu/clip-flant5","url":"https://github.com/linzhiqiu/clip-flant5"},{"title":"kdr/videorag-mrr2024","url":"https://github.com/kdr/videorag-mrr2024"},{"title":"rabiulcste/vqazero","url":"https://github.com/rabiulcste/vqazero"},{"title":"jiwanchung/vlis","url":"https://github.com/jiwanchung/vlis"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-2/blip_2"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/blip_2"},{"title":"albertotestoni/ndq_visual_objects","url":"https://github.com/albertotestoni/ndq_visual_objects"}],"metrics_order":"[\"recall@1\", \"recall@5\", \"Recall@10\", \"QPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48667,"task":"Image Retrieval","parent_task":null,"dataset":"COCO (Common Objects in Context)","model_name":"VisualSparta","metrics":{"QPS":"451.4","Recall@10":"96.3","recall@1":"68.2","recall@5":"91.8"},"paper_url":"https://arxiv.org/abs/2101.00265v2","paper_title":"VisualSparta: An Embarrassingly Simple Approach to Large-scale Text-to-Image Search with Weighted Bag-of-words","paper_date":"2021-01-01","code_links":[{"title":"soco-ai/SF-QA","url":"https://github.com/soco-ai/SF-QA"}],"metrics_order":"[\"recall@1\", \"recall@5\", \"Recall@10\", \"QPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48668,"task":"Image Retrieval","parent_task":null,"dataset":"COCO (Common Objects in Context)","model_name":"BLIP-2 ViT-L (fine-tuned)","metrics":{"Recall@10":"91.8","recall@1":"66.3","recall@5":"86.5"},"paper_url":"https://arxiv.org/abs/2301.12597v3","paper_title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","paper_date":"2023-01-30","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"salesforce/lavis","url":"https://github.com/salesforce/lavis"},{"title":"thudm/visualglm-6b","url":"https://github.com/thudm/visualglm-6b"},{"title":"baaivision/eva","url":"https://github.com/baaivision/eva"},{"title":"junshutang/Make-It-3D","url":"https://github.com/junshutang/Make-It-3D"},{"title":"facebookresearch/multimodal","url":"https://github.com/facebookresearch/multimodal"},{"title":"unispac/visual-adversarial-examples-jailbreak-large-language-models","url":"https://github.com/unispac/visual-adversarial-examples-jailbreak-large-language-models"},{"title":"yukw777/videoblip","url":"https://github.com/yukw777/videoblip"},{"title":"alibaba/graphtranslator","url":"https://github.com/alibaba/graphtranslator"},{"title":"gregor-ge/mblip","url":"https://github.com/gregor-ge/mblip"},{"title":"linzhiqiu/clip-flant5","url":"https://github.com/linzhiqiu/clip-flant5"},{"title":"kdr/videorag-mrr2024","url":"https://github.com/kdr/videorag-mrr2024"},{"title":"rabiulcste/vqazero","url":"https://github.com/rabiulcste/vqazero"},{"title":"jiwanchung/vlis","url":"https://github.com/jiwanchung/vlis"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-2/blip_2"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/blip_2"},{"title":"albertotestoni/ndq_visual_objects","url":"https://github.com/albertotestoni/ndq_visual_objects"}],"metrics_order":"[\"recall@1\", \"recall@5\", \"Recall@10\", \"QPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48669,"task":"Image Retrieval","parent_task":null,"dataset":"COCO (Common Objects in Context)","model_name":"FLAVA (zero-shot)","metrics":{"recall@1":"38.38","recall@5":"67.47"},"paper_url":"https://arxiv.org/abs/2112.04482v3","paper_title":"FLAVA: A Foundational Language And Vision Alignment Model","paper_date":"2021-12-08","code_links":[{"title":"facebookresearch/multimodal","url":"https://github.com/facebookresearch/multimodal"},{"title":"apsdehal/flava-tutorials","url":"https://github.com/apsdehal/flava-tutorials"},{"title":"social-ai-studio/matk","url":"https://github.com/social-ai-studio/matk"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/falcon"}],"metrics_order":"[\"recall@1\", \"recall@5\", \"Recall@10\", \"QPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48670,"task":"Image Retrieval","parent_task":null,"dataset":"COCO (Common Objects in Context)","model_name":"CLIP (zero-shot)","metrics":{"recall@1":"33.29","recall@5":"62.47"},"paper_url":"https://arxiv.org/abs/2112.04482v3","paper_title":"FLAVA: A Foundational Language And Vision Alignment Model","paper_date":"2021-12-08","code_links":[{"title":"facebookresearch/multimodal","url":"https://github.com/facebookresearch/multimodal"},{"title":"apsdehal/flava-tutorials","url":"https://github.com/apsdehal/flava-tutorials"},{"title":"social-ai-studio/matk","url":"https://github.com/social-ai-studio/matk"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/falcon"}],"metrics_order":"[\"recall@1\", \"recall@5\", \"Recall@10\", \"QPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":48671,"task":"Image Retrieval","parent_task":null,"dataset":"COCO (Common Objects in Context)","model_name":"Oscar","metrics":{"Recall@10":"98.3"},"paper_url":"https://arxiv.org/abs/2004.06165v5","paper_title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","paper_date":"2020-04-13","code_links":[{"title":"rmokady/clip_prefix_caption","url":"https://github.com/rmokady/clip_prefix_caption"},{"title":"microsoft/Oscar","url":"https://github.com/microsoft/Oscar"},{"title":"milvlg/rosita","url":"https://github.com/milvlg/rosita"},{"title":"ThanThoai/Visual-Question-Answering_Vietnamese","url":"https://github.com/ThanThoai/Visual-Question-Answering_Vietnamese"}],"metrics_order":"[\"recall@1\", \"recall@5\", \"Recall@10\", \"QPS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]}]}