{"task":"Image Captioning","dataset":"COCO Captions","metric_names":["BLEU-4","CIDER","METEOR","SPICE","ROUGE-L","BLEU-1","BLEU-2","BLEU-3"],"rows":[{"id":47002,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"mPLUG","metrics":{"BLEU-4":"46.5","CIDER":"155.1","METEOR":"32.0","SPICE":"26.0"},"paper_url":"https://arxiv.org/abs/2205.12005v2","paper_title":"mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections","paper_date":"2022-05-24","code_links":[{"title":"modelscope/modelscope","url":"https://github.com/modelscope/modelscope"},{"title":"alibaba/AliceMind","url":"https://github.com/alibaba/AliceMind/tree/main/mPLUG"},{"title":"x-plug/mplug","url":"https://github.com/x-plug/mplug"}],"metrics_order":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47003,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"OFA","metrics":{"BLEU-4":"44.9","CIDER":"154.9","METEOR":"32.5","SPICE":"26.6"},"paper_url":"https://arxiv.org/abs/2202.03052v2","paper_title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","paper_date":"2022-02-07","code_links":[{"title":"modelscope/modelscope","url":"https://github.com/modelscope/modelscope"},{"title":"ofa-sys/ofa","url":"https://github.com/ofa-sys/ofa"},{"title":"JHKim-snu/GVCCI","url":"https://github.com/JHKim-snu/GVCCI"},{"title":"JHKim-snu/PGA","url":"https://github.com/JHKim-snu/PGA"}],"metrics_order":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47004,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"GIT","metrics":{"BLEU-4":"44.1","CIDER":"151.1","METEOR":" 32.2","SPICE":"26.3"},"paper_url":"https://arxiv.org/abs/2205.14100v5","paper_title":"GIT: A Generative Image-to-text Transformer for Vision and Language","paper_date":"2022-05-27","code_links":[{"title":"microsoft/GenerativeImage2Text","url":"https://github.com/microsoft/GenerativeImage2Text"}],"metrics_order":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47005,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"BLIP-2 ViT-G OPT 2.7B (zero-shot)","metrics":{"BLEU-4":"43.7","CIDER":"145.8"},"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":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47006,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"BLIP-2 ViT-G OPT 6.7B (zero-shot)","metrics":{"BLEU-4":"43.5","CIDER":"145.2"},"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":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47007,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"ExpansionNet v2 (No VL pretraining)","metrics":{"BLEU-1":"83.5","BLEU-4":"42.7","CIDER":"143.7","METEOR":"30.6","ROUGE-L":"61.1","SPICE":"24.7"},"paper_url":"https://arxiv.org/abs/2208.06551v4","paper_title":"Exploiting Multiple Sequence Lengths in Fast End to End Training for Image Captioning","paper_date":"2022-08-13","code_links":[{"title":"jchenghu/expansionnet_v2","url":"https://github.com/jchenghu/expansionnet_v2"}],"metrics_order":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47008,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"LEMON","metrics":{"BLEU-4":"42.6","CIDER":"145.5","METEOR":"31.4","SPICE":"25.5"},"paper_url":"https://arxiv.org/abs/2111.12233v2","paper_title":"Scaling Up Vision-Language Pre-training for Image Captioning","paper_date":"2021-11-24","code_links":[],"metrics_order":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47009,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"BLIP-2 ViT-G FlanT5 XL (zero-shot)","metrics":{"BLEU-4":"42.4","CIDER":"144.5"},"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":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47010,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"GRIT (No VL pretraining - base)","metrics":{"BLEU-1":"84.2","BLEU-4":"42.4","CIDER":"144.2","METEOR":"30.6","ROUGE-L":"60.7","SPICE":"24.3"},"paper_url":"https://arxiv.org/abs/2207.09666v1","paper_title":"GRIT: Faster and Better Image captioning Transformer Using Dual Visual Features","paper_date":"2022-07-20","code_links":[{"title":"davidnvq/grit","url":"https://github.com/davidnvq/grit"},{"title":"pacman-ctm/thesis_code","url":"https://github.com/pacman-ctm/thesis_code"}],"metrics_order":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47011,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"Prompt Tuning","metrics":{"BLEU-4":"41.81","CIDER":"141.4","METEOR":"31.51","SPICE":"24.42"},"paper_url":"https://arxiv.org/abs/2208.02532v1","paper_title":"Prompt Tuning for Generative Multimodal Pretrained Models","paper_date":"2022-08-04","code_links":[{"title":"ofa-sys/ofa","url":"https://github.com/ofa-sys/ofa"}],"metrics_order":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47012,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"Oscar","metrics":{"BLEU-4":"41.7","CIDER":"140","METEOR":"30.6","SPICE":"24.5"},"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":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47013,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"Xmodal-Ctx","metrics":{"BLEU-1":"83.4","BLEU-4":"41.4","CIDER":"139.9","METEOR":"30.4","ROUGE-L":"60.4","SPICE":"24.0"},"paper_url":"https://arxiv.org/abs/2205.04363v2","paper_title":"Beyond a Pre-Trained Object Detector: Cross-Modal Textual and Visual Context for Image Captioning","paper_date":"2022-05-09","code_links":[{"title":"GT-RIPL/Xmodal-Ctx","url":"https://github.com/GT-RIPL/Xmodal-Ctx"}],"metrics_order":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47014,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"Xmodal-Ctx + OSCAR","metrics":{"BLEU-4":"41.3","CIDER":"142.2","SPICE":"24.9"},"paper_url":"https://arxiv.org/abs/2205.04363v2","paper_title":"Beyond a Pre-Trained Object Detector: Cross-Modal Textual and Visual Context for Image Captioning","paper_date":"2022-05-09","code_links":[{"title":"GT-RIPL/Xmodal-Ctx","url":"https://github.com/GT-RIPL/Xmodal-Ctx"}],"metrics_order":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47015,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"X-VLM (base)","metrics":{"BLEU-4":"41.3","CIDER":"140.8"},"paper_url":"https://arxiv.org/abs/2111.08276v3","paper_title":"Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts","paper_date":"2021-11-16","code_links":[{"title":"zengyan-97/x-vlm","url":"https://github.com/zengyan-97/x-vlm"}],"metrics_order":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47016,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"VinVL","metrics":{"BLEU-4":"41.0","CIDER":"140.9","METEOR":"31.1","SPICE":"25.2"},"paper_url":"https://arxiv.org/abs/2101.00529v2","paper_title":"VinVL: Revisiting Visual Representations in Vision-Language Models","paper_date":"2021-01-02","code_links":[{"title":"microsoft/Oscar","url":"https://github.com/microsoft/Oscar"},{"title":"pzzhang/VinVL","url":"https://github.com/pzzhang/VinVL"},{"title":"yaolinli/capenrich","url":"https://github.com/yaolinli/capenrich"},{"title":"JoshuaPlacidi/MS-COCO-Object-Tags","url":"https://github.com/JoshuaPlacidi/MS-COCO-Object-Tags"},{"title":"mkhalil1998/EC601_Group_Project","url":"https://github.com/mkhalil1998/EC601_Group_Project"},{"title":"JoshuaPlacidi/MS-COCO-Tags","url":"https://github.com/JoshuaPlacidi/MS-COCO-Tags"},{"title":"cattidea/VinVL-Paddle","url":"https://github.com/cattidea/VinVL-Paddle"}],"metrics_order":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47017,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"CoCa","metrics":{"BLEU-4":"40.9","CIDER":"143.6","METEOR":"33.9","SPICE":"24.7"},"paper_url":"https://arxiv.org/abs/2205.01917v2","paper_title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","paper_date":"2022-05-04","code_links":[{"title":"mlfoundations/open_clip","url":"https://github.com/mlfoundations/open_clip"},{"title":"facebookresearch/multimodal","url":"https://github.com/facebookresearch/multimodal"},{"title":"lucidrains/CoCa-pytorch","url":"https://github.com/lucidrains/CoCa-pytorch"},{"title":"amitakamath/whatsup_vlms","url":"https://github.com/amitakamath/whatsup_vlms"},{"title":"amitakamath/hard_positives","url":"https://github.com/amitakamath/hard_positives"},{"title":"Chaolei98/FreeZAD","url":"https://github.com/Chaolei98/FreeZAD"}],"metrics_order":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47018,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"SimVLM","metrics":{"BLEU-4":"40.6","CIDER":"143.3","METEOR":"33.4","SPICE":"25.4"},"paper_url":"https://arxiv.org/abs/2108.10904v3","paper_title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","paper_date":"2021-08-24","code_links":[{"title":"yulong-XJTU/SimVLM","url":"https://github.com/yulong-XJTU/SimVLM"},{"title":"FerryHuang/SimVLM","url":"https://github.com/FerryHuang/SimVLM"}],"metrics_order":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47019,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"Prismer","metrics":{"BLEU-4":"40.4","CIDER":"136.5","METEOR":"31.4","SPICE":"24.4"},"paper_url":"https://arxiv.org/abs/2303.02506v3","paper_title":"Prismer: A Vision-Language Model with Multi-Task Experts","paper_date":"2023-03-04","code_links":[{"title":"nvlabs/prismer","url":"https://github.com/nvlabs/prismer"},{"title":"KastanDay/video-pretrained-transformer","url":"https://github.com/KastanDay/video-pretrained-transformer"}],"metrics_order":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47020,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"PTP-BLIP (14M)","metrics":{"BLEU-4":"40.1","CIDER":"135.0","METEOR":"30.4","SPICE":"23.7"},"paper_url":"https://arxiv.org/abs/2212.09737v2","paper_title":"Position-guided Text Prompt for Vision-Language Pre-training","paper_date":"2022-12-19","code_links":[{"title":"sail-sg/ptp","url":"https://github.com/sail-sg/ptp"}],"metrics_order":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47021,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"L-Verse","metrics":{"BLEU-4":"39.9","METEOR":"31.4","ROUGE-L":"60.4","SPICE":"23.3"},"paper_url":"https://arxiv.org/abs/2111.11133v10","paper_title":"L-Verse: Bidirectional Generation Between Image and Text","paper_date":"2021-11-22","code_links":[{"title":"tgisaturday/L-Verse","url":"https://github.com/tgisaturday/L-Verse"}],"metrics_order":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47022,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"Xmodal-Ctx","metrics":{"BLEU-1":"81.5","BLEU-4":"39.7","CIDER":"135.9","METEOR":"30.0","ROUGE-L":"59.5","SPICE":"23.7"},"paper_url":"https://arxiv.org/abs/2205.04363v2","paper_title":"Beyond a Pre-Trained Object Detector: Cross-Modal Textual and Visual Context for Image Captioning","paper_date":"2022-05-09","code_links":[{"title":"GT-RIPL/Xmodal-Ctx","url":"https://github.com/GT-RIPL/Xmodal-Ctx"}],"metrics_order":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47023,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"X-Transformer","metrics":{"BLEU-1":"80.9","BLEU-2":"65.8","BLEU-3":"51.5","BLEU-4":"39.7","CIDER":"132.8","METEOR":"29.5","ROUGE-L":"59.1","SPICE":"23.4"},"paper_url":"https://arxiv.org/abs/2003.14080v1","paper_title":"X-Linear Attention Networks for Image Captioning","paper_date":"2020-03-31","code_links":[{"title":"jdai-cv/image-captioning","url":"https://github.com/jdai-cv/image-captioning"},{"title":"Panda-Peter/image-captioning","url":"https://github.com/Panda-Peter/image-captioning"}],"metrics_order":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47024,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"AoANet + VC","metrics":{"BLEU-4":"39.5","METEOR":"29.3","ROUGE-L":"59.3"},"paper_url":"https://arxiv.org/abs/2002.12204v3","paper_title":"Visual Commonsense R-CNN","paper_date":"2020-02-27","code_links":[{"title":"Wangt-CN/VC-R-CNN","url":"https://github.com/Wangt-CN/VC-R-CNN"}],"metrics_order":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47025,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"Transformer_NSC","metrics":{"BLEU-1":"80.7","BLEU-2":"65.6","BLEU-3":"51.3","BLEU-4":"39.4","CIDER":"129.6","METEOR":"28.9","ROUGE-L":"58.7","SPICE":"22.8"},"paper_url":"https://arxiv.org/abs/2003.09971v2","paper_title":"A Better Variant of Self-Critical Sequence Training","paper_date":"2020-03-22","code_links":[{"title":"ruotianluo/self-critical.pytorch","url":"https://github.com/ruotianluo/self-critical.pytorch"}],"metrics_order":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47026,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"Meshed-Memory Transformer","metrics":{"BLEU-1":"80.8","BLEU-4":"39.1","CIDER":"131.2","METEOR":"29.2","ROUGE-L":"58.6","SPICE":"22.6"},"paper_url":"https://arxiv.org/abs/1912.08226v2","paper_title":"Meshed-Memory Transformer for Image Captioning","paper_date":"2019-12-17","code_links":[{"title":"aimagelab/meshed-memory-transformer","url":"https://github.com/aimagelab/meshed-memory-transformer"},{"title":"Japanese-Image-Captioning/M2-transformer-for-Japanese","url":"https://github.com/Japanese-Image-Captioning/M2-transformer-for-Japanese"}],"metrics_order":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47027,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"CLIP Text Encoder (RL w/ CIDEr-reward)","metrics":{"BLEU-4":"38.2","CIDER":"124.9","METEOR":"28.7","ROUGE-L":"58.5"},"paper_url":"https://arxiv.org/abs/2205.13115v2","paper_title":"Fine-grained Image Captioning with CLIP Reward","paper_date":"2022-05-26","code_links":[{"title":"j-min/clip-caption-reward","url":"https://github.com/j-min/clip-caption-reward"}],"metrics_order":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47028,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"RefineCap (w/ REINFORCE)","metrics":{"BLEU-1":"80.2","BLEU-2":"64.5","BLEU-3":"49.9","BLEU-4":"37.8","CIDER":"127.2","METEOR":"28.3","ROUGE-L":"58.0","SPICE":"22.5"},"paper_url":"https://arxiv.org/abs/2109.03529v1","paper_title":"RefineCap: Concept-Aware Refinement for Image Captioning","paper_date":"2021-09-08","code_links":[],"metrics_order":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47029,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"RDN","metrics":{"BLEU-1":"80.2","BLEU-4":"37.3","CIDER":"125.2","METEOR":"28.1","ROUGE-L":"57.4"},"paper_url":"https://arxiv.org/abs/1908.11824v1","paper_title":"Reflective Decoding Network for Image Captioning","paper_date":"2019-08-30","code_links":[],"metrics_order":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47030,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"SmallCapd=16, Large","metrics":{"BLEU-4":"37.2","CIDER":"121.8","METEOR":"28.3","SPICE":"21.5"},"paper_url":"https://arxiv.org/abs/2209.15323v2","paper_title":"SmallCap: Lightweight Image Captioning Prompted with Retrieval Augmentation","paper_date":"2022-09-30","code_links":[{"title":"ritaramo/smallcap","url":"https://github.com/ritaramo/smallcap"}],"metrics_order":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47031,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"ClipCap (Transformer)","metrics":{"BLEU-4":"33.53","CIDER":"113.08","METEOR":"27.45","SPICE":"21.05"},"paper_url":"https://arxiv.org/abs/2111.09734v1","paper_title":"ClipCap: CLIP Prefix for Image Captioning","paper_date":"2021-11-18","code_links":[{"title":"rmokady/clip_prefix_caption","url":"https://github.com/rmokady/clip_prefix_caption"},{"title":"Japanese-Image-Captioning/ClipCap-for-Japanese","url":"https://github.com/Japanese-Image-Captioning/ClipCap-for-Japanese"},{"title":"sithu31296/image-captioning","url":"https://github.com/sithu31296/image-captioning"},{"title":"MS-P3/code7","url":"https://github.com/MS-P3/code7/tree/main/x_clip"}],"metrics_order":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47032,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"ClipCap (MLP + GPT2 tuning)","metrics":{"BLEU-4":"32.15","CIDER":"108.35","METEOR":"27.1","SPICE":"20.12"},"paper_url":"https://arxiv.org/abs/2111.09734v1","paper_title":"ClipCap: CLIP Prefix for Image Captioning","paper_date":"2021-11-18","code_links":[{"title":"rmokady/clip_prefix_caption","url":"https://github.com/rmokady/clip_prefix_caption"},{"title":"Japanese-Image-Captioning/ClipCap-for-Japanese","url":"https://github.com/Japanese-Image-Captioning/ClipCap-for-Japanese"},{"title":"sithu31296/image-captioning","url":"https://github.com/sithu31296/image-captioning"},{"title":"MS-P3/code7","url":"https://github.com/MS-P3/code7/tree/main/x_clip"}],"metrics_order":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47033,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"CapDec","metrics":{"BLEU-4":"26.4","CIDER":"91.8","METEOR":"25.1"},"paper_url":"https://arxiv.org/abs/2211.00575v1","paper_title":"Text-Only Training for Image Captioning using Noise-Injected CLIP","paper_date":"2022-11-01","code_links":[{"title":"davidhuji/capdec","url":"https://github.com/davidhuji/capdec"},{"title":"zelaki/wsac","url":"https://github.com/zelaki/wsac"},{"title":"avitej-iyer/CapDec-Recreation","url":"https://github.com/avitej-iyer/CapDec-Recreation"},{"title":"uriberger/re_cap","url":"https://github.com/uriberger/re_cap"}],"metrics_order":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47034,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"From Captions to Visual Concepts and Back","metrics":{"BLEU-4":"25.7","METEOR":"23.6"},"paper_url":"http://arxiv.org/abs/1411.4952v3","paper_title":"From Captions to Visual Concepts and Back","paper_date":"2014-11-18","code_links":[{"title":"s-gupta/visual-concepts","url":"https://github.com/s-gupta/visual-concepts"}],"metrics_order":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47035,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"VLKD (ViT-B/16)","metrics":{"BLEU-4":"16.7","CIDER":"58.3","METEOR":"19.7","SPICE":"13.4"},"paper_url":"https://openreview.net/forum?id=YTGg7kv8qIq","paper_title":"Enabling Multimodal Generation on CLIP via Vision-Language Knowledge Distillation","paper_date":"2021-11-16","code_links":[],"metrics_order":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47036,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"LaDiC (ours, 30 steps)","metrics":{"BLEU-4":"0.382","CIDER":"126.2","METEOR":"29.5"},"paper_url":"https://arxiv.org/abs/2404.10763v1","paper_title":"LaDiC: Are Diffusion Models Really Inferior to Autoregressive Counterparts for Image-to-Text Generation?","paper_date":"2024-04-16","code_links":[{"title":"wangyuchi369/ladic","url":"https://github.com/wangyuchi369/ladic"}],"metrics_order":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47037,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"VALOR","metrics":{"CIDER":"152.5","SPICE":"25.7"},"paper_url":"https://arxiv.org/abs/2304.08345v2","paper_title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","paper_date":"2023-04-17","code_links":[{"title":"TXH-mercury/VALOR","url":"https://github.com/TXH-mercury/VALOR"}],"metrics_order":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":1,"source":"archive","tags":[]},{"id":47038,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"VAST","metrics":{"CIDER":"149.0","SPICE":"27.0"},"paper_url":"https://arxiv.org/abs/2305.18500v2","paper_title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","paper_date":"2023-05-29","code_links":[{"title":"TXH-mercury/VALOR","url":"https://github.com/TXH-mercury/VALOR"},{"title":"txh-mercury/vast","url":"https://github.com/txh-mercury/vast"}],"metrics_order":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":1,"source":"archive","tags":[]},{"id":47039,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"Virtex (ResNet-101)","metrics":{"CIDER":"94","SPICE":"18.5"},"paper_url":"https://arxiv.org/abs/2006.06666v3","paper_title":"VirTex: Learning Visual Representations from Textual Annotations","paper_date":"2020-06-11","code_links":[{"title":"kdexd/virtex","url":"https://github.com/kdexd/virtex"},{"title":"mattdeitke/cvpr-buzz","url":"https://github.com/mattdeitke/cvpr-buzz"},{"title":"rahulvigneswaran/longtail-buzz","url":"https://github.com/rahulvigneswaran/longtail-buzz"}],"metrics_order":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47040,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"KOSMOS-1 (1.6B) (zero-shot)","metrics":{"CIDER":"84.7","SPICE":"16.8"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47041,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"LaDiC","metrics":{"ROUGE-L":"58.7","SPICE":"22.4"},"paper_url":"https://arxiv.org/abs/2404.10763v1","paper_title":"LaDiC: Are Diffusion Models Really Inferior to Autoregressive Counterparts for Image-to-Text Generation?","paper_date":"2024-04-16","code_links":[{"title":"wangyuchi369/ladic","url":"https://github.com/wangyuchi369/ladic"}],"metrics_order":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47042,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions","model_name":"BLIP-FuseCap","metrics":{"CLIPScore":"78.5"},"paper_url":"https://arxiv.org/abs/2305.17718v2","paper_title":"FuseCap: Leveraging Large Language Models for Enriched Fused Image Captions","paper_date":"2023-05-28","code_links":[{"title":"RotsteinNoam/FuseCap","url":"https://github.com/RotsteinNoam/FuseCap"}],"metrics_order":"[\"BLEU-4\", \"CIDER\", \"METEOR\", \"SPICE\", \"ROUGE-L\", \"BLEU-1\", \"BLEU-2\", \"BLEU-3\", \"CLIPScore\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]}]}