{"task":"Video Captioning","dataset":"MSVD","metric_names":["CIDEr","BLEU-4","METEOR","ROUGE-L","GS"],"rows":[{"id":47351,"task":"Video Captioning","parent_task":null,"dataset":"MSVD","model_name":"MaMMUT","metrics":{"CIDEr":"195.6"},"paper_url":"https://arxiv.org/abs/2303.16839v3","paper_title":"MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks","paper_date":"2023-03-29","code_links":[{"title":"lucidrains/mammut-pytorch","url":"https://github.com/lucidrains/mammut-pytorch"}],"metrics_order":"[\"CIDEr\", \"BLEU-4\", \"METEOR\", \"ROUGE-L\", \"GS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":47352,"task":"Video Captioning","parent_task":null,"dataset":"MSVD","model_name":"VLAB","metrics":{"BLEU-4":"79.3","CIDEr":"179.8","METEOR":"51.2","ROUGE-L":"87.9"},"paper_url":"https://arxiv.org/abs/2305.13167v1","paper_title":"VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending","paper_date":"2023-05-22","code_links":[],"metrics_order":"[\"CIDEr\", \"BLEU-4\", \"METEOR\", \"ROUGE-L\", \"GS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":47353,"task":"Video Captioning","parent_task":null,"dataset":"MSVD","model_name":"VALOR","metrics":{"BLEU-4":"80.7","CIDEr":"178.5","METEOR":"51.0","ROUGE-L":"87.9"},"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":"[\"CIDEr\", \"BLEU-4\", \"METEOR\", \"ROUGE-L\", \"GS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":47354,"task":"Video Captioning","parent_task":null,"dataset":"MSVD","model_name":"COSA","metrics":{"BLEU-4":"76.5","CIDEr":"178.5"},"paper_url":"https://arxiv.org/abs/2306.09085v1","paper_title":"COSA: Concatenated Sample Pretrained Vision-Language Foundation Model","paper_date":"2023-06-15","code_links":[{"title":"txh-mercury/cosa","url":"https://github.com/txh-mercury/cosa"}],"metrics_order":"[\"CIDEr\", \"BLEU-4\", \"METEOR\", \"ROUGE-L\", \"GS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":47355,"task":"Video Captioning","parent_task":null,"dataset":"MSVD","model_name":"mPLUG-2","metrics":{"BLEU-4":"70.5","CIDEr":"165.8","METEOR":"48.4","ROUGE-L":"85.3"},"paper_url":"https://arxiv.org/abs/2302.00402v1","paper_title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","paper_date":"2023-02-01","code_links":[{"title":"modelscope/modelscope","url":"https://github.com/modelscope/modelscope"},{"title":"x-plug/mplug-owl","url":"https://github.com/x-plug/mplug-owl"},{"title":"alibaba/AliceMind","url":"https://github.com/alibaba/AliceMind"},{"title":"X-PLUG/mPLUG-2","url":"https://github.com/X-PLUG/mPLUG-2"}],"metrics_order":"[\"CIDEr\", \"BLEU-4\", \"METEOR\", \"ROUGE-L\", \"GS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":47356,"task":"Video Captioning","parent_task":null,"dataset":"MSVD","model_name":"HowToCaption","metrics":{"BLEU-4":"70.4","CIDEr":"154.2","METEOR":"46.4","ROUGE-L":"83.2"},"paper_url":"https://arxiv.org/abs/2310.04900v2","paper_title":"HowToCaption: Prompting LLMs to Transform Video Annotations at Scale","paper_date":"2023-10-07","code_links":[{"title":"ninatu/howtocaption","url":"https://github.com/ninatu/howtocaption"}],"metrics_order":"[\"CIDEr\", \"BLEU-4\", \"METEOR\", \"ROUGE-L\", \"GS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":47357,"task":"Video Captioning","parent_task":null,"dataset":"MSVD","model_name":"HiTeA","metrics":{"BLEU-4":"71.0","CIDEr":"146.9","METEOR":"45.3","ROUGE-L":"81.4"},"paper_url":"https://arxiv.org/abs/2212.14546v1","paper_title":"HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training","paper_date":"2022-12-30","code_links":[],"metrics_order":"[\"CIDEr\", \"BLEU-4\", \"METEOR\", \"ROUGE-L\", \"GS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":47358,"task":"Video Captioning","parent_task":null,"dataset":"MSVD","model_name":"Vid2Seq","metrics":{"CIDEr":"146.2","METEOR":"45.3"},"paper_url":"https://arxiv.org/abs/2302.14115v2","paper_title":"Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning","paper_date":"2023-02-27","code_links":[{"title":"google-research/scenic","url":"https://github.com/google-research/scenic/tree/main/scenic/projects/vid2seq"},{"title":"antoyang/VidChapters","url":"https://github.com/antoyang/VidChapters"},{"title":"KastanDay/video-pretrained-transformer","url":"https://github.com/KastanDay/video-pretrained-transformer"}],"metrics_order":"[\"CIDEr\", \"BLEU-4\", \"METEOR\", \"ROUGE-L\", \"GS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":47359,"task":"Video Captioning","parent_task":null,"dataset":"MSVD","model_name":"VIOLETv2","metrics":{"CIDEr":"139.2"},"paper_url":"https://arxiv.org/abs/2209.01540v5","paper_title":"An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling","paper_date":"2022-09-04","code_links":[{"title":"tsujuifu/pytorch_empirical-mvm","url":"https://github.com/tsujuifu/pytorch_empirical-mvm"}],"metrics_order":"[\"CIDEr\", \"BLEU-4\", \"METEOR\", \"ROUGE-L\", \"GS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":47360,"task":"Video Captioning","parent_task":null,"dataset":"MSVD","model_name":"RTQ","metrics":{"BLEU-4":"66.9","CIDEr":"123.4","ROUGE-L":"82.2"},"paper_url":"https://arxiv.org/abs/2312.00347v2","paper_title":"RTQ: Rethinking Video-language Understanding Based on Image-text Model","paper_date":"2023-12-01","code_links":[{"title":"SCZwangxiao/RTQ-MM2023","url":"https://github.com/SCZwangxiao/RTQ-MM2023"},{"title":"sczwangxiao/tsgvs-mm2023","url":"https://github.com/sczwangxiao/tsgvs-mm2023"}],"metrics_order":"[\"CIDEr\", \"BLEU-4\", \"METEOR\", \"ROUGE-L\", \"GS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":47361,"task":"Video Captioning","parent_task":null,"dataset":"MSVD","model_name":"CoCap (ViT/L14)","metrics":{"BLEU-4":"60.1","CIDEr":"121.5","METEOR":"41.4","ROUGE-L":"78.2"},"paper_url":"https://arxiv.org/abs/2309.12867v2","paper_title":"Accurate and Fast Compressed Video Captioning","paper_date":"2023-09-22","code_links":[{"title":"acherstyx/CoCap","url":"https://github.com/acherstyx/CoCap"}],"metrics_order":"[\"CIDEr\", \"BLEU-4\", \"METEOR\", \"ROUGE-L\", \"GS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":47362,"task":"Video Captioning","parent_task":null,"dataset":"MSVD","model_name":"VASTA (Vatex-backbone)","metrics":{"BLEU-4":"59.2","CIDEr":"119.7","METEOR":"40.65","ROUGE-L":"76.7"},"paper_url":"https://arxiv.org/abs/2208.09266v1","paper_title":"Diverse Video Captioning by Adaptive Spatio-temporal Attention","paper_date":"2022-08-19","code_links":[{"title":"zohrehghaderi/vasta","url":"https://github.com/zohrehghaderi/vasta"}],"metrics_order":"[\"CIDEr\", \"BLEU-4\", \"METEOR\", \"ROUGE-L\", \"GS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":47363,"task":"Video Captioning","parent_task":null,"dataset":"MSVD","model_name":"IcoCap (ViT-B/16)","metrics":{"BLEU-4":"59.1","CIDEr":"110.3","METEOR":"39.5","ROUGE-L":"76.5"},"paper_url":"https://ieeexplore.ieee.org/abstract/document/10272675","paper_title":"IcoCap: Improving Video Captioning by Compounding Images","paper_date":"2023-10-05","code_links":[],"metrics_order":"[\"CIDEr\", \"BLEU-4\", \"METEOR\", \"ROUGE-L\", \"GS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":47364,"task":"Video Captioning","parent_task":null,"dataset":"MSVD","model_name":"SEM-POS","metrics":{"BLEU-4":"60.1","CIDEr":"108.3","GS":"607.1","METEOR":"38.5","ROUGE-L":"76.0"},"paper_url":"https://arxiv.org/abs/2303.14829v2","paper_title":"SEM-POS: Grammatically and Semantically Correct Video Captioning","paper_date":"2023-03-26","code_links":[],"metrics_order":"[\"CIDEr\", \"BLEU-4\", \"METEOR\", \"ROUGE-L\", \"GS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":47365,"task":"Video Captioning","parent_task":null,"dataset":"MSVD","model_name":"VASTA (Kinetics-backbone)","metrics":{"BLEU-4":"56.1","CIDEr":"106.4","METEOR":"39.1","ROUGE-L":"74.5"},"paper_url":"https://arxiv.org/abs/2208.09266v1","paper_title":"Diverse Video Captioning by Adaptive Spatio-temporal Attention","paper_date":"2022-08-19","code_links":[{"title":"zohrehghaderi/vasta","url":"https://github.com/zohrehghaderi/vasta"}],"metrics_order":"[\"CIDEr\", \"BLEU-4\", \"METEOR\", \"ROUGE-L\", \"GS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":47366,"task":"Video Captioning","parent_task":null,"dataset":"MSVD","model_name":"IcoCap (ViT-B/32)","metrics":{"BLEU-4":"56.3","CIDEr":"103.8","METEOR":"38.9","ROUGE-L":"75.0"},"paper_url":"https://ieeexplore.ieee.org/abstract/document/10272675","paper_title":"IcoCap: Improving Video Captioning by Compounding Images","paper_date":"2023-10-05","code_links":[],"metrics_order":"[\"CIDEr\", \"BLEU-4\", \"METEOR\", \"ROUGE-L\", \"GS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]}]}