{"url":"/sota/visual-dialog-on-visual-dialog-v1-0-test-std","task":{"name":"Visual Dialog","url":"/task/visual-dialogue","note":null},"dataset":{"name":"Visual Dialog v1.0 test-std","url":"/dataset/visdial"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Visual Dialog requires an AI agent to hold a meaningful dialog with humans in natural, conversational language about visual content. Specifically, given an image, a dialog history, and a follow-up question about the image, the task is to answer the question.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["NDCG (x 100)","MRR (x 100)","R@1","R@5","R@10","Mean"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"NDCG (x 100)":"higher","MRR (x 100)":"higher","R@1":null,"R@5":null,"R@10":null,"Mean":null}},"counts":{"rows":80,"rows_with_code":14,"rows_with_paper_page":16,"rows_dated":16,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"Single","metrics":{"MRR (x 100)":"45.75","Mean":"6.54","NDCG (x 100)":"78.7","R@1":"29.5","R@10":"82.45","R@5":"65.7"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"P1P2+Distill+Ensemble","metrics":{"MRR (x 100)":"56.2","Mean":"5.41","NDCG (x 100)":"77.92","R@1":"44.45","R@10":"83.78","R@5":"68.9"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"Ensemble + Fine-tuning","metrics":{"MRR (x 100)":"56.35","Mean":"5.79","NDCG (x 100)":"76.43","R@1":"45.17","R@10":"82.17","R@5":"68.12"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"ensemble, finetune","metrics":{"MRR (x 100)":"56.42","Mean":"5.47","NDCG (x 100)":"76.17","R@1":"44.32","R@10":"84.52","R@5":"70.23"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":5,"model":"VD-PCR","metrics":{"MRR (x 100)":"56.05","Mean":"5.72","NDCG (x 100)":"76.14","R@1":"44.75","R@10":"82.75","R@5":"68.4"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"Ensemble","metrics":{"MRR (x 100)":"51.17","Mean":"6.69","NDCG (x 100)":"75.35","R@1":"38.9","R@10":"77.98","R@5":"62.82"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"Ensemble + Finetune","metrics":{"MRR (x 100)":"52.14","Mean":"6.53","NDCG (x 100)":"74.88","R@1":"38.92","R@10":"80.65","R@5":"66.6"},"uses_additional_data":false,"paper_date":"2019-11-26","paper":"/paper/efficient-attention-mechanism-for-handling","paper_url":"https://arxiv.org/abs/1911.11390v2","paper_title":"Efficient Attention Mechanism for Visual Dialog that can Handle All the Interactions between Multiple Inputs","code":"https://github.com/davidnvq/visdial","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"bert-double-stream-finetuning","metrics":{"MRR (x 100)":"62.65","Mean":"5.89","NDCG (x 100)":"74.62","R@1":"54.37","R@10":"83.33","R@5":"70.75"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"CE-finetuned, single model","metrics":{"MRR (x 100)":"50.74","Mean":"6.28","NDCG (x 100)":"74.47","R@1":"37.95","R@10":"80.0","R@5":"64.12"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":10,"model":"2","metrics":{"MRR (x 100)":"49.26","Mean":"7.0","NDCG (x 100)":"73.36","R@1":"36.35","R@10":"78.12","R@5":"62.42"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"2","metrics":{"MRR (x 100)":"43.07","Mean":"7.42","NDCG (x 100)":"73.15","R@1":"27.82","R@10":"76.55","R@5":"60.38"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"5_4","metrics":{"MRR (x 100)":"48.37","Mean":"7.05","NDCG (x 100)":"73.08","R@1":"34.65","R@10":"77.53","R@5":"62.98"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":13,"model":"7","metrics":{"MRR (x 100)":"56.03","Mean":"5.98","NDCG (x 100)":"73.07","R@1":"44.2","R@10":"81.62","R@5":"68.45"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":14,"model":"1","metrics":{"MRR (x 100)":"56.73","Mean":"6.0","NDCG (x 100)":"72.99","R@1":"45.42","R@10":"81.73","R@5":"68.92"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":15,"model":"5-2","metrics":{"MRR (x 100)":"49.03","Mean":"7.07","NDCG (x 100)":"72.85","R@1":"35.88","R@10":"77.75","R@5":"62.88"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":16,"model":"2 Step: Factor Graph Attention + VD-Bert","metrics":{"MRR (x 100)":"69.92","Mean":"3.84","NDCG (x 100)":"72.83","R@1":"58.3","R@10":"89.6","R@5":"81.55"},"uses_additional_data":false,"paper_date":"2021-04-15","paper":"/paper/ensemble-of-mrr-and-ndcg-models-for-visual","paper_url":"https://arxiv.org/abs/2104.07511v3","paper_title":"Ensemble of MRR and NDCG models for Visual Dialog","code":"https://github.com/idansc/mrr-ndcg","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":17,"model":"1","metrics":{"MRR (x 100)":"56.67","Mean":"5.98","NDCG (x 100)":"72.8","R@1":"44.82","R@10":"81.9","R@5":"68.67"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":18,"model":"10","metrics":{"MRR (x 100)":"49.47","Mean":"6.9","NDCG (x 100)":"72.58","R@1":"35.77","R@10":"78.25","R@5":"64.15"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":19,"model":"Disc, Dense, 4 Ensemble.","metrics":{"MRR (x 100)":"55.11","Mean":"6.55","NDCG (x 100)":"72.41","R@1":"43.23","R@10":"79.77","R@5":"67.65"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":20,"model":"shanshandu","metrics":{"MRR (x 100)":"57.19","Mean":"6.04","NDCG (x 100)":"72.35","R@1":"45.3","R@10":"82.38","R@5":"70.15"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":21,"model":"1","metrics":{"MRR (x 100)":"57.13","Mean":"5.85","NDCG (x 100)":"72.33","R@1":"45.17","R@10":"82.4","R@5":"69.95"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":22,"model":"20","metrics":{"MRR (x 100)":"47.54","Mean":"7.14","NDCG (x 100)":"72.33","R@1":"33.5","R@10":"77.33","R@5":"63.28"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":23,"model":"Two-Step(refactor)","metrics":{"MRR (x 100)":"70.41","Mean":"3.66","NDCG (x 100)":"72.16","R@1":"58.17","R@10":"90.83","R@5":"83.85"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":24,"model":"simple_test","metrics":{"MRR (x 100)":"41.66","Mean":"8.3","NDCG (x 100)":"71.91","R@1":"25.85","R@10":"74.67","R@5":"60.12"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":25,"model":"1","metrics":{"MRR (x 100)":"56.34","Mean":"6.04","NDCG (x 100)":"71.82","R@1":"44.22","R@10":"81.7","R@5":"69.65"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":26,"model":"5TS","metrics":{"MRR (x 100)":"39.61","Mean":"9.01","NDCG (x 100)":"70.08","R@1":"25.65","R@10":"70.12","R@5":"53.62"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":27,"model":"Bert(two-stream)","metrics":{"MRR (x 100)":"63.92","Mean":"4.28","NDCG (x 100)":"68.08","R@1":"50.78","R@10":"89.6","R@5":"79.53"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":28,"model":"Ensemble FGA + BERT","metrics":{"MRR (x 100)":"70.95","Mean":"2.91","NDCG (x 100)":"67.09","R@1":"57.07","R@10":"95.08","R@5":"88.42"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":29,"model":"CARE(Single Model)","metrics":{"MRR (x 100)":"64.62","Mean":"4.29","NDCG (x 100)":"64.79","R@1":"51.82","R@10":"89.95","R@5":"80.35"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":30,"model":"sdfsdaf","metrics":{"MRR (x 100)":"58.57","Mean":"5.13","NDCG (x 100)":"64.48","R@1":"44.27","R@10":"86.42","R@5":"76.15"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":31,"model":"MRR ensemble (Naive)","metrics":{"MRR (x 100)":"71.24","Mean":"2.96","NDCG (x 100)":"64.04","R@1":"58.27","R@10":"94.45","R@5":"87.55"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":32,"model":"CAF","metrics":{"MRR (x 100)":"68.16","Mean":"3.3","NDCG (x 100)":"63.94","R@1":"54.67","R@10":"93.1","R@5":"84.95"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":33,"model":"w/ VQA + CC, single model","metrics":{"MRR (x 100)":"67.5","Mean":"3.32","NDCG (x 100)":"63.87","R@1":"53.85","R@10":"93.25","R@5":"84.67"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":34,"model":"test1","metrics":{"MRR (x 100)":"67.5","Mean":"3.32","NDCG (x 100)":"63.87","R@1":"53.85","R@10":"93.25","R@5":"84.67"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":35,"model":"sh101","metrics":{"MRR (x 100)":"67.49","Mean":"3.31","NDCG (x 100)":"63.75","R@1":"53.75","R@10":"93.25","R@5":"85.02"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":36,"model":"SCL_48","metrics":{"MRR (x 100)":"66.63","Mean":"3.41","NDCG (x 100)":"60.91","R@1":"52.52","R@10":"92.27","R@5":"84.1"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":37,"model":"Transformer+2cons","metrics":{"MRR (x 100)":"66.53","Mean":"3.4","NDCG (x 100)":"60.33","R@1":"52.62","R@10":"92.5","R@5":"84.12"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":38,"model":"single-model","metrics":{"MRR (x 100)":"64.95","Mean":"3.44","NDCG (x 100)":"60.31","R@1":"50.48","R@10":"93.15","R@5":"83.15"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":39,"model":"1","metrics":{"MRR (x 100)":"64.25","Mean":"4.11","NDCG (x 100)":"60.19","R@1":"50.88","R@10":"90.6","R@5":"80.92"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":40,"model":"211","metrics":{"MRR (x 100)":"64.14","Mean":"4.18","NDCG (x 100)":"59.69","R@1":"50.62","R@10":"89.83","R@5":"80.77"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":41,"model":"MVAN","metrics":{"MRR (x 100)":"64.84","Mean":"3.97","NDCG (x 100)":"59.37","R@1":"51.45","R@10":"90.65","R@5":"81.12"},"uses_additional_data":false,"paper_date":"2020-04-29","paper":"/paper/multi-view-attention-networks-for-visual","paper_url":"https://arxiv.org/abs/2004.14025v3","paper_title":"Multi-View Attention Network for Visual Dialog","code":"https://github.com/taesunwhang/MVAN-VisDial","n_code_links":1,"syntology":null},{"rank_in_archive_order":42,"model":"single model","metrics":{"MRR (x 100)":"66.2","Mean":"3.25","NDCG (x 100)":"59.33","R@1":"51.62","R@10":"93.7","R@5":"85.05"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":43,"model":"gr","metrics":{"MRR (x 100)":"64.58","Mean":"4.03","NDCG (x 100)":"59.23","R@1":"51.25","R@10":"90.05","R@5":"80.92"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":44,"model":"lkh(single-model)","metrics":{"MRR (x 100)":"62.65","Mean":"4.5","NDCG (x 100)":"59.0","R@1":"49.48","R@10":"88.35","R@5":"78.1"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":45,"model":"lijunlin_7","metrics":{"MRR (x 100)":"63.7","Mean":"4.26","NDCG (x 100)":"58.59","R@1":"50.3","R@10":"89.15","R@5":"79.47"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":46,"model":"wqedasd(single model)","metrics":{"MRR (x 100)":"61.87","Mean":"4.49","NDCG (x 100)":"58.56","R@1":"48.4","R@10":"88.6","R@5":"78.0"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":47,"model":"Bert2constraints","metrics":{"MRR (x 100)":"65.7","Mean":"3.68","NDCG (x 100)":"58.51","R@1":"51.73","R@10":"91.97","R@5":"82.97"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":48,"model":"zxcdd","metrics":{"MRR (x 100)":"64.31","Mean":"4.11","NDCG (x 100)":"58.49","R@1":"50.8","R@10":"89.65","R@5":"80.8"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":49,"model":"jiuyigedian","metrics":{"MRR (x 100)":"64.79","Mean":"3.98","NDCG (x 100)":"58.25","R@1":"51.32","R@10":"90.38","R@5":"81.0"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":50,"model":"disc","metrics":{"MRR (x 100)":"64.43","Mean":"4.13","NDCG (x 100)":"58.19","R@1":"50.7","R@10":"90.18","R@5":"80.83"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":51,"model":"lijunlin_9","metrics":{"MRR (x 100)":"63.31","Mean":"4.31","NDCG (x 100)":"58.14","R@1":"49.68","R@10":"89.25","R@5":"80.45"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":52,"model":"NMN","metrics":{"MRR (x 100)":"58.8","Mean":"4.4","NDCG (x 100)":"58.1","R@1":"44.15","R@10":"86.88","R@5":"76.88"},"uses_additional_data":false,"paper_date":"2017-04-18","paper":"/paper/learning-to-reason-end-to-end-module-networks","paper_url":"http://arxiv.org/abs/1704.05526v3","paper_title":"Learning to Reason: End-to-End Module Networks for Visual Question Answering","code":"https://github.com/ronghanghu/n2nmn","n_code_links":1,"syntology":null},{"rank_in_archive_order":53,"model":"zuizhong","metrics":{"MRR (x 100)":"64.3","Mean":"4.07","NDCG (x 100)":"57.82","R@1":"50.58","R@10":"90.03","R@5":"81.25"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":54,"model":"clean_wac_4freeze","metrics":{"MRR (x 100)":"64.57","Mean":"3.67","NDCG (x 100)":"57.6","R@1":"49.75","R@10":"91.67","R@5":"82.23"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":55,"model":"DAN","metrics":{"MRR (x 100)":"63.2","Mean":"4.3","NDCG (x 100)":"57.59","R@1":"49.63","R@10":"89.35","R@5":"79.75"},"uses_additional_data":false,"paper_date":"2019-02-25","paper":"/paper/dual-attention-networks-for-visual-reference","paper_url":"https://arxiv.org/abs/1902.09368v3","paper_title":"Dual Attention Networks for Visual Reference Resolution in Visual Dialog","code":"https://github.com/gicheonkang/DAN-VisDial","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":6,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":56,"model":"mvan_len40_test","metrics":{"MRR (x 100)":"47.03","Mean":"13.3","NDCG (x 100)":"57.39","R@1":"36.93","R@10":"65.8","R@5":"56.47"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":57,"model":"Synergistic","metrics":{"MRR (x 100)":"62.20","Mean":"4.17","NDCG (x 100)":"57.32","R@1":"47.90","R@5":"80.43"},"uses_additional_data":false,"paper_date":"2019-02-26","paper":"/paper/image-question-answer-synergistic-network-for","paper_url":"http://arxiv.org/abs/1902.09774v1","paper_title":"Image-Question-Answer Synergistic Network for Visual Dialog","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":58,"model":"5xFGA (F-RCNNx101)","metrics":{"MRR (x 100)":"69.3","Mean":"3.14","NDCG (x 100)":"57.20","R@1":"55.65","R@10":"94.05","R@5":"86.73"},"uses_additional_data":false,"paper_date":"2019-04-11","paper":"/paper/factor-graph-attention","paper_url":"https://arxiv.org/abs/1904.05880v3","paper_title":"Factor Graph Attention","code":"https://github.com/idansc/fga","n_code_links":1,"syntology":null},{"rank_in_archive_order":59,"model":"HACAN","metrics":{"MRR (x 100)":"64.22","Mean":"4.20","NDCG (x 100)":"57.17","R@1":"50.88","R@10":"89.45","R@5":"80.63"},"uses_additional_data":false,"paper_date":"2019-02-25","paper":"/paper/making-history-matter-gold-critic-sequence","paper_url":"http://arxiv.org/abs/1902.09326v3","paper_title":"Making History Matter: History-Advantage Sequence Training for Visual Dialog","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":60,"model":"CAG","metrics":{"MRR (x 100)":"63.49","Mean":"4.11","NDCG (x 100)":"56.64","R@1":"49.85","R@10":"90.15","R@5":"80.63"},"uses_additional_data":false,"paper_date":"2020-04-05","paper":"/paper/iterative-context-aware-graph-inference-for","paper_url":"https://arxiv.org/abs/2004.02194v1","paper_title":"Iterative Context-Aware Graph Inference for Visual Dialog","code":"https://github.com/wh0330/CAG_VisDial","n_code_links":1,"syntology":null},{"rank_in_archive_order":61,"model":"kbgn_disc_5","metrics":{"MRR (x 100)":"62.68","Mean":"4.22","NDCG (x 100)":"56.38","R@1":"48.6","R@10":"89.48","R@5":"80.1"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":62,"model":"DualVD","metrics":{"MRR (x 100)":"63.23","Mean":"4.11","NDCG (x 100)":"56.32","R@1":"49.25","R@10":"89.7","R@5":"80.23"},"uses_additional_data":false,"paper_date":"2019-11-17","paper":"/paper/dualvd-an-adaptive-dual-encoding-model-for","paper_url":"https://arxiv.org/abs/1911.07251v1","paper_title":"DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue","code":"https://github.com/JXZe/DualVD","n_code_links":1,"syntology":null},{"rank_in_archive_order":63,"model":"ERIC666","metrics":{"MRR (x 100)":"63.3","Mean":"4.2","NDCG (x 100)":"55.94","R@1":"49.18","R@10":"89.6","R@5":"81.0"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":64,"model":"eightepoch","metrics":{"MRR (x 100)":"62.24","Mean":"4.09","NDCG (x 100)":"55.88","R@1":"47.58","R@10":"89.72","R@5":"80.45"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":65,"model":"RVA","metrics":{"MRR (x 100)":"63.03","Mean":"4.18","NDCG (x 100)":"55.59","R@1":"49.03","R@10":"89.83","R@5":"80.40"},"uses_additional_data":false,"paper_date":"2018-12-06","paper":"/paper/recursive-visual-attention-in-visual-dialog","paper_url":"http://arxiv.org/abs/1812.02664v2","paper_title":"Recursive Visual Attention in Visual Dialog","code":"https://github.com/yuleiniu/rva","n_code_links":1,"syntology":null},{"rank_in_archive_order":66,"model":"single-model","metrics":{"MRR (x 100)":"62.56","Mean":"3.82","NDCG (x 100)":"55.21","R@1":"47.45","R@10":"92.0","R@5":"81.55"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":67,"model":"CorefNMN (ResNet-152)","metrics":{"MRR (x 100)":"61.50","Mean":"4.40","NDCG (x 100)":"54.70","R@1":"47.55","R@10":"88.80","R@5":"78.10"},"uses_additional_data":false,"paper_date":"2018-09-06","paper":"/paper/visual-coreference-resolution-in-visual","paper_url":"http://arxiv.org/abs/1809.01816v1","paper_title":"Visual Coreference Resolution in Visual Dialog using Neural Module Networks","code":"https://github.com/facebookresearch/corefnmn","n_code_links":1,"syntology":null},{"rank_in_archive_order":68,"model":"jkl","metrics":{"MRR (x 100)":"59.96","Mean":"5.12","NDCG (x 100)":"53.2","R@1":"46.35","R@10":"86.48","R@5":"76.78"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":69,"model":"trainval_ch_9","metrics":{"MRR (x 100)":"45.84","Mean":"20.71","NDCG (x 100)":"53.19","R@1":"35.9","R@10":"61.7","R@5":"54.97"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":70,"model":"GNN","metrics":{"MRR (x 100)":"61.37","Mean":"4.57","NDCG (x 100)":"52.82","R@1":"47.33","R@10":"87.83","R@5":"77.98"},"uses_additional_data":false,"paper_date":"2019-04-11","paper":"/paper/reasoning-visual-dialogs-with-structural-and","paper_url":"https://arxiv.org/abs/1904.05548v2","paper_title":"Reasoning Visual Dialogs with Structural and Partial Observations","code":"https://github.com/zilongzheng/visdial-gnn","n_code_links":1,"syntology":null},{"rank_in_archive_order":71,"model":"DLC-4","metrics":{"MRR (x 100)":"61.09","Mean":"4.65","NDCG (x 100)":"52.57","R@1":"46.83","R@10":"87.42","R@5":"78.22"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":72,"model":"gat_disc_relto_4","metrics":{"MRR (x 100)":"55.69","Mean":"7.87","NDCG (x 100)":"51.87","R@1":"42.7","R@10":"79.72","R@5":"70.17"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":73,"model":"adasd","metrics":{"MRR (x 100)":"60.11","Mean":"4.7","NDCG (x 100)":"49.94","R@1":"45.6","R@10":"87.9","R@5":"77.53"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":74,"model":"gat_disc_3","metrics":{"MRR (x 100)":"53.19","Mean":"11.96","NDCG (x 100)":"47.51","R@1":"41.4","R@10":"74.15","R@5":"65.85"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":75,"model":"MN-QIH-D","metrics":{"MRR (x 100)":"55.5","Mean":"5.92","NDCG (x 100)":"47.5","R@1":"40.98","R@10":"83.30","R@5":"72.30"},"uses_additional_data":false,"paper_date":"2016-11-26","paper":"/paper/visual-dialog","paper_url":"http://arxiv.org/abs/1611.08669v5","paper_title":"Visual Dialog","code":"https://github.com/facebookresearch/ParlAI","n_code_links":11,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":76,"model":"paratraining1epoch","metrics":{"MRR (x 100)":"53.3","Mean":"5.91","NDCG (x 100)":"46.75","R@1":"36.83","R@10":"83.1","R@5":"73.45"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":77,"model":"HRE-QIH-D","metrics":{"MRR (x 100)":"54.2","Mean":"6.41","NDCG (x 100)":"45.5","R@1":"39.93","R@10":"81.50","R@5":"70.45"},"uses_additional_data":false,"paper_date":"2016-11-26","paper":"/paper/visual-dialog","paper_url":"http://arxiv.org/abs/1611.08669v5","paper_title":"Visual Dialog","code":"https://github.com/facebookresearch/ParlAI","n_code_links":11,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":78,"model":"MN-QIH-D","metrics":{"MRR (x 100)":"55.4","Mean":"5.95","NDCG (x 100)":"45.3","R@1":"40.95","R@10":"82.83","R@5":"72.45"},"uses_additional_data":false,"paper_date":"2016-11-26","paper":"/paper/visual-dialog","paper_url":"http://arxiv.org/abs/1611.08669v5","paper_title":"Visual Dialog","code":"https://github.com/facebookresearch/ParlAI","n_code_links":11,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":79,"model":"czczx","metrics":{"MRR (x 100)":"29.97","Mean":"22.05","NDCG (x 100)":"23.0","R@1":"16.62","R@10":"53.05","R@5":"43.58"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":80,"model":"qqhe","metrics":{"MRR (x 100)":"7.25","Mean":"49.61","NDCG (x 100)":"11.84","R@1":"3.02","R@10":"12.22","R@5":"7.22"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":5,"rows_with_any_sample_ran":5,"distinct_papers_with_graph_line":3,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":5,"n_unverified":6,"n_samples":11,"n_pointer_only_licence":2,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":9,"n_unverified":6,"n_samples":15,"n_pointer_only_licence":2,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}