{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T08:31:54Z","timestamp":1778661114716,"version":"3.51.4"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1109\/icra40945.2020.9196653","type":"proceedings-article","created":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T21:25:46Z","timestamp":1600205146000},"page":"1128-1134","source":"Crossref","is-referenced-by-count":25,"title":["SMArT: Training Shallow Memory-aware Transformers for Robotic Explainability"],"prefix":"10.1109","author":[{"given":"Marcella","family":"Cornia","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lorenzo","family":"Baraldi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rita","family":"Cucchiara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref31","article-title":"Augmenting Self-attention with Persistent Memory","author":"sukhbaatar","year":"2019"},{"key":"ref30","article-title":"Layer Normalization","author":"ba","year":"2016"},{"key":"ref37","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","author":"banerjee","year":"2005","journal-title":"Proceedings annual meeting of the Association for Computational Linguistics"},{"key":"ref36","article-title":"Rouge: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Proceedings annual meeting of the Association for Computational Linguistics"},{"key":"ref35","article-title":"BLEU: a method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proceedings of the 17th annual meeting on Association for Computational Linguistics -"},{"key":"ref34","article-title":"Probabilistic Object Detection: Definition and Evaluation","author":"hall","year":"2018"},{"key":"ref10","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref11","article-title":"Image Captioning: Transforming Objects into Words","author":"herdade","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_31"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2010.2050411"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540112"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.100"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2587640"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref28","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","author":"devlin","year":"2019","journal-title":"Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics"},{"key":"ref4","article-title":"Speaker-follower models for vision-and-language navigation","author":"fried","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00583"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-42999-1"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref5","article-title":"Embodied Vision-and-Language Navigation with Dynamic Convolutional Filters","author":"landi","year":"2019","journal-title":"Proceedings of the British Machine Vision Conference"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00754"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00850"},{"key":"ref1","article-title":"On evaluation of embodied navigation agents","author":"anderson","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref22","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"ref21","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proceedings of the International Conference on Learning Representations"},{"key":"ref42","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proceedings of the International Conference on Learning Representations"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3177745"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref26","article-title":"Sequence level training with recurrent neural networks","author":"ranzato","year":"2015","journal-title":"Proceedings of the International Conference on Learning Representations"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.140"}],"event":{"name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","location":"Paris, France","start":{"date-parts":[[2020,5,31]]},"end":{"date-parts":[[2020,8,31]]}},"container-title":["2020 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9187508\/9196508\/09196653.pdf?arnumber=9196653","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:18:44Z","timestamp":1656375524000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9196653\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/icra40945.2020.9196653","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}