{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/denssiam-end-to-end-densely-siamese-network","title":"DensSiam: End-to-End Densely-Siamese Network with Self-Attention Model for Object Tracking","arxiv_id":"1809.02714","date":"2018-09-07","proceeding":null,"authors":["Mohamed H. Abdelpakey","Mohamed S. Shehata","Mostafa M. Mohamed"],"abstract":"Convolutional Siamese neural networks have been recently used to track\nobjects using deep features. Siamese architecture can achieve real time speed,\nhowever it is still difficult to find a Siamese architecture that maintains the\ngeneralization capability, high accuracy and speed while decreasing the number\nof shared parameters especially when it is very deep. Furthermore, a\nconventional Siamese architecture usually processes one local neighborhood at a\ntime, which makes the appearance model local and non-robust to appearance\nchanges.\n  To overcome these two problems, this paper proposes DensSiam, a novel\nconvolutional Siamese architecture, which uses the concept of dense layers and\nconnects each dense layer to all layers in a feed-forward fashion with a\nsimilarity-learning function. DensSiam also includes a Self-Attention mechanism\nto force the network to pay more attention to the non-local features during\noffline training. Extensive experiments are performed on four tracking\nbenchmarks: OTB2013 and OTB2015 for validation set; and VOT2015, VOT2016 and\nVOT2017 for testing set. The obtained results show that DensSiam achieves\nsuperior results on these benchmarks compared to other current state-of-the-art\nmethods.","url_abs":"http://arxiv.org/abs/1809.02714v1","url_pdf":"http://arxiv.org/pdf/1809.02714v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"denssiam-end-to-end-densely-siamese-network","repo_url":"https://github.com/mrdoer/DSRPN_batch_pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"object-tracking","task_name":"Object Tracking"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}