{"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/multi-direction-and-multi-scale-pyramid-in-1","title":"Multi-direction and Multi-scale Pyramid in Transformer for Video-based Pedestrian Retrieval","arxiv_id":null,"date":"2022-02-12","proceeding":"IEEE Transactions on Industrial Informatics 2022 2","authors":["Xianghao Zang; Ge Li; Wei Gao"],"abstract":"In video surveillance, pedestrian retrieval (also called person re-identification) is a critical task. This task aims to retrieve the pedestrian of interest from non-overlapping cameras. Recently, transformer-based models have achieved significant progress for this task. However, these models still suffer from ignoring fine-grained, part-informed information. This paper proposes a multi-direction and multi-scale Pyramid in Transformer (PiT) to solve this problem. In transformer-based architecture, each pedestrian image is split into many patches. Then, these patches are fed to transformer layers to obtain the feature representation of this image. To explore the fine-grained information, this paper proposes to apply vertical division and horizontal division on these patches to generate different-direction human parts. These parts provide more fine-grained information.  To fuse multi-scale feature representation, this paper presents a pyramid structure containing global-level information and many pieces of local-level information from different scales. The feature pyramids of all the pedestrian images from the same video are fused to form the final multi-direction and multi-scale feature representation. Experimental results on two challenging video-based benchmarks, MARS and iLIDS-VID, show the proposed PiT achieves state-of-the-art performance. Extensive ablation studies demonstrate the superiority of the proposed pyramid structure. The code is available at https://git.openi.org.cn/zangxh/PiT.git.","url_abs":"https://arxiv.org/abs/2202.06014","url_pdf":"https://arxiv.org/pdf/2202.06014.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":"multi-direction-and-multi-scale-pyramid-in-1","repo_url":"https://github.com/deropty/PiT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"person-re-identification","task_name":"Person Re-Identification"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/person-re-identification-on-mars","task":"Person Re-Identification","dataset":"MARS","model":"PiT","rank_in_archive_order":3,"of":21,"metrics":{"Rank-1":"90.22","Rank-10":"98.04","Rank-5":"97.23","mAP":"86.8"},"uses_additional_data":false},{"leaderboard":"/sota/person-re-identification-on-ilids-vid","task":"Person Re-Identification","dataset":"iLIDS-VID","model":"PiT","rank_in_archive_order":2,"of":10,"metrics":{"Rank-1":"92.07","Rank-10":"99.80","Rank-20":"100","Rank-5":"98.93"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}