{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/improving-local-features-with-relevant","title":"Improving Local Features with Relevant Spatial Information by Vision Transformer for Crowd Counting","arxiv_id":null,"date":"2022-09-30","proceeding":"British Machine Vision Conference (BMVC) 2022 9","authors":["Nguyen H. Tran","Ta Duc Huy","Soan T. M. Duong","Phan Nguyen","Dao Huu Hung","Chanh D. Tr. Nguyen","Trung Bui","Steven Q.H. Truong"],"abstract":"Vision Transformer (ViT) variants have demonstrated state-of-the-art performances in plenty of computer vision benchmarks, including crowd counting. Although Transformer based models have shown breakthroughs in crowd counting, existing methods\r\nhave some limitations. Global embeddings extracted from ViTs do not encapsulate finegrained local features and, thus, are prone to errors in crowded scenes with diverse human scales and densities. In this paper, we propose LoViTCrowd with the argument that: LOcal features with spatial information from relevant regions via the attention mechanism of ViT can effectively reduce the crowd counting error. To this end, we divide each image into a cell grid. Considering patches of 3 × 3 cells, in which the main parts\r\nof the human body are encapsulated, the surrounding cells provide meaningful cues for crowd estimation. ViT is adapted on each patch to employ the attention mechanism across the 3 × 3 cells to count the number of people in the central cell. The number\r\nof people in the image is obtained by summing up the counts of its non-overlapping cells. Extensive experiments on four public datasets of sparse and dense scenes, i.e., Mall, ShanghaiTech Part A, ShanghaiTech Part B, and UCF-QNRF, demonstrate our\r\nmethod’s state-of-the-art performance. Compared to TransCrowd, LoViTCrowd reduces the root mean square errors (RMSE) and the mean absolute errors (MAE) by an average of 14.2% and 9.7%, respectively. The source is available at https://github.com/nguyen1312/LoViTCrowd","url_abs":"https://bmvc2022.mpi-inf.mpg.de/729/","url_pdf":"https://bmvc2022.mpi-inf.mpg.de/0729.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":"improving-local-features-with-relevant","repo_url":"https://github.com/nguyen1312/LoViTCrowd","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"crowd-counting","task_name":"Crowd Counting"}],"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/crowd-counting-on-shanghaitech-a","task":"Crowd Counting","dataset":"ShanghaiTech A","model":"LoViTCrowd","rank_in_archive_order":10,"of":35,"metrics":{"MAE":"54.8","RMSE":"80.9"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[{"repo":"nguyen1312/LoViTCrowd","kind":"named_in_paper","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"c6e0affd87c24c4f58ffe385f0a712cdd1911e21050f374a3e496a94b395b7d9","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}