Papers › Harmonious Attention Network for Person Re-Identification

Harmonious Attention Network for Person Re-Identification

22 Feb 2018CVPR 2018 6arXiv:1802.08122archive 2025-07-28

Wei Li, Xiatian Zhu, Shaogang Gong

Existing person re-identification (re-id) methods either assume the availability of well-aligned person bounding box images as model input or rely on constrained attention selection mechanisms to calibrate misaligned images. They are therefore sub-optimal for re-id matching in arbitrarily aligned person images potentially with large human pose variations and unconstrained auto-detection errors. In this work, we show the advantages of jointly learning attention selection and feature representation in a Convolutional Neural Network (CNN) by maximising the complementary information of different levels of visual attention subject to re-id discriminative learning constraints. Specifically, we formulate a novel Harmonious Attention CNN (HA-CNN) model for joint learning of soft pixel attention and hard regional attention along with simultaneous optimisation of feature representations, dedicated to optimise person re-id in uncontrolled (misaligned) images. Extensive comparative evaluations validate the superiority of this new HA-CNN model for person re-id over a wide variety of state-of-the-art methods on three large-scale benchmarks including CUHK03, Market-1501, and DukeMTMC-ReID.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1802.08122")

Code

Syntology Ran 0 of 15 code samples harvested from 1 repository linked to this paper; 15 have no recorded run.

By repository: community (archive-listed): 15 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

milkplz/keras-frcnn mentioned on GitHubtfApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

15 samples harvested; 0 ran; 0 honoured the contract we drafted; 15 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

15unverified

Licence: 0 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from milkplz/keras-frcnn. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

apply_regr milkplz/keras-frcnn/keras_frcnn/roi_helpers.py community (archive-listed) unverified Apache-2.0 (permissive) · ec8be8008c975765 · report
apply_regr_np milkplz/keras-frcnn/keras_frcnn/roi_helpers.py community (archive-listed) unverified Apache-2.0 (permissive) · 12ba3e9b0c04e9e4 · report
augment milkplz/keras-frcnn/keras_frcnn/data_augment.py community (archive-listed) unverified Apache-2.0 (permissive) · 73efd07b31c131cd · report
calc_iou milkplz/keras-frcnn/keras_frcnn/roi_helpers.py community (archive-listed) unverified Apache-2.0 (permissive) · a4a32a93a4b2a1ba · report
class_loss_regr milkplz/keras-frcnn/keras_frcnn/losses.py community (archive-listed) unverified Apache-2.0 (permissive) · b6396e65cc2d636e · report
get_data milkplz/keras-frcnn/keras_frcnn/pascal_voc_parser.py community (archive-listed) unverified Apache-2.0 (permissive) · 260ceac63872066b · report
get_data milkplz/keras-frcnn/keras_frcnn/simple_parser.py community (archive-listed) unverified Apache-2.0 (permissive) · 435a2a871a9eb7c3 · report
get_img_output_length milkplz/keras-frcnn/keras_frcnn/resnet.py community (archive-listed) unverified Apache-2.0 (permissive) · b5afb710b31b739c · report
intersection milkplz/keras-frcnn/keras_frcnn/data_generators.py community (archive-listed) unverified Apache-2.0 (permissive) · 6e6137b5ba0e8c93 · report
iou milkplz/keras-frcnn/keras_frcnn/data_generators.py community (archive-listed) unverified Apache-2.0 (permissive) · 3347c438ffd1288b · report
nn_base milkplz/keras-frcnn/keras_frcnn/vgg.py community (archive-listed) unverified Apache-2.0 (permissive) · dcc94e6b36d98c9b · report
rpn milkplz/keras-frcnn/keras_frcnn/vgg.py community (archive-listed) unverified Apache-2.0 (permissive) · d00e643cbaa5b847 · report
rpn_loss_cls milkplz/keras-frcnn/keras_frcnn/losses.py community (archive-listed) unverified Apache-2.0 (permissive) · 7fa7565671a5e2b3 · report
rpn_loss_regr milkplz/keras-frcnn/keras_frcnn/losses.py community (archive-listed) unverified Apache-2.0 (permissive) · c0ceb156b9cb836c · report
union milkplz/keras-frcnn/keras_frcnn/data_generators.py community (archive-listed) unverified Apache-2.0 (permissive) · 7855b626f923050b · report

Tasks

Person Re-Identification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Person Re-Identification CUHK03 HA-CNN MAP 38.6 #15 of 19 Archive leaderboard report
Person Re-Identification CUHK03 HA-CNN Rank-1 41.7 #15 of 19 Archive leaderboard report
Person Re-Identification CUHK03 detected HA-CNN (CVPR'18) MAP 38.6 #13 of 19 Archive leaderboard report
Person Re-Identification CUHK03 detected HA-CNN (CVPR'18) Rank-1 41.7 #13 of 19 Archive leaderboard report
Person Re-Identification CUHK03 labeled HA-CNN (CVPR'18) MAP 41.0 #16 of 21 Archive leaderboard report
Person Re-Identification CUHK03 labeled HA-CNN (CVPR'18) Rank-1 44.4 #16 of 21 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections