Matches in SemOpenAlex for { <https://semopenalex.org/work/W2468348601> ?p ?o ?g. }
- W2468348601 endingPage "524" @default.
- W2468348601 startingPage "513" @default.
- W2468348601 abstract "Person reidentification (re-id) aims to match a specific person across nonoverlapping cameras, which is an important but challenging task in video surveillance. Conventional methods mainly focus either on feature constructing or metric learning. Recently, some deep learning-based methods have been proposed to learn image features and similarity measures jointly. However, current deep models for person re-id are usually trained with either pairwise loss , where the number of negative pairs greatly outnumbering that of positive pairs may lead the training model to be biased toward negative pairs or constant margin hinge loss , without considering the fact that hard negative samples should be paid more attention in the training stage. In this paper, we propose to learn deep representations with an adaptive margin listwise loss. First, ranking lists instead of image pairs are used as training samples, in this way, the problem of data imbalance is relaxed. Second, by introducing an adaptive margin parameter in the listwise loss function, it can assign larger margins to harder negative samples, which can be interpreted as an implementation of the automatic hard negative mining strategy. To gain robustness against changes in poses and part occlusions, our architecture combines four convolutional neural networks, each of which embeds images from different scales or different body parts. The final combined model performs much better than each single model. The experimental results show that our approach achieves very promising results on the challenging CUHK03, CUHK01, and VIPeR data sets." @default.
- W2468348601 created "2016-07-22" @default.
- W2468348601 creator A5029499523 @default.
- W2468348601 creator A5035295689 @default.
- W2468348601 creator A5046216110 @default.
- W2468348601 creator A5066955276 @default.
- W2468348601 date "2017-03-01" @default.
- W2468348601 modified "2023-10-12" @default.
- W2468348601 title "DeepList: Learning Deep Features With Adaptive Listwise Constraint for Person Reidentification" @default.
- W2468348601 cites W1605761733 @default.
- W2468348601 cites W1649859964 @default.
- W2468348601 cites W1928419358 @default.
- W2468348601 cites W1949591461 @default.
- W2468348601 cites W1963882359 @default.
- W2468348601 cites W1971955426 @default.
- W2468348601 cites W1975517671 @default.
- W2468348601 cites W1979260620 @default.
- W2468348601 cites W1982925187 @default.
- W2468348601 cites W1998443077 @default.
- W2468348601 cites W2009077327 @default.
- W2468348601 cites W2014764728 @default.
- W2468348601 cites W2022508996 @default.
- W2468348601 cites W2046835352 @default.
- W2468348601 cites W2047632871 @default.
- W2468348601 cites W2048110836 @default.
- W2468348601 cites W2068042582 @default.
- W2468348601 cites W2079972027 @default.
- W2468348601 cites W2089074647 @default.
- W2468348601 cites W2091158010 @default.
- W2468348601 cites W2108862644 @default.
- W2468348601 cites W2125447566 @default.
- W2468348601 cites W2125889200 @default.
- W2468348601 cites W2135442311 @default.
- W2468348601 cites W2163072399 @default.
- W2468348601 cites W2167292325 @default.
- W2468348601 cites W2168356304 @default.
- W2468348601 cites W2171590421 @default.
- W2468348601 cites W2204750386 @default.
- W2468348601 cites W2219504084 @default.
- W2468348601 cites W2227159637 @default.
- W2468348601 cites W2258844511 @default.
- W2468348601 cites W2293561010 @default.
- W2468348601 cites W2295155381 @default.
- W2468348601 cites W2326772079 @default.
- W2468348601 cites W2342514851 @default.
- W2468348601 cites W3099206234 @default.
- W2468348601 cites W4317524344 @default.
- W2468348601 doi "https://doi.org/10.1109/tcsvt.2016.2586851" @default.
- W2468348601 hasPublicationYear "2017" @default.
- W2468348601 type Work @default.
- W2468348601 sameAs 2468348601 @default.
- W2468348601 citedByCount "54" @default.
- W2468348601 countsByYear W24683486012017 @default.
- W2468348601 countsByYear W24683486012018 @default.
- W2468348601 countsByYear W24683486012019 @default.
- W2468348601 countsByYear W24683486012020 @default.
- W2468348601 countsByYear W24683486012021 @default.
- W2468348601 countsByYear W24683486012022 @default.
- W2468348601 countsByYear W24683486012023 @default.
- W2468348601 crossrefType "journal-article" @default.
- W2468348601 hasAuthorship W2468348601A5029499523 @default.
- W2468348601 hasAuthorship W2468348601A5035295689 @default.
- W2468348601 hasAuthorship W2468348601A5046216110 @default.
- W2468348601 hasAuthorship W2468348601A5066955276 @default.
- W2468348601 hasConcept C108583219 @default.
- W2468348601 hasConcept C119857082 @default.
- W2468348601 hasConcept C153180895 @default.
- W2468348601 hasConcept C154945302 @default.
- W2468348601 hasConcept C2524010 @default.
- W2468348601 hasConcept C2776036281 @default.
- W2468348601 hasConcept C33923547 @default.
- W2468348601 hasConcept C41008148 @default.
- W2468348601 hasConceptScore W2468348601C108583219 @default.
- W2468348601 hasConceptScore W2468348601C119857082 @default.
- W2468348601 hasConceptScore W2468348601C153180895 @default.
- W2468348601 hasConceptScore W2468348601C154945302 @default.
- W2468348601 hasConceptScore W2468348601C2524010 @default.
- W2468348601 hasConceptScore W2468348601C2776036281 @default.
- W2468348601 hasConceptScore W2468348601C33923547 @default.
- W2468348601 hasConceptScore W2468348601C41008148 @default.
- W2468348601 hasFunder F4320321001 @default.
- W2468348601 hasIssue "3" @default.
- W2468348601 hasLocation W24683486011 @default.
- W2468348601 hasOpenAccess W2468348601 @default.
- W2468348601 hasPrimaryLocation W24683486011 @default.
- W2468348601 hasRelatedWork W2773120646 @default.
- W2468348601 hasRelatedWork W3014300295 @default.
- W2468348601 hasRelatedWork W3164822677 @default.
- W2468348601 hasRelatedWork W3215138031 @default.
- W2468348601 hasRelatedWork W4223943233 @default.
- W2468348601 hasRelatedWork W4225161397 @default.
- W2468348601 hasRelatedWork W4309045103 @default.
- W2468348601 hasRelatedWork W4312200629 @default.
- W2468348601 hasRelatedWork W4360585206 @default.
- W2468348601 hasRelatedWork W4364306694 @default.
- W2468348601 hasVolume "27" @default.
- W2468348601 isParatext "false" @default.
- W2468348601 isRetracted "false" @default.