Matches in SemOpenAlex for { <https://semopenalex.org/work/W4320712925> ?p ?o ?g. }
- W4320712925 endingPage "14620" @default.
- W4320712925 startingPage "14612" @default.
- W4320712925 abstract "Person re-identification is the key technology for designing a intelligent video surveillance system to retrieve and recongise a specific person in a series of videos. It mainly plays a role in multiple non-overlapping camera monitoring environments to determine whether the target person of interest that has appeared under a camera appears again under others. However, the image data, in the real scene, taken by the surveillance camera may be occluded or blurred, which increased the difficulty of identifying the pedestrian posturn and then lead to dramatically decrease the accuracy of recognition. To solve the above problems, we propose a dualbranch multi-scale feature fusion network, which improves the expression ability of pedestrian features under partial occlusion by learning discriminative pedestrian features. The feature erasure mechanism is introduced into the branch network to effectively enhance the fine-grained feature learning ability of the network. By embedding the lightweight attention module into Resnet-50, the image sequence features of the channel dimension will be extracted, and the interference caused by the cluttered back ground information will be suppressed. In the training phase, the average pooling layer and the maximum pooling layer of different kernels and strides are utilized for different residual stages, and the mixed pooling strategy and mixed loss function of different kernels are designed. Finally, a novel hybrid loss function which combines triplet loss and ID loss is presented to train the network model. By comparison with the existing representative methods on Market1501, DukeMTMC reID and MTMS17 datasets, the experimental results show that the features extracted by the proposed method are more discriminative and with high recognition accuracy." @default.
- W4320712925 created "2023-02-15" @default.
- W4320712925 creator A5062792660 @default.
- W4320712925 creator A5070105853 @default.
- W4320712925 creator A5070680688 @default.
- W4320712925 date "2023-01-01" @default.
- W4320712925 modified "2023-09-30" @default.
- W4320712925 title "A Double Stream Person Re-Identification Method Based on Attention Mechanism and Multi-Scale Feature Fusion" @default.
- W4320712925 cites W2131255818 @default.
- W4320712925 cites W2157643754 @default.
- W4320712925 cites W2183341477 @default.
- W4320712925 cites W2194775991 @default.
- W4320712925 cites W2204750386 @default.
- W4320712925 cites W2585635281 @default.
- W4320712925 cites W2604463754 @default.
- W4320712925 cites W2606377603 @default.
- W4320712925 cites W2737725206 @default.
- W4320712925 cites W2752782242 @default.
- W4320712925 cites W2773003563 @default.
- W4320712925 cites W2798874329 @default.
- W4320712925 cites W2810967842 @default.
- W4320712925 cites W2887695188 @default.
- W4320712925 cites W2947319827 @default.
- W4320712925 cites W2962706983 @default.
- W4320712925 cites W2962926870 @default.
- W4320712925 cites W2963047834 @default.
- W4320712925 cites W2963049565 @default.
- W4320712925 cites W2963842104 @default.
- W4320712925 cites W2963852441 @default.
- W4320712925 cites W2963899050 @default.
- W4320712925 cites W2963901085 @default.
- W4320712925 cites W2963910742 @default.
- W4320712925 cites W2964130064 @default.
- W4320712925 cites W2964304299 @default.
- W4320712925 cites W2979931389 @default.
- W4320712925 cites W2980073905 @default.
- W4320712925 cites W2981420411 @default.
- W4320712925 cites W2982119297 @default.
- W4320712925 cites W2992183111 @default.
- W4320712925 cites W2993325947 @default.
- W4320712925 cites W3034580371 @default.
- W4320712925 cites W3035186652 @default.
- W4320712925 cites W3035539956 @default.
- W4320712925 cites W3047312295 @default.
- W4320712925 cites W3098711604 @default.
- W4320712925 cites W3099206234 @default.
- W4320712925 cites W3100555577 @default.
- W4320712925 cites W3101408564 @default.
- W4320712925 cites W3105159632 @default.
- W4320712925 cites W3111255625 @default.
- W4320712925 cites W3175823695 @default.
- W4320712925 cites W4205720260 @default.
- W4320712925 doi "https://doi.org/10.1109/access.2023.3243553" @default.
- W4320712925 hasPublicationYear "2023" @default.
- W4320712925 type Work @default.
- W4320712925 citedByCount "0" @default.
- W4320712925 crossrefType "journal-article" @default.
- W4320712925 hasAuthorship W4320712925A5062792660 @default.
- W4320712925 hasAuthorship W4320712925A5070105853 @default.
- W4320712925 hasAuthorship W4320712925A5070680688 @default.
- W4320712925 hasBestOaLocation W43207129251 @default.
- W4320712925 hasConcept C127413603 @default.
- W4320712925 hasConcept C138885662 @default.
- W4320712925 hasConcept C153180895 @default.
- W4320712925 hasConcept C154945302 @default.
- W4320712925 hasConcept C22212356 @default.
- W4320712925 hasConcept C2776401178 @default.
- W4320712925 hasConcept C2777113093 @default.
- W4320712925 hasConcept C2780156472 @default.
- W4320712925 hasConcept C31972630 @default.
- W4320712925 hasConcept C41008148 @default.
- W4320712925 hasConcept C41895202 @default.
- W4320712925 hasConcept C52622490 @default.
- W4320712925 hasConcept C70437156 @default.
- W4320712925 hasConcept C97931131 @default.
- W4320712925 hasConceptScore W4320712925C127413603 @default.
- W4320712925 hasConceptScore W4320712925C138885662 @default.
- W4320712925 hasConceptScore W4320712925C153180895 @default.
- W4320712925 hasConceptScore W4320712925C154945302 @default.
- W4320712925 hasConceptScore W4320712925C22212356 @default.
- W4320712925 hasConceptScore W4320712925C2776401178 @default.
- W4320712925 hasConceptScore W4320712925C2777113093 @default.
- W4320712925 hasConceptScore W4320712925C2780156472 @default.
- W4320712925 hasConceptScore W4320712925C31972630 @default.
- W4320712925 hasConceptScore W4320712925C41008148 @default.
- W4320712925 hasConceptScore W4320712925C41895202 @default.
- W4320712925 hasConceptScore W4320712925C52622490 @default.
- W4320712925 hasConceptScore W4320712925C70437156 @default.
- W4320712925 hasConceptScore W4320712925C97931131 @default.
- W4320712925 hasFunder F4320328771 @default.
- W4320712925 hasLocation W43207129251 @default.
- W4320712925 hasOpenAccess W4320712925 @default.
- W4320712925 hasPrimaryLocation W43207129251 @default.
- W4320712925 hasRelatedWork W2024160000 @default.
- W4320712925 hasRelatedWork W2043075591 @default.
- W4320712925 hasRelatedWork W2061273563 @default.
- W4320712925 hasRelatedWork W2285052147 @default.
- W4320712925 hasRelatedWork W2546942002 @default.