Matches in SemOpenAlex for { <https://semopenalex.org/work/W2898074480> ?p ?o ?g. }
- W2898074480 abstract "Person re-identification(ReID) is a task of associating persons that cross the non-overlapping camera views at different locations and times. It is a challenging task due to the large variations in person pose, background, luminance, occlusion, low resolution, etc. How to extracting a powerful features representation is the prime problem in ReID and is still unsolved. In this paper, we propose a cascade network architecture combined with a generative adversarial networks(GANs) and a convolutional neural network(CNN) to improve the performance of person re-identification. The GANs first generates the person body parts segmentation from the person image, and then inputs the segmentation label into the connected CNN together with the original person image. Finally obtain a discriminative and robust feature representation for ReID task. The body parts segmentation partitioning the person image into multiple segments, such as background, head, face, arms, lags, etc. The body parts segmentation information contains accurate borders and category attributes for body parts, which makes the our model more accurate compared to other predefined rigid parts alignment models. Experiments are conduced on the CUHK03, Market1501, DukeMTMC-ReID datasets and the results demonstrate that this approach outperforms several existing state-of-the-art methods." @default.
- W2898074480 created "2018-10-26" @default.
- W2898074480 creator A5022141624 @default.
- W2898074480 creator A5025631695 @default.
- W2898074480 creator A5030814492 @default.
- W2898074480 creator A5078181662 @default.
- W2898074480 creator A5080537200 @default.
- W2898074480 date "2018-07-01" @default.
- W2898074480 modified "2023-09-26" @default.
- W2898074480 title "Improving Person Re-identification by Body Parts Segmentation Generated by GAN" @default.
- W2898074480 cites W1677182931 @default.
- W2898074480 cites W1920259731 @default.
- W2898074480 cites W1928419358 @default.
- W2898074480 cites W1949591461 @default.
- W2898074480 cites W1967988963 @default.
- W2898074480 cites W1979260620 @default.
- W2898074480 cites W1982925187 @default.
- W2898074480 cites W2046835352 @default.
- W2898074480 cites W2047632871 @default.
- W2898074480 cites W2079972027 @default.
- W2898074480 cites W2089074647 @default.
- W2898074480 cites W2102605133 @default.
- W2898074480 cites W2113609219 @default.
- W2898074480 cites W2115669554 @default.
- W2898074480 cites W2135442311 @default.
- W2898074480 cites W2153410696 @default.
- W2898074480 cites W2168356304 @default.
- W2898074480 cites W2194775991 @default.
- W2898074480 cites W2204750386 @default.
- W2898074480 cites W2474013209 @default.
- W2898074480 cites W2475284720 @default.
- W2898074480 cites W2526833393 @default.
- W2898074480 cites W2585635281 @default.
- W2898074480 cites W2606377603 @default.
- W2898074480 cites W2736410039 @default.
- W2898074480 cites W2768610172 @default.
- W2898074480 cites W2963073614 @default.
- W2898074480 cites W2963438548 @default.
- W2898074480 cites W2963690547 @default.
- W2898074480 cites W2963787027 @default.
- W2898074480 cites W2964130064 @default.
- W2898074480 cites W2964163358 @default.
- W2898074480 cites W2964289004 @default.
- W2898074480 cites W2964304299 @default.
- W2898074480 cites W3100555577 @default.
- W2898074480 doi "https://doi.org/10.1109/ijcnn.2018.8489450" @default.
- W2898074480 hasPublicationYear "2018" @default.
- W2898074480 type Work @default.
- W2898074480 sameAs 2898074480 @default.
- W2898074480 citedByCount "3" @default.
- W2898074480 countsByYear W28980744802019 @default.
- W2898074480 countsByYear W28980744802022 @default.
- W2898074480 crossrefType "proceedings-article" @default.
- W2898074480 hasAuthorship W2898074480A5022141624 @default.
- W2898074480 hasAuthorship W2898074480A5025631695 @default.
- W2898074480 hasAuthorship W2898074480A5030814492 @default.
- W2898074480 hasAuthorship W2898074480A5078181662 @default.
- W2898074480 hasAuthorship W2898074480A5080537200 @default.
- W2898074480 hasConcept C116834253 @default.
- W2898074480 hasConcept C124504099 @default.
- W2898074480 hasConcept C138885662 @default.
- W2898074480 hasConcept C144024400 @default.
- W2898074480 hasConcept C153180895 @default.
- W2898074480 hasConcept C154945302 @default.
- W2898074480 hasConcept C162324750 @default.
- W2898074480 hasConcept C17744445 @default.
- W2898074480 hasConcept C187736073 @default.
- W2898074480 hasConcept C199539241 @default.
- W2898074480 hasConcept C2776359362 @default.
- W2898074480 hasConcept C2776401178 @default.
- W2898074480 hasConcept C2779304628 @default.
- W2898074480 hasConcept C2780451532 @default.
- W2898074480 hasConcept C31972630 @default.
- W2898074480 hasConcept C36289849 @default.
- W2898074480 hasConcept C41008148 @default.
- W2898074480 hasConcept C41895202 @default.
- W2898074480 hasConcept C52622490 @default.
- W2898074480 hasConcept C59822182 @default.
- W2898074480 hasConcept C81363708 @default.
- W2898074480 hasConcept C86803240 @default.
- W2898074480 hasConcept C89600930 @default.
- W2898074480 hasConcept C94625758 @default.
- W2898074480 hasConcept C97931131 @default.
- W2898074480 hasConceptScore W2898074480C116834253 @default.
- W2898074480 hasConceptScore W2898074480C124504099 @default.
- W2898074480 hasConceptScore W2898074480C138885662 @default.
- W2898074480 hasConceptScore W2898074480C144024400 @default.
- W2898074480 hasConceptScore W2898074480C153180895 @default.
- W2898074480 hasConceptScore W2898074480C154945302 @default.
- W2898074480 hasConceptScore W2898074480C162324750 @default.
- W2898074480 hasConceptScore W2898074480C17744445 @default.
- W2898074480 hasConceptScore W2898074480C187736073 @default.
- W2898074480 hasConceptScore W2898074480C199539241 @default.
- W2898074480 hasConceptScore W2898074480C2776359362 @default.
- W2898074480 hasConceptScore W2898074480C2776401178 @default.
- W2898074480 hasConceptScore W2898074480C2779304628 @default.
- W2898074480 hasConceptScore W2898074480C2780451532 @default.
- W2898074480 hasConceptScore W2898074480C31972630 @default.
- W2898074480 hasConceptScore W2898074480C36289849 @default.
- W2898074480 hasConceptScore W2898074480C41008148 @default.