FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4318149008> ?p ?o ?g. }

• W4318149008 endingPage "1051" @default.
• W4318149008 startingPage "1039" @default.
• W4318149008 abstract "Transformers are more and more popular in computer vision, which treat an image as a sequence of patches and learn robust global features from the sequence. However, pure transformers are not entirely suitable for vehicle re-identification because vehicle re-identification requires both robust global features and discriminative local features. For that, a graph interactive transformer (GiT) is proposed in this paper. In the macro view, a list of GiT blocks are stacked to build a vehicle re-identification model, in where graphs are to extract discriminative local features within patches and transformers are to extract robust global features among patches. In the micro view, graphs and transformers are in an interactive status, bringing effective cooperation between local and global features. Specifically, one current graph is embedded after the former level’s graph and transformer, while the current transform is embedded after the current graph and the former level’s transformer. In addition to the interaction between graphs and transforms, the graph is a newly-designed local correction graph, which learns discriminative local features within a patch by exploring nodes’ relationships. Extensive experiments on three large-scale vehicle re-identification datasets demonstrate that our GiT method is superior to state-of-the-art vehicle re-identification approaches." @default.
• W4318149008 created "2023-01-26" @default.
• W4318149008 creator A5024079940 @default.
• W4318149008 creator A5033119978 @default.
• W4318149008 creator A5035422552 @default.
• W4318149008 creator A5075489680 @default.
• W4318149008 creator A5078514263 @default.
• W4318149008 date "2023-01-01" @default.
• W4318149008 modified "2023-10-16" @default.
• W4318149008 title "GiT: Graph Interactive Transformer for Vehicle Re-Identification" @default.
• W4318149008 cites W1958236864 @default.
• W4318149008 cites W2097117768 @default.
• W4318149008 cites W2194775991 @default.
• W4318149008 cites W2204750386 @default.
• W4318149008 cites W2302255633 @default.
• W4318149008 cites W2343104654 @default.
• W4318149008 cites W2470322391 @default.
• W4318149008 cites W2512434173 @default.
• W4318149008 cites W2519904008 @default.
• W4318149008 cites W2549858646 @default.
• W4318149008 cites W2585635281 @default.
• W4318149008 cites W2750699122 @default.
• W4318149008 cites W2756012011 @default.
• W4318149008 cites W2756261853 @default.
• W4318149008 cites W2776879428 @default.
• W4318149008 cites W2779954854 @default.
• W4318149008 cites W2788212895 @default.
• W4318149008 cites W2789546350 @default.
• W4318149008 cites W2789938689 @default.
• W4318149008 cites W2799251491 @default.
• W4318149008 cites W2885476150 @default.
• W4318149008 cites W2889929596 @default.
• W4318149008 cites W2903318697 @default.
• W4318149008 cites W2909593838 @default.
• W4318149008 cites W2916798096 @default.
• W4318149008 cites W2919317477 @default.
• W4318149008 cites W2936222941 @default.
• W4318149008 cites W2938503583 @default.
• W4318149008 cites W2951491521 @default.
• W4318149008 cites W2953759675 @default.
• W4318149008 cites W2954626788 @default.
• W4318149008 cites W2955854238 @default.
• W4318149008 cites W2962858109 @default.
• W4318149008 cites W2963037989 @default.
• W4318149008 cites W2963047834 @default.
• W4318149008 cites W2963049565 @default.
• W4318149008 cites W2963200533 @default.
• W4318149008 cites W2963446712 @default.
• W4318149008 cites W2963977416 @default.
• W4318149008 cites W2968459853 @default.
• W4318149008 cites W2970584431 @default.
• W4318149008 cites W2977696760 @default.
• W4318149008 cites W2979152723 @default.
• W4318149008 cites W2982041213 @default.
• W4318149008 cites W2983188006 @default.
• W4318149008 cites W2984145721 @default.
• W4318149008 cites W2986968301 @default.
• W4318149008 cites W2989607888 @default.
• W4318149008 cites W2990827756 @default.
• W4318149008 cites W2991522752 @default.
• W4318149008 cites W2996199246 @default.
• W4318149008 cites W2996837277 @default.
• W4318149008 cites W2997351135 @default.
• W4318149008 cites W2998792609 @default.
• W4318149008 cites W2999111188 @default.
• W4318149008 cites W3005394220 @default.
• W4318149008 cites W3011394296 @default.
• W4318149008 cites W3015744537 @default.
• W4318149008 cites W3031868989 @default.
• W4318149008 cites W3033235266 @default.
• W4318149008 cites W3034373842 @default.
• W4318149008 cites W3034390599 @default.
• W4318149008 cites W3034580371 @default.
• W4318149008 cites W3034627172 @default.
• W4318149008 cites W3035186652 @default.
• W4318149008 cites W3035645942 @default.
• W4318149008 cites W3092740872 @default.
• W4318149008 cites W3092949934 @default.
• W4318149008 cites W3093418233 @default.
• W4318149008 cites W3098409225 @default.
• W4318149008 cites W3099206234 @default.
• W4318149008 cites W3100506510 @default.
• W4318149008 cites W3105077954 @default.
• W4318149008 cites W3107848599 @default.
• W4318149008 cites W3109976024 @default.
• W4318149008 cites W3114393917 @default.
• W4318149008 cites W3120500219 @default.
• W4318149008 cites W3174480456 @default.
• W4318149008 cites W3203857058 @default.
• W4318149008 cites W3205959870 @default.
• W4318149008 cites W3208382980 @default.
• W4318149008 cites W4214736485 @default.
• W4318149008 cites W4285122421 @default.
• W4318149008 doi "https://doi.org/10.1109/tip.2023.3238642" @default.
• W4318149008 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37022078" @default.
• W4318149008 hasPublicationYear "2023" @default.
• W4318149008 type Work @default.
• W4318149008 citedByCount "9" @default.

• next