Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313449037> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W4313449037 endingPage "191" @default.
- W4313449037 startingPage "184" @default.
- W4313449037 abstract "Self-supervised point cloud understanding can pre-train the point cloud learning network on a large dataset, which helps boost the performance of fine-tuning on other smaller datasets in downstream tasks. Motivated to design an efficient self-supervised pre-training strategy and capture useful and discriminative representations of the 3D point cloud, we propose ContrastMPCT, a self-reconstruction scheme with the contrastive learning principle. Specifically, two contrastive loss functions are designed for 3D point clouds to maximize the dependence between the input tokens and output tokens of the encoder and fasten the convergence of the model. Extensive experiments show that our pre-training strategy of ContrastMPCT can effectively improve the fine-tuning performance on the downstream tasks, including object classification and part segmentation. Moreover, compared with both CNN-based and Transformer-based existing works, the superior results indicate the efficacy of the proposed method." @default.
- W4313449037 created "2023-01-06" @default.
- W4313449037 creator A5011123518 @default.
- W4313449037 creator A5072652203 @default.
- W4313449037 date "2023-01-01" @default.
- W4313449037 modified "2023-10-10" @default.
- W4313449037 title "Self-Supervised Point Cloud Understanding via Mask Transformer and Contrastive Learning" @default.
- W4313449037 cites W2366389387 @default.
- W4313449037 cites W2553307952 @default.
- W4313449037 cites W2560722161 @default.
- W4313449037 cites W2796426482 @default.
- W4313449037 cites W2886499109 @default.
- W4313449037 cites W2953356739 @default.
- W4313449037 cites W2958073455 @default.
- W4313449037 cites W2960986959 @default.
- W4313449037 cites W2963053547 @default.
- W4313449037 cites W2981440248 @default.
- W4313449037 cites W3034459762 @default.
- W4313449037 cites W3035363555 @default.
- W4313449037 cites W3035524453 @default.
- W4313449037 cites W3094046420 @default.
- W4313449037 cites W3097823560 @default.
- W4313449037 cites W3116959466 @default.
- W4313449037 cites W3118806719 @default.
- W4313449037 cites W3153465022 @default.
- W4313449037 cites W3155390614 @default.
- W4313449037 cites W3157424380 @default.
- W4313449037 cites W3168649818 @default.
- W4313449037 cites W3173783447 @default.
- W4313449037 cites W3177722744 @default.
- W4313449037 cites W3197097949 @default.
- W4313449037 cites W3202611145 @default.
- W4313449037 cites W3203898101 @default.
- W4313449037 cites W4206778101 @default.
- W4313449037 cites W4210668485 @default.
- W4313449037 cites W4214755140 @default.
- W4313449037 cites W4214893857 @default.
- W4313449037 cites W4221087504 @default.
- W4313449037 cites W4284973155 @default.
- W4313449037 cites W4312270234 @default.
- W4313449037 cites W4312788538 @default.
- W4313449037 cites W4313156423 @default.
- W4313449037 doi "https://doi.org/10.1109/lra.2022.3224370" @default.
- W4313449037 hasPublicationYear "2023" @default.
- W4313449037 type Work @default.
- W4313449037 citedByCount "0" @default.
- W4313449037 crossrefType "journal-article" @default.
- W4313449037 hasAuthorship W4313449037A5011123518 @default.
- W4313449037 hasAuthorship W4313449037A5072652203 @default.
- W4313449037 hasConcept C111919701 @default.
- W4313449037 hasConcept C118505674 @default.
- W4313449037 hasConcept C119857082 @default.
- W4313449037 hasConcept C121332964 @default.
- W4313449037 hasConcept C131979681 @default.
- W4313449037 hasConcept C153180895 @default.
- W4313449037 hasConcept C154945302 @default.
- W4313449037 hasConcept C165801399 @default.
- W4313449037 hasConcept C41008148 @default.
- W4313449037 hasConcept C62520636 @default.
- W4313449037 hasConcept C66322947 @default.
- W4313449037 hasConcept C89600930 @default.
- W4313449037 hasConcept C97931131 @default.
- W4313449037 hasConceptScore W4313449037C111919701 @default.
- W4313449037 hasConceptScore W4313449037C118505674 @default.
- W4313449037 hasConceptScore W4313449037C119857082 @default.
- W4313449037 hasConceptScore W4313449037C121332964 @default.
- W4313449037 hasConceptScore W4313449037C131979681 @default.
- W4313449037 hasConceptScore W4313449037C153180895 @default.
- W4313449037 hasConceptScore W4313449037C154945302 @default.
- W4313449037 hasConceptScore W4313449037C165801399 @default.
- W4313449037 hasConceptScore W4313449037C41008148 @default.
- W4313449037 hasConceptScore W4313449037C62520636 @default.
- W4313449037 hasConceptScore W4313449037C66322947 @default.
- W4313449037 hasConceptScore W4313449037C89600930 @default.
- W4313449037 hasConceptScore W4313449037C97931131 @default.
- W4313449037 hasFunder F4320322841 @default.
- W4313449037 hasFunder F4320337111 @default.
- W4313449037 hasIssue "1" @default.
- W4313449037 hasLocation W43134490371 @default.
- W4313449037 hasOpenAccess W4313449037 @default.
- W4313449037 hasPrimaryLocation W43134490371 @default.
- W4313449037 hasRelatedWork W1972656095 @default.
- W4313449037 hasRelatedWork W2024160000 @default.
- W4313449037 hasRelatedWork W2061273563 @default.
- W4313449037 hasRelatedWork W2285052147 @default.
- W4313449037 hasRelatedWork W2729514902 @default.
- W4313449037 hasRelatedWork W2743258233 @default.
- W4313449037 hasRelatedWork W2773500201 @default.
- W4313449037 hasRelatedWork W2970216048 @default.
- W4313449037 hasRelatedWork W2998168123 @default.
- W4313449037 hasRelatedWork W4287995534 @default.
- W4313449037 hasVolume "8" @default.
- W4313449037 isParatext "false" @default.
- W4313449037 isRetracted "false" @default.
- W4313449037 workType "article" @default.