Matches in SemOpenAlex for { <https://semopenalex.org/work/W4367053463> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4367053463 abstract "Tactile object recognition (TOR) is very important for the accurate perception of robots. Most of the TOR methods usually adopt uniform sampling strategy to randomly select tactile frames from a sequence of frames, which will lead to a dilemma problem, i.e., acquiring the tactile frames with high sampling rate will get lots of redundant data, while the low sampling rate will miss important information. In addition, the existing methods usually adopt single time scale to construct TOR model, which will induce that the generalization capability is not enough for processing the tactile data generated under different grasping speeds. To address the first problem, a novel gradient adaptive sampling (GAS) strategy is proposed, which can adaptively determine the sampling interval according to the importance of tactile data, therefore, the key information can be acquired as much as possible when the number of tactile frames is limited. To handle the second problem, a multiple temporal scale 3D convolutional neural networks (MTS-3DCNNs) model is proposed, which downsamples the input tactile frames with multiple temporal scales (MTSs) and extracts the MTS deep features, and the fused features have better generalization capability for recognizing the object grasped with different speed. Furthermore, the existing lightweight network ResNet3D-18 is modified to obtain a MR3D-18 network which can match the tactile data with smaller size and prevent the overfitting problem. The ablation studies show the effectiveness of GAS strategy, MTS-3DCNNs, and MR3D-18 networks. The comprehensive comparisons with advanced methods demonstrate that our method is SOTA on two benchmarks." @default.
- W4367053463 created "2023-04-27" @default.
- W4367053463 creator A5000359310 @default.
- W4367053463 creator A5019273238 @default.
- W4367053463 creator A5034781601 @default.
- W4367053463 creator A5046597133 @default.
- W4367053463 date "2023-04-26" @default.
- W4367053463 modified "2023-10-11" @default.
- W4367053463 title "Gradient adaptive sampling and multiple temporal scale 3D CNNs for tactile object recognition" @default.
- W4367053463 cites W1973228056 @default.
- W4367053463 cites W2082669075 @default.
- W4367053463 cites W2096243067 @default.
- W4367053463 cites W2538419421 @default.
- W4367053463 cites W2564318728 @default.
- W4367053463 cites W2772584122 @default.
- W4367053463 cites W2805264857 @default.
- W4367053463 cites W2890084868 @default.
- W4367053463 cites W2947434510 @default.
- W4367053463 cites W2981504308 @default.
- W4367053463 cites W2994492048 @default.
- W4367053463 cites W2998030133 @default.
- W4367053463 cites W3112665924 @default.
- W4367053463 cites W3130801148 @default.
- W4367053463 cites W3199440838 @default.
- W4367053463 cites W3214471858 @default.
- W4367053463 cites W4221132833 @default.
- W4367053463 cites W4225374811 @default.
- W4367053463 cites W4225986700 @default.
- W4367053463 cites W4226186112 @default.
- W4367053463 cites W4283747624 @default.
- W4367053463 cites W4285286860 @default.
- W4367053463 cites W4291209117 @default.
- W4367053463 cites W4303712246 @default.
- W4367053463 doi "https://doi.org/10.3389/fnbot.2023.1159168" @default.
- W4367053463 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37180284" @default.
- W4367053463 hasPublicationYear "2023" @default.
- W4367053463 type Work @default.
- W4367053463 citedByCount "0" @default.
- W4367053463 crossrefType "journal-article" @default.
- W4367053463 hasAuthorship W4367053463A5000359310 @default.
- W4367053463 hasAuthorship W4367053463A5019273238 @default.
- W4367053463 hasAuthorship W4367053463A5034781601 @default.
- W4367053463 hasAuthorship W4367053463A5046597133 @default.
- W4367053463 hasBestOaLocation W43670534631 @default.
- W4367053463 hasConcept C106131492 @default.
- W4367053463 hasConcept C134306372 @default.
- W4367053463 hasConcept C140779682 @default.
- W4367053463 hasConcept C153180895 @default.
- W4367053463 hasConcept C154945302 @default.
- W4367053463 hasConcept C177148314 @default.
- W4367053463 hasConcept C22019652 @default.
- W4367053463 hasConcept C2781238097 @default.
- W4367053463 hasConcept C31972630 @default.
- W4367053463 hasConcept C3261483 @default.
- W4367053463 hasConcept C33923547 @default.
- W4367053463 hasConcept C41008148 @default.
- W4367053463 hasConcept C50644808 @default.
- W4367053463 hasConcept C81363708 @default.
- W4367053463 hasConceptScore W4367053463C106131492 @default.
- W4367053463 hasConceptScore W4367053463C134306372 @default.
- W4367053463 hasConceptScore W4367053463C140779682 @default.
- W4367053463 hasConceptScore W4367053463C153180895 @default.
- W4367053463 hasConceptScore W4367053463C154945302 @default.
- W4367053463 hasConceptScore W4367053463C177148314 @default.
- W4367053463 hasConceptScore W4367053463C22019652 @default.
- W4367053463 hasConceptScore W4367053463C2781238097 @default.
- W4367053463 hasConceptScore W4367053463C31972630 @default.
- W4367053463 hasConceptScore W4367053463C3261483 @default.
- W4367053463 hasConceptScore W4367053463C33923547 @default.
- W4367053463 hasConceptScore W4367053463C41008148 @default.
- W4367053463 hasConceptScore W4367053463C50644808 @default.
- W4367053463 hasConceptScore W4367053463C81363708 @default.
- W4367053463 hasFunder F4320321001 @default.
- W4367053463 hasLocation W43670534631 @default.
- W4367053463 hasLocation W43670534632 @default.
- W4367053463 hasLocation W43670534633 @default.
- W4367053463 hasOpenAccess W4367053463 @default.
- W4367053463 hasPrimaryLocation W43670534631 @default.
- W4367053463 hasRelatedWork W1837097281 @default.
- W4367053463 hasRelatedWork W1966410754 @default.
- W4367053463 hasRelatedWork W2007544051 @default.
- W4367053463 hasRelatedWork W2325242284 @default.
- W4367053463 hasRelatedWork W2363840281 @default.
- W4367053463 hasRelatedWork W2767651786 @default.
- W4367053463 hasRelatedWork W2975200075 @default.
- W4367053463 hasRelatedWork W3012393889 @default.
- W4367053463 hasRelatedWork W3081496756 @default.
- W4367053463 hasRelatedWork W3127819136 @default.
- W4367053463 hasVolume "17" @default.
- W4367053463 isParatext "false" @default.
- W4367053463 isRetracted "false" @default.
- W4367053463 workType "article" @default.