Matches in SemOpenAlex for { <https://semopenalex.org/work/W4280493911> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4280493911 abstract "In this paper, we propose an end-to-end multi-resolution three-dimensional (3D) capsule network for detecting actions of multiple actors in a video scene. Unlike previous capsule, network-based action recognition does not specifically concern with the individual action of multiple actors in a single scene, our 3D capsule network takes advantage of multi-resolution technique to detect different actions of multiple actors that have different sizes, scales, and aspect ratios. Our 3D capsule network is built on top of 3D convolutional neural network (3DCNN) that extracts spatio-temporal features from video frames inside regions of interest generated by Faster RCNN object detection. We first apply our method to the problem of detecting illegal cheating activities in a classroom examination scene with multiple subjects involved. Second, we test our system on the publicly available and extensively studied UCF-101 dataset. We compare our method with several state-of-the-art 3DCNN-based methods, first the multi-resolution 3DCNN, the single-resolution 3D capsule network, and a combination of both these models. We show that models containing 3D capsule networks have a slight advantage over the conventional 3DCNN and multi-resolution 3DCNN. Our 3D capsule networks not only perform a classification of said actions but also generate videos of single actions. Our experimental results show that the use of multi-resolution pathways in the 3D capsule networks make the result even better. Such findings also hold even when we use pre-trained C3D (convolutional 3D) features to train these networks. We believe that the multiple resolutions capture lower-level features at different scales. At the same time, the 3D capsule layers combine these features in more complex ways than conventional convolutional models." @default.
- W4280493911 created "2022-05-22" @default.
- W4280493911 creator A5037824784 @default.
- W4280493911 creator A5081741492 @default.
- W4280493911 date "2022-05-13" @default.
- W4280493911 modified "2023-09-27" @default.
- W4280493911 title "End-to-End Multi-Resolution 3D Capsule Network for People Action Detection" @default.
- W4280493911 cites W1522734439 @default.
- W4280493911 cites W1861492603 @default.
- W4280493911 cites W1983364832 @default.
- W4280493911 cites W1985957764 @default.
- W4280493911 cites W2016053056 @default.
- W4280493911 cites W2048931426 @default.
- W4280493911 cites W2301358467 @default.
- W4280493911 cites W2507009361 @default.
- W4280493911 cites W2604690669 @default.
- W4280493911 cites W2966661 @default.
- W4280493911 cites W639708223 @default.
- W4280493911 doi "https://doi.org/10.1142/s0218001422550151" @default.
- W4280493911 hasPublicationYear "2022" @default.
- W4280493911 type Work @default.
- W4280493911 citedByCount "1" @default.
- W4280493911 countsByYear W42804939112023 @default.
- W4280493911 crossrefType "journal-article" @default.
- W4280493911 hasAuthorship W4280493911A5037824784 @default.
- W4280493911 hasAuthorship W4280493911A5081741492 @default.
- W4280493911 hasConcept C104122410 @default.
- W4280493911 hasConcept C121332964 @default.
- W4280493911 hasConcept C138268822 @default.
- W4280493911 hasConcept C153180895 @default.
- W4280493911 hasConcept C154945302 @default.
- W4280493911 hasConcept C2778778583 @default.
- W4280493911 hasConcept C2780791683 @default.
- W4280493911 hasConcept C2781238097 @default.
- W4280493911 hasConcept C31972630 @default.
- W4280493911 hasConcept C41008148 @default.
- W4280493911 hasConcept C59822182 @default.
- W4280493911 hasConcept C62520636 @default.
- W4280493911 hasConcept C81363708 @default.
- W4280493911 hasConcept C86803240 @default.
- W4280493911 hasConceptScore W4280493911C104122410 @default.
- W4280493911 hasConceptScore W4280493911C121332964 @default.
- W4280493911 hasConceptScore W4280493911C138268822 @default.
- W4280493911 hasConceptScore W4280493911C153180895 @default.
- W4280493911 hasConceptScore W4280493911C154945302 @default.
- W4280493911 hasConceptScore W4280493911C2778778583 @default.
- W4280493911 hasConceptScore W4280493911C2780791683 @default.
- W4280493911 hasConceptScore W4280493911C2781238097 @default.
- W4280493911 hasConceptScore W4280493911C31972630 @default.
- W4280493911 hasConceptScore W4280493911C41008148 @default.
- W4280493911 hasConceptScore W4280493911C59822182 @default.
- W4280493911 hasConceptScore W4280493911C62520636 @default.
- W4280493911 hasConceptScore W4280493911C81363708 @default.
- W4280493911 hasConceptScore W4280493911C86803240 @default.
- W4280493911 hasFunder F4320323819 @default.
- W4280493911 hasIssue "08" @default.
- W4280493911 hasLocation W42804939111 @default.
- W4280493911 hasOpenAccess W4280493911 @default.
- W4280493911 hasPrimaryLocation W42804939111 @default.
- W4280493911 hasRelatedWork W1837097281 @default.
- W4280493911 hasRelatedWork W1966410754 @default.
- W4280493911 hasRelatedWork W2007544051 @default.
- W4280493911 hasRelatedWork W2030539674 @default.
- W4280493911 hasRelatedWork W2095705906 @default.
- W4280493911 hasRelatedWork W2325242284 @default.
- W4280493911 hasRelatedWork W2363840281 @default.
- W4280493911 hasRelatedWork W2732308154 @default.
- W4280493911 hasRelatedWork W2789220062 @default.
- W4280493911 hasRelatedWork W2975200075 @default.
- W4280493911 hasVolume "36" @default.
- W4280493911 isParatext "false" @default.
- W4280493911 isRetracted "false" @default.
- W4280493911 workType "article" @default.