Matches in SemOpenAlex for { <https://semopenalex.org/work/W3074270321> ?p ?o ?g. }
- W3074270321 endingPage "151691" @default.
- W3074270321 startingPage "151681" @default.
- W3074270321 abstract "One of the major challenges in video object detection is drastic scale changes of objects due to camera motion. In this paper, we propose a two-path Convolutional Long Short-Term Memory (convLSTM) pyramid network designed to extract and convey multi-scale temporal contextual information in order to handle object scale changes efficiently. The proposed two-path convLSTM pyramid consists of a stack of multi-input convLSTM modules. It is updated in top-down and bottom-up pathways so that the temporal contextual information for small-to-large and large-to-small scale changes is exploited. The proposed multi-input convLSTM module uses two input feature maps of different resolutions to store and exchange temporal contextual information of different scales between neighboring convLSTM modules. The outputs of the proposed convLSTM pyramid network constitute a feature pyramid where each feature map contains multi-scale temporal contextual information from earlier frames. The proposed convLSTM pyramid can be combined with various still-image object detectors to improve the performance of video object detection. Experimental results on ImageNet VID dataset show that the proposed method achieves state-of-the-art performance and can handle scale changes efficiently in video object detection." @default.
- W3074270321 created "2020-08-24" @default.
- W3074270321 creator A5034855502 @default.
- W3074270321 creator A5076689613 @default.
- W3074270321 date "2020-01-01" @default.
- W3074270321 modified "2023-10-16" @default.
- W3074270321 title "Video Object Detection With Two-Path Convolutional LSTM Pyramid" @default.
- W3074270321 cites W1536680647 @default.
- W3074270321 cites W2064675550 @default.
- W3074270321 cites W2082007860 @default.
- W3074270321 cites W2117539524 @default.
- W3074270321 cites W2122585011 @default.
- W3074270321 cites W2131774270 @default.
- W3074270321 cites W2143612262 @default.
- W3074270321 cites W2159386181 @default.
- W3074270321 cites W2161969291 @default.
- W3074270321 cites W2183182206 @default.
- W3074270321 cites W2194775991 @default.
- W3074270321 cites W2336589871 @default.
- W3074270321 cites W2565639579 @default.
- W3074270321 cites W2569778727 @default.
- W3074270321 cites W2601564443 @default.
- W3074270321 cites W2793130599 @default.
- W3074270321 cites W2806224701 @default.
- W3074270321 cites W2888845200 @default.
- W3074270321 cites W2895340898 @default.
- W3074270321 cites W2898044248 @default.
- W3074270321 cites W2962855257 @default.
- W3074270321 cites W2963037989 @default.
- W3074270321 cites W2963212638 @default.
- W3074270321 cites W2963446712 @default.
- W3074270321 cites W2963585656 @default.
- W3074270321 cites W2963625188 @default.
- W3074270321 cites W2963653352 @default.
- W3074270321 cites W2963857746 @default.
- W3074270321 cites W2964086649 @default.
- W3074270321 cites W2964286567 @default.
- W3074270321 cites W2969727121 @default.
- W3074270321 cites W2978311037 @default.
- W3074270321 cites W2990578161 @default.
- W3074270321 cites W2994810768 @default.
- W3074270321 cites W639708223 @default.
- W3074270321 cites W764651262 @default.
- W3074270321 doi "https://doi.org/10.1109/access.2020.3017411" @default.
- W3074270321 hasPublicationYear "2020" @default.
- W3074270321 type Work @default.
- W3074270321 sameAs 3074270321 @default.
- W3074270321 citedByCount "8" @default.
- W3074270321 countsByYear W30742703212021 @default.
- W3074270321 countsByYear W30742703212022 @default.
- W3074270321 countsByYear W30742703212023 @default.
- W3074270321 crossrefType "journal-article" @default.
- W3074270321 hasAuthorship W3074270321A5034855502 @default.
- W3074270321 hasAuthorship W3074270321A5076689613 @default.
- W3074270321 hasBestOaLocation W30742703211 @default.
- W3074270321 hasConcept C120665830 @default.
- W3074270321 hasConcept C121332964 @default.
- W3074270321 hasConcept C138885662 @default.
- W3074270321 hasConcept C142575187 @default.
- W3074270321 hasConcept C153180895 @default.
- W3074270321 hasConcept C154945302 @default.
- W3074270321 hasConcept C199360897 @default.
- W3074270321 hasConcept C2776151529 @default.
- W3074270321 hasConcept C2776401178 @default.
- W3074270321 hasConcept C2777735758 @default.
- W3074270321 hasConcept C2778755073 @default.
- W3074270321 hasConcept C2781238097 @default.
- W3074270321 hasConcept C31972630 @default.
- W3074270321 hasConcept C41008148 @default.
- W3074270321 hasConcept C41895202 @default.
- W3074270321 hasConcept C62520636 @default.
- W3074270321 hasConcept C81363708 @default.
- W3074270321 hasConceptScore W3074270321C120665830 @default.
- W3074270321 hasConceptScore W3074270321C121332964 @default.
- W3074270321 hasConceptScore W3074270321C138885662 @default.
- W3074270321 hasConceptScore W3074270321C142575187 @default.
- W3074270321 hasConceptScore W3074270321C153180895 @default.
- W3074270321 hasConceptScore W3074270321C154945302 @default.
- W3074270321 hasConceptScore W3074270321C199360897 @default.
- W3074270321 hasConceptScore W3074270321C2776151529 @default.
- W3074270321 hasConceptScore W3074270321C2776401178 @default.
- W3074270321 hasConceptScore W3074270321C2777735758 @default.
- W3074270321 hasConceptScore W3074270321C2778755073 @default.
- W3074270321 hasConceptScore W3074270321C2781238097 @default.
- W3074270321 hasConceptScore W3074270321C31972630 @default.
- W3074270321 hasConceptScore W3074270321C41008148 @default.
- W3074270321 hasConceptScore W3074270321C41895202 @default.
- W3074270321 hasConceptScore W3074270321C62520636 @default.
- W3074270321 hasConceptScore W3074270321C81363708 @default.
- W3074270321 hasLocation W30742703211 @default.
- W3074270321 hasOpenAccess W3074270321 @default.
- W3074270321 hasPrimaryLocation W30742703211 @default.
- W3074270321 hasRelatedWork W1971759388 @default.
- W3074270321 hasRelatedWork W2007544051 @default.
- W3074270321 hasRelatedWork W2025800131 @default.
- W3074270321 hasRelatedWork W2035456249 @default.
- W3074270321 hasRelatedWork W2095705906 @default.
- W3074270321 hasRelatedWork W2129974284 @default.