Matches in SemOpenAlex for { <https://semopenalex.org/work/W2304651290> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W2304651290 abstract "Modern deep neural network based object detection methods typically classify candidate proposals using their interior features. However, global and local surrounding contexts that are believed to be valuable for object detection are not fully exploited by existing methods yet. In this work, we take a step towards understanding what is a robust practice to extract and utilize contextual information to facilitate object detection in practice. Specifically, we consider the following two questions: how to identify useful global contextual information for detecting a certain object? and how to exploit local context surrounding a proposal for better inferring its contents?. We provide preliminary answers to these questions through developing a novel Attention to Context Convolution Neural Network (AC-CNN) based object detection model. AC-CNN effectively incorporates global and local contextual information into the region-based CNN (e.g. Fast RCNN) detection model and provides better object detection performance. It consists of one attention-based global contextualized (AGC) sub-network and one multi-scale local contextualized (MLC) sub-network. To capture global context, the AGC sub-network recurrently generates an attention map for an input image to highlight useful global contextual locations, through multiple stacked Long Short-Term Memory (LSTM) layers. For capturing surrounding local context, the MLC sub-network exploits both the inside and outside contextual information of each specific proposal at multiple scales. The global and local context are then fused together for making the final decision for detection. Extensive experiments on PASCAL VOC 2007 and VOC 2012 well demonstrate the superiority of the proposed AC-CNN over well-established baselines. In particular, AC-CNN outperforms the popular Fast-RCNN by 2.0% and 2.2% on VOC 2007 and VOC 2012 in terms of mAP, respectively." @default.
- W2304651290 created "2016-06-24" @default.
- W2304651290 creator A5008141914 @default.
- W2304651290 creator A5033884558 @default.
- W2304651290 creator A5039765869 @default.
- W2304651290 creator A5047878798 @default.
- W2304651290 creator A5081663262 @default.
- W2304651290 creator A5087043856 @default.
- W2304651290 date "2016-03-23" @default.
- W2304651290 modified "2023-09-23" @default.
- W2304651290 title "Attentive Contexts for Object Detection" @default.
- W2304651290 doi "https://doi.org/10.48550/arxiv.1603.07415" @default.
- W2304651290 hasPublicationYear "2016" @default.
- W2304651290 type Work @default.
- W2304651290 sameAs 2304651290 @default.
- W2304651290 citedByCount "0" @default.
- W2304651290 crossrefType "posted-content" @default.
- W2304651290 hasAuthorship W2304651290A5008141914 @default.
- W2304651290 hasAuthorship W2304651290A5033884558 @default.
- W2304651290 hasAuthorship W2304651290A5039765869 @default.
- W2304651290 hasAuthorship W2304651290A5047878798 @default.
- W2304651290 hasAuthorship W2304651290A5081663262 @default.
- W2304651290 hasAuthorship W2304651290A5087043856 @default.
- W2304651290 hasBestOaLocation W23046512901 @default.
- W2304651290 hasConcept C119857082 @default.
- W2304651290 hasConcept C153180895 @default.
- W2304651290 hasConcept C154945302 @default.
- W2304651290 hasConcept C165696696 @default.
- W2304651290 hasConcept C166957645 @default.
- W2304651290 hasConcept C199360897 @default.
- W2304651290 hasConcept C205649164 @default.
- W2304651290 hasConcept C2776151529 @default.
- W2304651290 hasConcept C2779343474 @default.
- W2304651290 hasConcept C2781238097 @default.
- W2304651290 hasConcept C38652104 @default.
- W2304651290 hasConcept C41008148 @default.
- W2304651290 hasConcept C50644808 @default.
- W2304651290 hasConcept C64754055 @default.
- W2304651290 hasConcept C75608658 @default.
- W2304651290 hasConcept C81363708 @default.
- W2304651290 hasConceptScore W2304651290C119857082 @default.
- W2304651290 hasConceptScore W2304651290C153180895 @default.
- W2304651290 hasConceptScore W2304651290C154945302 @default.
- W2304651290 hasConceptScore W2304651290C165696696 @default.
- W2304651290 hasConceptScore W2304651290C166957645 @default.
- W2304651290 hasConceptScore W2304651290C199360897 @default.
- W2304651290 hasConceptScore W2304651290C205649164 @default.
- W2304651290 hasConceptScore W2304651290C2776151529 @default.
- W2304651290 hasConceptScore W2304651290C2779343474 @default.
- W2304651290 hasConceptScore W2304651290C2781238097 @default.
- W2304651290 hasConceptScore W2304651290C38652104 @default.
- W2304651290 hasConceptScore W2304651290C41008148 @default.
- W2304651290 hasConceptScore W2304651290C50644808 @default.
- W2304651290 hasConceptScore W2304651290C64754055 @default.
- W2304651290 hasConceptScore W2304651290C75608658 @default.
- W2304651290 hasConceptScore W2304651290C81363708 @default.
- W2304651290 hasLocation W23046512901 @default.
- W2304651290 hasLocation W23046512902 @default.
- W2304651290 hasOpenAccess W2304651290 @default.
- W2304651290 hasPrimaryLocation W23046512901 @default.
- W2304651290 hasRelatedWork W2304651290 @default.
- W2304651290 hasRelatedWork W2424871898 @default.
- W2304651290 hasRelatedWork W2801801420 @default.
- W2304651290 hasRelatedWork W2952466432 @default.
- W2304651290 hasRelatedWork W3027997911 @default.
- W2304651290 hasRelatedWork W3038672259 @default.
- W2304651290 hasRelatedWork W3135818718 @default.
- W2304651290 hasRelatedWork W4287776258 @default.
- W2304651290 hasRelatedWork W4297914674 @default.
- W2304651290 hasRelatedWork W4318827001 @default.
- W2304651290 isParatext "false" @default.
- W2304651290 isRetracted "false" @default.
- W2304651290 magId "2304651290" @default.
- W2304651290 workType "article" @default.