Matches in SemOpenAlex for { <https://semopenalex.org/work/W2508051605> ?p ?o ?g. }
- W2508051605 abstract "Object detection is a fundamental goal to achieve intelligent visual perception by computers due to the fact that objects are the basic building blocks to achieve higher level image understanding. Among the numerous categories of objects in the real-world, pedestrians are among the most important due to several potential benefits brought about by successful pedestrian detection. Often, pedestrian detectors are trained in state-of-the-art systems using supervised machine learning algorithms which necessitates costly and often tedious manual annotation of pedestrians in the form of precise bounding boxes. In this paper, a novel weakly supervised learning algorithm is proposed to train a pedestrian detector that requires, instead of bounding boxes, only annotations of estimated centres of pedestrians. The algorithm makes use of a pedestrian prior learnt in an unsupervised way from the video and this prior is fused with the given weak supervision information in a systematic manner. By evaluating on publicly available datasets, we demonstrate that our weakly supervised algorithm reduces the cost of manual annotation of pedestrians by more than four times while achieving similar performance to a pedestrian detector trained with standard bounding box annotations." @default.
- W2508051605 created "2016-09-16" @default.
- W2508051605 creator A5013164554 @default.
- W2508051605 date "2016-08-01" @default.
- W2508051605 modified "2023-09-30" @default.
- W2508051605 title "Efficient Labelling of Pedestrian Supervisions" @default.
- W2508051605 cites W1499877760 @default.
- W2508051605 cites W1538131130 @default.
- W2508051605 cites W1570918423 @default.
- W2508051605 cites W1608462934 @default.
- W2508051605 cites W1618905105 @default.
- W2508051605 cites W1693345094 @default.
- W2508051605 cites W1934621328 @default.
- W2508051605 cites W1950935069 @default.
- W2508051605 cites W1952794764 @default.
- W2508051605 cites W1973054923 @default.
- W2508051605 cites W1994304612 @default.
- W2508051605 cites W1994488211 @default.
- W2508051605 cites W2013039598 @default.
- W2508051605 cites W2022148047 @default.
- W2508051605 cites W2031454541 @default.
- W2508051605 cites W2031489346 @default.
- W2508051605 cites W2044313232 @default.
- W2508051605 cites W2087347434 @default.
- W2508051605 cites W2105557521 @default.
- W2508051605 cites W2107775979 @default.
- W2508051605 cites W2109670112 @default.
- W2508051605 cites W2110119381 @default.
- W2508051605 cites W2112343299 @default.
- W2508051605 cites W2116076678 @default.
- W2508051605 cites W2120369594 @default.
- W2508051605 cites W2121274305 @default.
- W2508051605 cites W2125556102 @default.
- W2508051605 cites W2136595724 @default.
- W2508051605 cites W2136724559 @default.
- W2508051605 cites W2137023887 @default.
- W2508051605 cites W2139479830 @default.
- W2508051605 cites W2143373691 @default.
- W2508051605 cites W2148290050 @default.
- W2508051605 cites W2151928481 @default.
- W2508051605 cites W2153185908 @default.
- W2508051605 cites W2161969291 @default.
- W2508051605 cites W2163605009 @default.
- W2508051605 cites W2164598857 @default.
- W2508051605 cites W2165190596 @default.
- W2508051605 cites W2168356304 @default.
- W2508051605 cites W2186827065 @default.
- W2508051605 cites W349740100 @default.
- W2508051605 doi "https://doi.org/10.5565/rev/elcvia.881" @default.
- W2508051605 hasPublicationYear "2016" @default.
- W2508051605 type Work @default.
- W2508051605 sameAs 2508051605 @default.
- W2508051605 citedByCount "0" @default.
- W2508051605 crossrefType "journal-article" @default.
- W2508051605 hasAuthorship W2508051605A5013164554 @default.
- W2508051605 hasBestOaLocation W25080516051 @default.
- W2508051605 hasConcept C115961682 @default.
- W2508051605 hasConcept C119857082 @default.
- W2508051605 hasConcept C124101348 @default.
- W2508051605 hasConcept C127413603 @default.
- W2508051605 hasConcept C147037132 @default.
- W2508051605 hasConcept C153180895 @default.
- W2508051605 hasConcept C154945302 @default.
- W2508051605 hasConcept C22212356 @default.
- W2508051605 hasConcept C2776151529 @default.
- W2508051605 hasConcept C2776321320 @default.
- W2508051605 hasConcept C2777113093 @default.
- W2508051605 hasConcept C2780156472 @default.
- W2508051605 hasConcept C2781238097 @default.
- W2508051605 hasConcept C31972630 @default.
- W2508051605 hasConcept C41008148 @default.
- W2508051605 hasConcept C63584917 @default.
- W2508051605 hasConceptScore W2508051605C115961682 @default.
- W2508051605 hasConceptScore W2508051605C119857082 @default.
- W2508051605 hasConceptScore W2508051605C124101348 @default.
- W2508051605 hasConceptScore W2508051605C127413603 @default.
- W2508051605 hasConceptScore W2508051605C147037132 @default.
- W2508051605 hasConceptScore W2508051605C153180895 @default.
- W2508051605 hasConceptScore W2508051605C154945302 @default.
- W2508051605 hasConceptScore W2508051605C22212356 @default.
- W2508051605 hasConceptScore W2508051605C2776151529 @default.
- W2508051605 hasConceptScore W2508051605C2776321320 @default.
- W2508051605 hasConceptScore W2508051605C2777113093 @default.
- W2508051605 hasConceptScore W2508051605C2780156472 @default.
- W2508051605 hasConceptScore W2508051605C2781238097 @default.
- W2508051605 hasConceptScore W2508051605C31972630 @default.
- W2508051605 hasConceptScore W2508051605C41008148 @default.
- W2508051605 hasConceptScore W2508051605C63584917 @default.
- W2508051605 hasLocation W25080516051 @default.
- W2508051605 hasLocation W25080516052 @default.
- W2508051605 hasLocation W25080516053 @default.
- W2508051605 hasOpenAccess W2508051605 @default.
- W2508051605 hasPrimaryLocation W25080516051 @default.
- W2508051605 hasRelatedWork W1578917250 @default.
- W2508051605 hasRelatedWork W1595095002 @default.
- W2508051605 hasRelatedWork W162995005 @default.
- W2508051605 hasRelatedWork W1996303439 @default.
- W2508051605 hasRelatedWork W2007220461 @default.
- W2508051605 hasRelatedWork W2248800885 @default.
- W2508051605 hasRelatedWork W2276393162 @default.