Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912757566> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W2912757566 abstract "To address the Multiple Object Tracking (MOT) challenge, we propose to enhance the tracklet appearance features, given by a Convolutional Neural Network (CNN), based on the Residual Transfer Learning (RTL) method. Considering that object classification and tracking are significantly different tasks at high level. And that traditional fine-tuning limits the possible variations in all the layers of the network since it changes the last convolutional layers. Beyond that, our proposed method provides more flexibility in terms of modelling the difference between these two tasks with a four-stage training. This transfer approach increases the feature performance compared to traditional CNN fine-tuning. Experiments on the MOT17 challenge show competitive results with the current state-of-the-art methods." @default.
- W2912757566 created "2019-02-21" @default.
- W2912757566 creator A5037298642 @default.
- W2912757566 creator A5055781630 @default.
- W2912757566 creator A5084131335 @default.
- W2912757566 date "2018-11-01" @default.
- W2912757566 modified "2023-10-15" @default.
- W2912757566 title "Residual Transfer Learning for Multiple Object Tracking" @default.
- W2912757566 cites W1531192956 @default.
- W2912757566 cites W1908127633 @default.
- W2912757566 cites W1994762580 @default.
- W2912757566 cites W2083049794 @default.
- W2912757566 cites W2087003958 @default.
- W2912757566 cites W2124781496 @default.
- W2912757566 cites W2194775991 @default.
- W2912757566 cites W2237765446 @default.
- W2912757566 cites W2291627510 @default.
- W2912757566 cites W2477869242 @default.
- W2912757566 cites W2494577018 @default.
- W2912757566 cites W2520234541 @default.
- W2912757566 cites W2579024533 @default.
- W2912757566 cites W2616924599 @default.
- W2912757566 cites W2739374836 @default.
- W2912757566 cites W2765741142 @default.
- W2912757566 cites W2766984662 @default.
- W2912757566 cites W2801120851 @default.
- W2912757566 cites W2963940252 @default.
- W2912757566 doi "https://doi.org/10.1109/avss.2018.8639320" @default.
- W2912757566 hasPublicationYear "2018" @default.
- W2912757566 type Work @default.
- W2912757566 sameAs 2912757566 @default.
- W2912757566 citedByCount "0" @default.
- W2912757566 crossrefType "proceedings-article" @default.
- W2912757566 hasAuthorship W2912757566A5037298642 @default.
- W2912757566 hasAuthorship W2912757566A5055781630 @default.
- W2912757566 hasAuthorship W2912757566A5084131335 @default.
- W2912757566 hasBestOaLocation W29127575662 @default.
- W2912757566 hasConcept C105795698 @default.
- W2912757566 hasConcept C11413529 @default.
- W2912757566 hasConcept C119857082 @default.
- W2912757566 hasConcept C138885662 @default.
- W2912757566 hasConcept C150899416 @default.
- W2912757566 hasConcept C153180895 @default.
- W2912757566 hasConcept C154945302 @default.
- W2912757566 hasConcept C155512373 @default.
- W2912757566 hasConcept C15744967 @default.
- W2912757566 hasConcept C173608175 @default.
- W2912757566 hasConcept C19417346 @default.
- W2912757566 hasConcept C202474056 @default.
- W2912757566 hasConcept C2775936607 @default.
- W2912757566 hasConcept C2776151529 @default.
- W2912757566 hasConcept C2776175482 @default.
- W2912757566 hasConcept C2776401178 @default.
- W2912757566 hasConcept C2780598303 @default.
- W2912757566 hasConcept C2781238097 @default.
- W2912757566 hasConcept C33923547 @default.
- W2912757566 hasConcept C41008148 @default.
- W2912757566 hasConcept C41895202 @default.
- W2912757566 hasConcept C81363708 @default.
- W2912757566 hasConceptScore W2912757566C105795698 @default.
- W2912757566 hasConceptScore W2912757566C11413529 @default.
- W2912757566 hasConceptScore W2912757566C119857082 @default.
- W2912757566 hasConceptScore W2912757566C138885662 @default.
- W2912757566 hasConceptScore W2912757566C150899416 @default.
- W2912757566 hasConceptScore W2912757566C153180895 @default.
- W2912757566 hasConceptScore W2912757566C154945302 @default.
- W2912757566 hasConceptScore W2912757566C155512373 @default.
- W2912757566 hasConceptScore W2912757566C15744967 @default.
- W2912757566 hasConceptScore W2912757566C173608175 @default.
- W2912757566 hasConceptScore W2912757566C19417346 @default.
- W2912757566 hasConceptScore W2912757566C202474056 @default.
- W2912757566 hasConceptScore W2912757566C2775936607 @default.
- W2912757566 hasConceptScore W2912757566C2776151529 @default.
- W2912757566 hasConceptScore W2912757566C2776175482 @default.
- W2912757566 hasConceptScore W2912757566C2776401178 @default.
- W2912757566 hasConceptScore W2912757566C2780598303 @default.
- W2912757566 hasConceptScore W2912757566C2781238097 @default.
- W2912757566 hasConceptScore W2912757566C33923547 @default.
- W2912757566 hasConceptScore W2912757566C41008148 @default.
- W2912757566 hasConceptScore W2912757566C41895202 @default.
- W2912757566 hasConceptScore W2912757566C81363708 @default.
- W2912757566 hasLocation W29127575661 @default.
- W2912757566 hasLocation W29127575662 @default.
- W2912757566 hasLocation W29127575663 @default.
- W2912757566 hasOpenAccess W2912757566 @default.
- W2912757566 hasPrimaryLocation W29127575661 @default.
- W2912757566 hasRelatedWork W2498789492 @default.
- W2912757566 hasRelatedWork W2521347458 @default.
- W2912757566 hasRelatedWork W2560215812 @default.
- W2912757566 hasRelatedWork W2788972299 @default.
- W2912757566 hasRelatedWork W2912550626 @default.
- W2912757566 hasRelatedWork W2925692864 @default.
- W2912757566 hasRelatedWork W2965594636 @default.
- W2912757566 hasRelatedWork W4233449973 @default.
- W2912757566 hasRelatedWork W2729981612 @default.
- W2912757566 hasRelatedWork W2949601986 @default.
- W2912757566 isParatext "false" @default.
- W2912757566 isRetracted "false" @default.
- W2912757566 magId "2912757566" @default.
- W2912757566 workType "article" @default.