Matches in SemOpenAlex for { <https://semopenalex.org/work/W4376133601> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W4376133601 endingPage "13" @default.
- W4376133601 startingPage "1" @default.
- W4376133601 abstract "Convolutional neural networks (CNNs) have been successfully applied to the single target tracking task in recent years. Generally, training a deep CNN model requires numerous labeled training samples, and the number and quality of these samples directly affect the representational capability of the trained model. However, this approach is restrictive in practice, because manually labeling such a large number of training samples is time-consuming and prohibitively expensive. In this article, we propose an active learning method for deep visual tracking, which selects and annotates the unlabeled samples to train the deep CNN model. Under the guidance of active learning, the tracker based on the trained deep CNN model can achieve competitive tracking performance while reducing the labeling cost. More specifically, to ensure the diversity of selected samples, we propose an active learning method based on multiframe collaboration to select those training samples that should be and need to be annotated. Meanwhile, considering the representativeness of these selected samples, we adopt a nearest-neighbor discrimination method based on the average nearest-neighbor distance to screen isolated samples and low-quality samples. Therefore, the training samples’ subset selected based on our method requires only a given budget to maintain the diversity and representativeness of the entire sample set. Furthermore, we adopt a Tversky loss to improve the bounding box estimation of our tracker, which can ensure that the tracker achieves more accurate target states. Extensive experimental results confirm that our active-learning-based tracker (ALT) achieves competitive tracking accuracy and speed compared with state-of-the-art trackers on the seven most challenging evaluation benchmarks. Project website: https://sites.google.com/view/altrack/." @default.
- W4376133601 created "2023-05-12" @default.
- W4376133601 creator A5005421447 @default.
- W4376133601 creator A5019455734 @default.
- W4376133601 creator A5026086568 @default.
- W4376133601 creator A5034967388 @default.
- W4376133601 creator A5036464034 @default.
- W4376133601 creator A5044470103 @default.
- W4376133601 creator A5068725488 @default.
- W4376133601 creator A5071957113 @default.
- W4376133601 date "2023-01-01" @default.
- W4376133601 modified "2023-10-14" @default.
- W4376133601 title "Active Learning for Deep Visual Tracking" @default.
- W4376133601 doi "https://doi.org/10.1109/tnnls.2023.3266837" @default.
- W4376133601 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37163401" @default.
- W4376133601 hasPublicationYear "2023" @default.
- W4376133601 type Work @default.
- W4376133601 citedByCount "4" @default.
- W4376133601 countsByYear W43761336012022 @default.
- W4376133601 countsByYear W43761336012023 @default.
- W4376133601 crossrefType "journal-article" @default.
- W4376133601 hasAuthorship W4376133601A5005421447 @default.
- W4376133601 hasAuthorship W4376133601A5019455734 @default.
- W4376133601 hasAuthorship W4376133601A5026086568 @default.
- W4376133601 hasAuthorship W4376133601A5034967388 @default.
- W4376133601 hasAuthorship W4376133601A5036464034 @default.
- W4376133601 hasAuthorship W4376133601A5044470103 @default.
- W4376133601 hasAuthorship W4376133601A5068725488 @default.
- W4376133601 hasAuthorship W4376133601A5071957113 @default.
- W4376133601 hasBestOaLocation W43761336012 @default.
- W4376133601 hasConcept C105795698 @default.
- W4376133601 hasConcept C108583219 @default.
- W4376133601 hasConcept C115961682 @default.
- W4376133601 hasConcept C119857082 @default.
- W4376133601 hasConcept C147037132 @default.
- W4376133601 hasConcept C153180895 @default.
- W4376133601 hasConcept C154945302 @default.
- W4376133601 hasConcept C15744967 @default.
- W4376133601 hasConcept C177264268 @default.
- W4376133601 hasConcept C185592680 @default.
- W4376133601 hasConcept C19417346 @default.
- W4376133601 hasConcept C198531522 @default.
- W4376133601 hasConcept C199360897 @default.
- W4376133601 hasConcept C2775936607 @default.
- W4376133601 hasConcept C31972630 @default.
- W4376133601 hasConcept C33923547 @default.
- W4376133601 hasConcept C37381756 @default.
- W4376133601 hasConcept C41008148 @default.
- W4376133601 hasConcept C43617362 @default.
- W4376133601 hasConcept C56461940 @default.
- W4376133601 hasConcept C77967617 @default.
- W4376133601 hasConcept C81363708 @default.
- W4376133601 hasConceptScore W4376133601C105795698 @default.
- W4376133601 hasConceptScore W4376133601C108583219 @default.
- W4376133601 hasConceptScore W4376133601C115961682 @default.
- W4376133601 hasConceptScore W4376133601C119857082 @default.
- W4376133601 hasConceptScore W4376133601C147037132 @default.
- W4376133601 hasConceptScore W4376133601C153180895 @default.
- W4376133601 hasConceptScore W4376133601C154945302 @default.
- W4376133601 hasConceptScore W4376133601C15744967 @default.
- W4376133601 hasConceptScore W4376133601C177264268 @default.
- W4376133601 hasConceptScore W4376133601C185592680 @default.
- W4376133601 hasConceptScore W4376133601C19417346 @default.
- W4376133601 hasConceptScore W4376133601C198531522 @default.
- W4376133601 hasConceptScore W4376133601C199360897 @default.
- W4376133601 hasConceptScore W4376133601C2775936607 @default.
- W4376133601 hasConceptScore W4376133601C31972630 @default.
- W4376133601 hasConceptScore W4376133601C33923547 @default.
- W4376133601 hasConceptScore W4376133601C37381756 @default.
- W4376133601 hasConceptScore W4376133601C41008148 @default.
- W4376133601 hasConceptScore W4376133601C43617362 @default.
- W4376133601 hasConceptScore W4376133601C56461940 @default.
- W4376133601 hasConceptScore W4376133601C77967617 @default.
- W4376133601 hasConceptScore W4376133601C81363708 @default.
- W4376133601 hasFunder F4320321001 @default.
- W4376133601 hasFunder F4320321543 @default.
- W4376133601 hasFunder F4320323172 @default.
- W4376133601 hasFunder F4320335777 @default.
- W4376133601 hasFunder F4320335787 @default.
- W4376133601 hasLocation W43761336011 @default.
- W4376133601 hasLocation W43761336012 @default.
- W4376133601 hasLocation W43761336013 @default.
- W4376133601 hasLocation W43761336014 @default.
- W4376133601 hasOpenAccess W4376133601 @default.
- W4376133601 hasPrimaryLocation W43761336011 @default.
- W4376133601 hasRelatedWork W2030712947 @default.
- W4376133601 hasRelatedWork W2597787948 @default.
- W4376133601 hasRelatedWork W2732542196 @default.
- W4376133601 hasRelatedWork W2738221750 @default.
- W4376133601 hasRelatedWork W2951786554 @default.
- W4376133601 hasRelatedWork W3015973434 @default.
- W4376133601 hasRelatedWork W3156786002 @default.
- W4376133601 hasRelatedWork W3211166691 @default.
- W4376133601 hasRelatedWork W4311257506 @default.
- W4376133601 hasRelatedWork W4311594954 @default.
- W4376133601 isParatext "false" @default.
- W4376133601 isRetracted "false" @default.
- W4376133601 workType "article" @default.