Matches in SemOpenAlex for { <https://semopenalex.org/work/W3035941596> ?p ?o ?g. }
- W3035941596 endingPage "343" @default.
- W3035941596 startingPage "334" @default.
- W3035941596 abstract "Visual trackers using deep neural networks have demonstrated favorable performance in object tracking. However, training a deep classification network using overlapped initial target regions may lead an overfitted model. To increase the model generalization, we propose an appearance variation adaptation (AVA) tracker that aligns the feature distributions of target regions over time by learning an adaptation mask in an adversarial network. The proposed adversarial network consists of a generator and a discriminator network that compete with each other over optimizing a discriminator loss in a mini-max optimization problem. Specifically, the discriminator network aims to distinguish recent target regions from earlier ones by minimizing the discriminator loss, while the generator network aims to produce an adaptation mask to maximize the discriminator loss. We incorporate a gradient reverse layer in the adversarial network to solve the aforementioned mini-max optimization in an end-to-end manner. We compare the performance of the proposed AVA tracker with the most recent state-of-the-art trackers by doing extensive experiments on OTB50, OTB100, and VOT2016 tracking benchmarks. Among the compared methods, AVA yields the highest area under curve (AUC) score of 0.712 and the highest average precision score of 0.951 on the OTB50 tracking benchmark. It achieves the second best AUC score of 0.688 and the best precision score of 0.924 on the OTB100 tracking benchmark. AVA also achieves the second best expected average overlap (EAO) score of 0.366, the best failure rate of 0.68, and the second best accuracy of 0.53 on the VOT2016 tracking benchmark." @default.
- W3035941596 created "2020-06-25" @default.
- W3035941596 creator A5013520979 @default.
- W3035941596 creator A5067295776 @default.
- W3035941596 date "2020-09-01" @default.
- W3035941596 modified "2023-09-27" @default.
- W3035941596 title "Appearance variation adaptation tracker using adversarial network" @default.
- W3035941596 cites W182940129 @default.
- W3035941596 cites W1857884451 @default.
- W3035941596 cites W1915599933 @default.
- W3035941596 cites W1955514522 @default.
- W3035941596 cites W2089961441 @default.
- W3035941596 cites W2154889144 @default.
- W3035941596 cites W2158592639 @default.
- W3035941596 cites W2244956674 @default.
- W3035941596 cites W2343187456 @default.
- W3035941596 cites W2421627342 @default.
- W3035941596 cites W2473868734 @default.
- W3035941596 cites W2557641257 @default.
- W3035941596 cites W2738318237 @default.
- W3035941596 cites W2740685955 @default.
- W3035941596 cites W2795210153 @default.
- W3035941596 cites W2799058067 @default.
- W3035941596 cites W2885722640 @default.
- W3035941596 cites W2894176037 @default.
- W3035941596 cites W2895588569 @default.
- W3035941596 cites W2927438889 @default.
- W3035941596 cites W2955983623 @default.
- W3035941596 cites W2962824803 @default.
- W3035941596 cites W2963030525 @default.
- W3035941596 cites W2963080758 @default.
- W3035941596 cites W2963251831 @default.
- W3035941596 cites W2963534981 @default.
- W3035941596 cites W2964099610 @default.
- W3035941596 cites W2964111344 @default.
- W3035941596 cites W2964242925 @default.
- W3035941596 cites W2964423614 @default.
- W3035941596 cites W3016186637 @default.
- W3035941596 cites W3028354736 @default.
- W3035941596 cites W3102624093 @default.
- W3035941596 doi "https://doi.org/10.1016/j.neunet.2020.06.011" @default.
- W3035941596 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/32593930" @default.
- W3035941596 hasPublicationYear "2020" @default.
- W3035941596 type Work @default.
- W3035941596 sameAs 3035941596 @default.
- W3035941596 citedByCount "10" @default.
- W3035941596 countsByYear W30359415962020 @default.
- W3035941596 countsByYear W30359415962021 @default.
- W3035941596 countsByYear W30359415962022 @default.
- W3035941596 crossrefType "journal-article" @default.
- W3035941596 hasAuthorship W3035941596A5013520979 @default.
- W3035941596 hasAuthorship W3035941596A5067295776 @default.
- W3035941596 hasConcept C121332964 @default.
- W3035941596 hasConcept C13280743 @default.
- W3035941596 hasConcept C134306372 @default.
- W3035941596 hasConcept C138885662 @default.
- W3035941596 hasConcept C153180895 @default.
- W3035941596 hasConcept C154945302 @default.
- W3035941596 hasConcept C163258240 @default.
- W3035941596 hasConcept C177148314 @default.
- W3035941596 hasConcept C185798385 @default.
- W3035941596 hasConcept C205649164 @default.
- W3035941596 hasConcept C2776401178 @default.
- W3035941596 hasConcept C2778334786 @default.
- W3035941596 hasConcept C2779803651 @default.
- W3035941596 hasConcept C2780992000 @default.
- W3035941596 hasConcept C33923547 @default.
- W3035941596 hasConcept C41008148 @default.
- W3035941596 hasConcept C41895202 @default.
- W3035941596 hasConcept C44870925 @default.
- W3035941596 hasConcept C50644808 @default.
- W3035941596 hasConcept C56461940 @default.
- W3035941596 hasConcept C57501372 @default.
- W3035941596 hasConcept C62520636 @default.
- W3035941596 hasConcept C76155785 @default.
- W3035941596 hasConcept C94915269 @default.
- W3035941596 hasConceptScore W3035941596C121332964 @default.
- W3035941596 hasConceptScore W3035941596C13280743 @default.
- W3035941596 hasConceptScore W3035941596C134306372 @default.
- W3035941596 hasConceptScore W3035941596C138885662 @default.
- W3035941596 hasConceptScore W3035941596C153180895 @default.
- W3035941596 hasConceptScore W3035941596C154945302 @default.
- W3035941596 hasConceptScore W3035941596C163258240 @default.
- W3035941596 hasConceptScore W3035941596C177148314 @default.
- W3035941596 hasConceptScore W3035941596C185798385 @default.
- W3035941596 hasConceptScore W3035941596C205649164 @default.
- W3035941596 hasConceptScore W3035941596C2776401178 @default.
- W3035941596 hasConceptScore W3035941596C2778334786 @default.
- W3035941596 hasConceptScore W3035941596C2779803651 @default.
- W3035941596 hasConceptScore W3035941596C2780992000 @default.
- W3035941596 hasConceptScore W3035941596C33923547 @default.
- W3035941596 hasConceptScore W3035941596C41008148 @default.
- W3035941596 hasConceptScore W3035941596C41895202 @default.
- W3035941596 hasConceptScore W3035941596C44870925 @default.
- W3035941596 hasConceptScore W3035941596C50644808 @default.
- W3035941596 hasConceptScore W3035941596C56461940 @default.
- W3035941596 hasConceptScore W3035941596C57501372 @default.
- W3035941596 hasConceptScore W3035941596C62520636 @default.