Matches in SemOpenAlex for { <https://semopenalex.org/work/W2895589658> ?p ?o ?g. }
- W2895589658 endingPage "193" @default.
- W2895589658 startingPage "176" @default.
- W2895589658 abstract "This paper addresses the scalability and robustness issues of estimating labels from imbalanced unlabeled data for unsupervised video-based person re-identification (re-ID). To achieve it, we propose a novel Robust AnChor Embedding (RACE) framework via deep feature representation learning for large-scale unsupervised video re-ID. Within this framework, anchor sequences representing different persons are firstly selected to formulate an anchor graph which also initializes the CNN model to get discriminative feature representations for later label estimation. To accurately estimate labels from unlabeled sequences with noisy frames, robust anchor embedding is introduced based on the regularized affine hull. Efficiency is ensured with kNN anchors embedding instead of the whole anchor set under manifold assumptions. After that, a robust and efficient top-k counts label prediction strategy is proposed to predict the labels of unlabeled image sequences. With the newly estimated labeled sequences, the unified anchor embedding framework enables the feature learning process to be further facilitated. Extensive experimental results on the large-scale dataset show that the proposed method outperforms existing unsupervised video re-ID methods." @default.
- W2895589658 created "2018-10-12" @default.
- W2895589658 creator A5008999954 @default.
- W2895589658 creator A5055543314 @default.
- W2895589658 creator A5079920605 @default.
- W2895589658 date "2018-01-01" @default.
- W2895589658 modified "2023-10-16" @default.
- W2895589658 title "Robust Anchor Embedding for Unsupervised Video Person re-IDentification in the Wild" @default.
- W2895589658 cites W1596233070 @default.
- W2895589658 cites W1906374873 @default.
- W2895589658 cites W1949591461 @default.
- W2895589658 cites W1963702692 @default.
- W2895589658 cites W1978259121 @default.
- W2895589658 cites W2030558520 @default.
- W2895589658 cites W2046835352 @default.
- W2895589658 cites W2065675334 @default.
- W2895589658 cites W2108710284 @default.
- W2895589658 cites W2143159002 @default.
- W2895589658 cites W2194775991 @default.
- W2895589658 cites W2219504084 @default.
- W2895589658 cites W2441160157 @default.
- W2895589658 cites W2463071499 @default.
- W2895589658 cites W2467139031 @default.
- W2895589658 cites W2499468060 @default.
- W2895589658 cites W2502225121 @default.
- W2895589658 cites W2510970676 @default.
- W2895589658 cites W2518754566 @default.
- W2895589658 cites W2520433280 @default.
- W2895589658 cites W2520668558 @default.
- W2895589658 cites W2520831962 @default.
- W2895589658 cites W2550580161 @default.
- W2895589658 cites W2557641257 @default.
- W2895589658 cites W2558661413 @default.
- W2895589658 cites W2584637367 @default.
- W2895589658 cites W2585635281 @default.
- W2895589658 cites W2604211872 @default.
- W2895589658 cites W2604983939 @default.
- W2895589658 cites W2761121566 @default.
- W2895589658 cites W2768166594 @default.
- W2895589658 cites W2778652957 @default.
- W2895589658 cites W2779003141 @default.
- W2895589658 cites W2788846526 @default.
- W2895589658 cites W2795165441 @default.
- W2895589658 cites W2799185441 @default.
- W2895589658 cites W2807957650 @default.
- W2895589658 cites W2808134123 @default.
- W2895589658 cites W2808174311 @default.
- W2895589658 cites W2962698660 @default.
- W2895589658 cites W2963216120 @default.
- W2895589658 cites W2963721283 @default.
- W2895589658 cites W2963736028 @default.
- W2895589658 cites W2963842104 @default.
- W2895589658 cites W2963960612 @default.
- W2895589658 cites W2963989829 @default.
- W2895589658 cites W2964037671 @default.
- W2895589658 cites W2964130064 @default.
- W2895589658 cites W760855798 @default.
- W2895589658 doi "https://doi.org/10.1007/978-3-030-01234-2_11" @default.
- W2895589658 hasPublicationYear "2018" @default.
- W2895589658 type Work @default.
- W2895589658 sameAs 2895589658 @default.
- W2895589658 citedByCount "73" @default.
- W2895589658 countsByYear W28955896582018 @default.
- W2895589658 countsByYear W28955896582019 @default.
- W2895589658 countsByYear W28955896582020 @default.
- W2895589658 countsByYear W28955896582021 @default.
- W2895589658 countsByYear W28955896582022 @default.
- W2895589658 countsByYear W28955896582023 @default.
- W2895589658 crossrefType "book-chapter" @default.
- W2895589658 hasAuthorship W2895589658A5008999954 @default.
- W2895589658 hasAuthorship W2895589658A5055543314 @default.
- W2895589658 hasAuthorship W2895589658A5079920605 @default.
- W2895589658 hasConcept C104317684 @default.
- W2895589658 hasConcept C119857082 @default.
- W2895589658 hasConcept C138885662 @default.
- W2895589658 hasConcept C153180895 @default.
- W2895589658 hasConcept C154945302 @default.
- W2895589658 hasConcept C185592680 @default.
- W2895589658 hasConcept C202444582 @default.
- W2895589658 hasConcept C2776401178 @default.
- W2895589658 hasConcept C33923547 @default.
- W2895589658 hasConcept C41008148 @default.
- W2895589658 hasConcept C41608201 @default.
- W2895589658 hasConcept C41895202 @default.
- W2895589658 hasConcept C48044578 @default.
- W2895589658 hasConcept C55493867 @default.
- W2895589658 hasConcept C59404180 @default.
- W2895589658 hasConcept C63479239 @default.
- W2895589658 hasConcept C77088390 @default.
- W2895589658 hasConcept C8038995 @default.
- W2895589658 hasConcept C92757383 @default.
- W2895589658 hasConcept C97931131 @default.
- W2895589658 hasConceptScore W2895589658C104317684 @default.
- W2895589658 hasConceptScore W2895589658C119857082 @default.
- W2895589658 hasConceptScore W2895589658C138885662 @default.
- W2895589658 hasConceptScore W2895589658C153180895 @default.
- W2895589658 hasConceptScore W2895589658C154945302 @default.
- W2895589658 hasConceptScore W2895589658C185592680 @default.