Matches in SemOpenAlex for { <https://semopenalex.org/work/W2945578092> ?p ?o ?g. }
- W2945578092 endingPage "2275" @default.
- W2945578092 startingPage "2262" @default.
- W2945578092 abstract "In this paper, we present a novel supervised cross-modal hashing framework, namely Scalable disCRete mATrix faCtorization Hashing (SCRATCH). First, it utilizes collective matrix factorization on original features together with label semantic embedding, to learn the latent representations in a shared latent space. Thereafter, it generates binary hash codes based on the latent representations. During optimization, it avoids using a large n × n similarity matrix and generates hash codes discretely. Besides, based on different objective functions, learning strategy, and features, we further present three models in this framework, i.e., SCRATCH-o, SCRATCH-t, and SCRATCH-d. The first one is a one-step method, learning the hash functions and the binary codes in the same optimization problem. The second is a two-step method, which first generates the binary codes and then learns the hash functions based on the learned hash codes. The third one is a deep version of SCRATCH-t, which utilizes deep neural networks as hash functions. The extensive experiments on two widely used benchmark datasets demonstrate that SCRATCH-o and SCRATCH-t outperform some state-of-the-art shallow hashing methods for cross-modal retrieval. The SCRATCH-d also outperforms some state-of-the-art deep hashing models." @default.
- W2945578092 created "2019-05-29" @default.
- W2945578092 creator A5021275163 @default.
- W2945578092 creator A5029734250 @default.
- W2945578092 creator A5038612499 @default.
- W2945578092 creator A5052168662 @default.
- W2945578092 creator A5077088563 @default.
- W2945578092 creator A5086235570 @default.
- W2945578092 date "2020-07-01" @default.
- W2945578092 modified "2023-10-14" @default.
- W2945578092 title "SCRATCH: A Scalable Discrete Matrix Factorization Hashing Framework for Cross-Modal Retrieval" @default.
- W2945578092 cites W1910300841 @default.
- W2945578092 cites W1922199343 @default.
- W2945578092 cites W1974647172 @default.
- W2945578092 cites W1976258951 @default.
- W2945578092 cites W2007972815 @default.
- W2945578092 cites W2025432722 @default.
- W2945578092 cites W2035517574 @default.
- W2945578092 cites W2041941461 @default.
- W2945578092 cites W2049993534 @default.
- W2945578092 cites W2057069782 @default.
- W2945578092 cites W2086958058 @default.
- W2945578092 cites W2144892774 @default.
- W2945578092 cites W2171790913 @default.
- W2945578092 cites W2194775991 @default.
- W2945578092 cites W2247935935 @default.
- W2945578092 cites W2266728343 @default.
- W2945578092 cites W2282231212 @default.
- W2945578092 cites W2411707397 @default.
- W2945578092 cites W2435696002 @default.
- W2945578092 cites W2512032049 @default.
- W2945578092 cites W2513342512 @default.
- W2945578092 cites W2588651547 @default.
- W2945578092 cites W2589952946 @default.
- W2945578092 cites W2591669147 @default.
- W2945578092 cites W2598003564 @default.
- W2945578092 cites W2606965845 @default.
- W2945578092 cites W2621122741 @default.
- W2945578092 cites W2624945720 @default.
- W2945578092 cites W2678677036 @default.
- W2945578092 cites W2733636222 @default.
- W2945578092 cites W2739103128 @default.
- W2945578092 cites W2739130108 @default.
- W2945578092 cites W2748725735 @default.
- W2945578092 cites W2752345995 @default.
- W2945578092 cites W2752930373 @default.
- W2945578092 cites W2755721434 @default.
- W2945578092 cites W2763874937 @default.
- W2945578092 cites W2765440071 @default.
- W2945578092 cites W2766623491 @default.
- W2945578092 cites W2781821509 @default.
- W2945578092 cites W2788387286 @default.
- W2945578092 cites W2798762763 @default.
- W2945578092 cites W2799214875 @default.
- W2945578092 cites W2886523323 @default.
- W2945578092 cites W2887712318 @default.
- W2945578092 cites W2894963073 @default.
- W2945578092 cites W2896038883 @default.
- W2945578092 cites W2909781645 @default.
- W2945578092 cites W2963187862 @default.
- W2945578092 cites W2964280870 @default.
- W2945578092 cites W3098232083 @default.
- W2945578092 cites W840129875 @default.
- W2945578092 doi "https://doi.org/10.1109/tcsvt.2019.2911359" @default.
- W2945578092 hasPublicationYear "2020" @default.
- W2945578092 type Work @default.
- W2945578092 sameAs 2945578092 @default.
- W2945578092 citedByCount "64" @default.
- W2945578092 countsByYear W29455780922019 @default.
- W2945578092 countsByYear W29455780922020 @default.
- W2945578092 countsByYear W29455780922021 @default.
- W2945578092 countsByYear W29455780922022 @default.
- W2945578092 countsByYear W29455780922023 @default.
- W2945578092 crossrefType "journal-article" @default.
- W2945578092 hasAuthorship W2945578092A5021275163 @default.
- W2945578092 hasAuthorship W2945578092A5029734250 @default.
- W2945578092 hasAuthorship W2945578092A5038612499 @default.
- W2945578092 hasAuthorship W2945578092A5052168662 @default.
- W2945578092 hasAuthorship W2945578092A5077088563 @default.
- W2945578092 hasAuthorship W2945578092A5086235570 @default.
- W2945578092 hasConcept C111919701 @default.
- W2945578092 hasConcept C11413529 @default.
- W2945578092 hasConcept C116058348 @default.
- W2945578092 hasConcept C122907437 @default.
- W2945578092 hasConcept C133667856 @default.
- W2945578092 hasConcept C137836250 @default.
- W2945578092 hasConcept C138111711 @default.
- W2945578092 hasConcept C145671259 @default.
- W2945578092 hasConcept C154945302 @default.
- W2945578092 hasConcept C2781235140 @default.
- W2945578092 hasConcept C33923547 @default.
- W2945578092 hasConcept C38652104 @default.
- W2945578092 hasConcept C41008148 @default.
- W2945578092 hasConcept C48044578 @default.
- W2945578092 hasConcept C48372109 @default.
- W2945578092 hasConcept C63435697 @default.
- W2945578092 hasConcept C67388219 @default.
- W2945578092 hasConcept C77088390 @default.