Matches in SemOpenAlex for { <https://semopenalex.org/work/W2534101049> ?p ?o ?g. }
- W2534101049 endingPage "118" @default.
- W2534101049 startingPage "107" @default.
- W2534101049 abstract "With the dramatic development of the Internet, how to exploit large-scale retrieval techniques for multimodal web data has become one of the most popular but challenging problems in computer vision and multimedia. Recently, hashing methods are used for fast nearest neighbor search in large-scale data spaces, by embedding high-dimensional feature descriptors into a similarity preserving Hamming space with a low dimension. Inspired by this, in this paper, we introduce a novel supervised cross-modality hashing framework, which can generate unified binary codes for instances represented in different modalities. Particularly, in the learning phase, each bit of a code can be sequentially learned with a discrete optimization scheme that jointly minimizes its empirical loss based on a boosting strategy. In a bitwise manner, hash functions are then learned for each modality, mapping the corresponding representations into unified hash codes. We regard this approach as cross-modality sequential discrete hashing (CSDH), which can effectively reduce the quantization errors arisen in the oversimplified rounding-off step and thus lead to high-quality binary codes. In the test phase, a simple fusion scheme is utilized to generate a unified hash code for final retrieval by merging the predicted hashing results of an unseen instance from different modalities. The proposed CSDH has been systematically evaluated on three standard data sets: Wiki, MIRFlickr, and NUS-WIDE, and the results show that our method significantly outperforms the state-of-the-art multimodality hashing techniques." @default.
- W2534101049 created "2016-10-28" @default.
- W2534101049 creator A5046605531 @default.
- W2534101049 creator A5057732142 @default.
- W2534101049 creator A5063481044 @default.
- W2534101049 creator A5074492050 @default.
- W2534101049 creator A5077882811 @default.
- W2534101049 creator A5082634513 @default.
- W2534101049 date "2017-01-01" @default.
- W2534101049 modified "2023-10-01" @default.
- W2534101049 title "Sequential Discrete Hashing for Scalable Cross-Modality Similarity Retrieval" @default.
- W2534101049 cites W1910300841 @default.
- W2534101049 cites W1922199343 @default.
- W2534101049 cites W1947372417 @default.
- W2534101049 cites W1970055505 @default.
- W2534101049 cites W1974647172 @default.
- W2534101049 cites W1976258951 @default.
- W2534101049 cites W1997559607 @default.
- W2534101049 cites W2007972815 @default.
- W2534101049 cites W2024046085 @default.
- W2534101049 cites W2025432722 @default.
- W2534101049 cites W2046866204 @default.
- W2534101049 cites W2049993534 @default.
- W2534101049 cites W2058116810 @default.
- W2534101049 cites W2064797228 @default.
- W2534101049 cites W2074668987 @default.
- W2534101049 cites W2076511276 @default.
- W2534101049 cites W2086958058 @default.
- W2534101049 cites W2106277773 @default.
- W2534101049 cites W2106642566 @default.
- W2534101049 cites W2113673182 @default.
- W2534101049 cites W2121378474 @default.
- W2534101049 cites W2123432324 @default.
- W2534101049 cites W2144530948 @default.
- W2534101049 cites W2151103935 @default.
- W2534101049 cites W2153273131 @default.
- W2534101049 cites W2155803963 @default.
- W2534101049 cites W2159373756 @default.
- W2534101049 cites W2164598857 @default.
- W2534101049 cites W2167451801 @default.
- W2534101049 cites W2171790913 @default.
- W2534101049 cites W2197084977 @default.
- W2534101049 cites W2206638072 @default.
- W2534101049 cites W2215369824 @default.
- W2534101049 cites W2220860909 @default.
- W2534101049 cites W2247935935 @default.
- W2534101049 cites W2343306217 @default.
- W2534101049 cites W2412709527 @default.
- W2534101049 cites W242817161 @default.
- W2534101049 cites W2476238768 @default.
- W2534101049 cites W2912236665 @default.
- W2534101049 doi "https://doi.org/10.1109/tip.2016.2619262" @default.
- W2534101049 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/27775517" @default.
- W2534101049 hasPublicationYear "2017" @default.
- W2534101049 type Work @default.
- W2534101049 sameAs 2534101049 @default.
- W2534101049 citedByCount "64" @default.
- W2534101049 countsByYear W25341010492017 @default.
- W2534101049 countsByYear W25341010492018 @default.
- W2534101049 countsByYear W25341010492019 @default.
- W2534101049 countsByYear W25341010492020 @default.
- W2534101049 countsByYear W25341010492021 @default.
- W2534101049 countsByYear W25341010492022 @default.
- W2534101049 countsByYear W25341010492023 @default.
- W2534101049 crossrefType "journal-article" @default.
- W2534101049 hasAuthorship W2534101049A5046605531 @default.
- W2534101049 hasAuthorship W2534101049A5057732142 @default.
- W2534101049 hasAuthorship W2534101049A5063481044 @default.
- W2534101049 hasAuthorship W2534101049A5074492050 @default.
- W2534101049 hasAuthorship W2534101049A5077882811 @default.
- W2534101049 hasAuthorship W2534101049A5082634513 @default.
- W2534101049 hasBestOaLocation W25341010492 @default.
- W2534101049 hasConcept C11413529 @default.
- W2534101049 hasConcept C116058348 @default.
- W2534101049 hasConcept C116738811 @default.
- W2534101049 hasConcept C122907437 @default.
- W2534101049 hasConcept C124101348 @default.
- W2534101049 hasConcept C133667856 @default.
- W2534101049 hasConcept C138111711 @default.
- W2534101049 hasConcept C153180895 @default.
- W2534101049 hasConcept C154945302 @default.
- W2534101049 hasConcept C157125643 @default.
- W2534101049 hasConcept C193319292 @default.
- W2534101049 hasConcept C2779494224 @default.
- W2534101049 hasConcept C33923547 @default.
- W2534101049 hasConcept C38652104 @default.
- W2534101049 hasConcept C41008148 @default.
- W2534101049 hasConcept C48044578 @default.
- W2534101049 hasConcept C48372109 @default.
- W2534101049 hasConcept C57273362 @default.
- W2534101049 hasConcept C63435697 @default.
- W2534101049 hasConcept C67388219 @default.
- W2534101049 hasConcept C73150493 @default.
- W2534101049 hasConcept C74270461 @default.
- W2534101049 hasConcept C77088390 @default.
- W2534101049 hasConcept C80444323 @default.
- W2534101049 hasConcept C94375191 @default.
- W2534101049 hasConcept C99138194 @default.