Matches in SemOpenAlex for { <https://semopenalex.org/work/W2996232404> ?p ?o ?g. }
- W2996232404 endingPage "1703" @default.
- W2996232404 startingPage "1692" @default.
- W2996232404 abstract "Zero-Shot Learning (ZSL) has received extensive attention and successes in recent years especially in areas of fine-grained object recognition, retrieval, and image captioning. Key to ZSL is to transfer knowledge from the seen to the unseen classes via auxiliary semantic prototypes (e.g., word or attribute vectors). However, the popularly learned projection functions in previous works cannot generalize well due to non-visual components included in semantic prototypes. Besides, the incompleteness of provided prototypes and captured images has less been considered by the state-of-the-art approaches in ZSL. In this paper, we propose a hierarchical prototype learning formulation to provide a systematical solution (named HPL) for zero-shot recognition. Specifically, HPL is able to obtain discriminability on both seen and unseen class domains by learning visual prototypes respectively under the transductive setting. To narrow the gap of two domains, we further learn the interpretable super-prototypes in both visual and semantic spaces. Meanwhile, the two spaces are further bridged by maximizing their structural consistency. This not only facilitates the representativeness of visual prototypes, but also alleviates the loss of information of semantic prototypes. An extensive group of experiments are then carefully designed and presented, demonstrating that HPL obtains remarkably more favorable efficiency and effectiveness, over currently available alternatives under various settings." @default.
- W2996232404 created "2019-12-26" @default.
- W2996232404 creator A5017102094 @default.
- W2996232404 creator A5028127027 @default.
- W2996232404 creator A5048634974 @default.
- W2996232404 creator A5049225160 @default.
- W2996232404 creator A5078189730 @default.
- W2996232404 date "2020-07-01" @default.
- W2996232404 modified "2023-10-18" @default.
- W2996232404 title "Hierarchical Prototype Learning for Zero-Shot Recognition" @default.
- W2996232404 cites W1999818274 @default.
- W2996232404 cites W2070148066 @default.
- W2996232404 cites W2088748973 @default.
- W2996232404 cites W2091917610 @default.
- W2996232404 cites W2098411764 @default.
- W2996232404 cites W2117539524 @default.
- W2996232404 cites W2123921497 @default.
- W2996232404 cites W2128532956 @default.
- W2996232404 cites W2141350700 @default.
- W2996232404 cites W2165232124 @default.
- W2996232404 cites W2171061940 @default.
- W2996232404 cites W2194775991 @default.
- W2996232404 cites W2209594346 @default.
- W2996232404 cites W2289084343 @default.
- W2996232404 cites W2293561010 @default.
- W2996232404 cites W2405223529 @default.
- W2996232404 cites W2463762378 @default.
- W2996232404 cites W2552383788 @default.
- W2996232404 cites W2603705233 @default.
- W2996232404 cites W2604808168 @default.
- W2996232404 cites W2605805765 @default.
- W2996232404 cites W2609698233 @default.
- W2996232404 cites W2611632661 @default.
- W2996232404 cites W2744242754 @default.
- W2996232404 cites W2748618181 @default.
- W2996232404 cites W2798913983 @default.
- W2996232404 cites W2799215068 @default.
- W2996232404 cites W2808657737 @default.
- W2996232404 cites W2883124384 @default.
- W2996232404 cites W2900393952 @default.
- W2996232404 cites W2910453440 @default.
- W2996232404 cites W2962716320 @default.
- W2996232404 cites W2962762077 @default.
- W2996232404 cites W2963283377 @default.
- W2996232404 cites W2963486920 @default.
- W2996232404 cites W2963499153 @default.
- W2996232404 cites W2963545832 @default.
- W2996232404 cites W2963846885 @default.
- W2996232404 cites W2963936013 @default.
- W2996232404 cites W2963960318 @default.
- W2996232404 cites W2964086552 @default.
- W2996232404 cites W2964307109 @default.
- W2996232404 cites W3099554308 @default.
- W2996232404 cites W3100093508 @default.
- W2996232404 cites W3143107425 @default.
- W2996232404 cites W652269744 @default.
- W2996232404 doi "https://doi.org/10.1109/tmm.2019.2959433" @default.
- W2996232404 hasPublicationYear "2020" @default.
- W2996232404 type Work @default.
- W2996232404 sameAs 2996232404 @default.
- W2996232404 citedByCount "19" @default.
- W2996232404 countsByYear W29962324042019 @default.
- W2996232404 countsByYear W29962324042020 @default.
- W2996232404 countsByYear W29962324042021 @default.
- W2996232404 countsByYear W29962324042022 @default.
- W2996232404 countsByYear W29962324042023 @default.
- W2996232404 crossrefType "journal-article" @default.
- W2996232404 hasAuthorship W2996232404A5017102094 @default.
- W2996232404 hasAuthorship W2996232404A5028127027 @default.
- W2996232404 hasAuthorship W2996232404A5048634974 @default.
- W2996232404 hasAuthorship W2996232404A5049225160 @default.
- W2996232404 hasAuthorship W2996232404A5078189730 @default.
- W2996232404 hasBestOaLocation W29962324042 @default.
- W2996232404 hasConcept C11413529 @default.
- W2996232404 hasConcept C115961682 @default.
- W2996232404 hasConcept C119857082 @default.
- W2996232404 hasConcept C138885662 @default.
- W2996232404 hasConcept C153180895 @default.
- W2996232404 hasConcept C154945302 @default.
- W2996232404 hasConcept C157657479 @default.
- W2996232404 hasConcept C1667742 @default.
- W2996232404 hasConcept C184337299 @default.
- W2996232404 hasConcept C199360897 @default.
- W2996232404 hasConcept C204321447 @default.
- W2996232404 hasConcept C2776436953 @default.
- W2996232404 hasConcept C2777212361 @default.
- W2996232404 hasConcept C2781238097 @default.
- W2996232404 hasConcept C36464697 @default.
- W2996232404 hasConcept C41008148 @default.
- W2996232404 hasConcept C41895202 @default.
- W2996232404 hasConcept C57493831 @default.
- W2996232404 hasConcept C64876066 @default.
- W2996232404 hasConcept C86034646 @default.
- W2996232404 hasConcept C90805587 @default.
- W2996232404 hasConceptScore W2996232404C11413529 @default.
- W2996232404 hasConceptScore W2996232404C115961682 @default.
- W2996232404 hasConceptScore W2996232404C119857082 @default.
- W2996232404 hasConceptScore W2996232404C138885662 @default.