Matches in SemOpenAlex for { <https://semopenalex.org/work/W3159514290> ?p ?o ?g. }
- W3159514290 endingPage "215" @default.
- W3159514290 startingPage "195" @default.
- W3159514290 abstract "The focus of this survey is on the analysis of two modalities of multimodal deep learning: image and text. Unlike classic reviews of deep learning where monomodal image classifiers such as VGG, ResNet and Inception module are central topics, this paper will examine recent multimodal deep models and structures, including auto-encoders, generative adversarial nets and their variants. These models go beyond the simple image classifiers in which they can do uni-directional (e.g. image captioning, image generation) and bi-directional (e.g. cross-modal retrieval, visual question answering) multimodal tasks. Besides, we analyze two aspects of the challenge in terms of better content understanding in deep multimodal applications. We then introduce current ideas and trends in deep multimodal feature learning, such as feature embedding approaches and objective function design, which are crucial in overcoming the aforementioned challenges. Finally, we include several promising directions for future research." @default.
- W3159514290 created "2021-05-10" @default.
- W3159514290 creator A5004895426 @default.
- W3159514290 creator A5017541508 @default.
- W3159514290 creator A5063481044 @default.
- W3159514290 creator A5077114895 @default.
- W3159514290 date "2021-02-01" @default.
- W3159514290 modified "2023-09-26" @default.
- W3159514290 title "New Ideas and Trends in Deep Multimodal Content Understanding: A Review" @default.
- W3159514290 cites W1202352811 @default.
- W3159514290 cites W1566256432 @default.
- W3159514290 cites W2119717200 @default.
- W3159514290 cites W2266728343 @default.
- W3159514290 cites W2529436507 @default.
- W3159514290 cites W2560920409 @default.
- W3159514290 cites W2563399268 @default.
- W3159514290 cites W2606473278 @default.
- W3159514290 cites W2606965845 @default.
- W3159514290 cites W2611884298 @default.
- W3159514290 cites W2619383789 @default.
- W3159514290 cites W2747853580 @default.
- W3159514290 cites W2759653627 @default.
- W3159514290 cites W2767290858 @default.
- W3159514290 cites W2767361967 @default.
- W3159514290 cites W2768428796 @default.
- W3159514290 cites W2778100917 @default.
- W3159514290 cites W2788710361 @default.
- W3159514290 cites W2795794390 @default.
- W3159514290 cites W2795832645 @default.
- W3159514290 cites W2799088654 @default.
- W3159514290 cites W2803259101 @default.
- W3159514290 cites W2808071176 @default.
- W3159514290 cites W2810884800 @default.
- W3159514290 cites W2884001105 @default.
- W3159514290 cites W2886517819 @default.
- W3159514290 cites W2889924266 @default.
- W3159514290 cites W2890531016 @default.
- W3159514290 cites W2890923031 @default.
- W3159514290 cites W2891193211 @default.
- W3159514290 cites W2896348597 @default.
- W3159514290 cites W2900953995 @default.
- W3159514290 cites W2900993617 @default.
- W3159514290 cites W2903377222 @default.
- W3159514290 cites W2903838325 @default.
- W3159514290 cites W2904551248 @default.
- W3159514290 cites W2904713804 @default.
- W3159514290 cites W2905040928 @default.
- W3159514290 cites W2905288264 @default.
- W3159514290 cites W2905434858 @default.
- W3159514290 cites W2905524945 @default.
- W3159514290 cites W2942614241 @default.
- W3159514290 cites W2953016680 @default.
- W3159514290 cites W2962781483 @default.
- W3159514290 cites W2963402808 @default.
- W3159514290 cites W2963536419 @default.
- W3159514290 cites W2963560084 @default.
- W3159514290 cites W2963560969 @default.
- W3159514290 cites W2963656855 @default.
- W3159514290 cites W2963991868 @default.
- W3159514290 cites W2964019343 @default.
- W3159514290 cites W2964092725 @default.
- W3159514290 cites W2964138343 @default.
- W3159514290 cites W2964149283 @default.
- W3159514290 cites W2964303913 @default.
- W3159514290 cites W2966350350 @default.
- W3159514290 cites W2969659868 @default.
- W3159514290 cites W2979739834 @default.
- W3159514290 cites W2983408952 @default.
- W3159514290 cites W2996002873 @default.
- W3159514290 cites W2997143100 @default.
- W3159514290 cites W3015437081 @default.
- W3159514290 cites W3101313921 @default.
- W3159514290 cites W3105204788 @default.
- W3159514290 cites W4249992252 @default.
- W3159514290 cites W639708223 @default.
- W3159514290 doi "https://doi.org/10.1016/j.neucom.2020.10.042" @default.
- W3159514290 hasPublicationYear "2021" @default.
- W3159514290 type Work @default.
- W3159514290 sameAs 3159514290 @default.
- W3159514290 citedByCount "11" @default.
- W3159514290 countsByYear W31595142902022 @default.
- W3159514290 countsByYear W31595142902023 @default.
- W3159514290 crossrefType "journal-article" @default.
- W3159514290 hasAuthorship W3159514290A5004895426 @default.
- W3159514290 hasAuthorship W3159514290A5017541508 @default.
- W3159514290 hasAuthorship W3159514290A5063481044 @default.
- W3159514290 hasAuthorship W3159514290A5077114895 @default.
- W3159514290 hasBestOaLocation W31595142901 @default.
- W3159514290 hasConcept C101738243 @default.
- W3159514290 hasConcept C108583219 @default.
- W3159514290 hasConcept C115961682 @default.
- W3159514290 hasConcept C119857082 @default.
- W3159514290 hasConcept C120665830 @default.
- W3159514290 hasConcept C121332964 @default.
- W3159514290 hasConcept C136764020 @default.
- W3159514290 hasConcept C138885662 @default.
- W3159514290 hasConcept C144024400 @default.
- W3159514290 hasConcept C153180895 @default.