Matches in SemOpenAlex for { <https://semopenalex.org/work/W3037297831> ?p ?o ?g. }
- W3037297831 abstract "Traditional video captioning requests a holistic description of the video, yet the detailed descriptions of the specific objects may not be available. Without associating the moving trajectories, these image-based data-driven methods cannot understand the activities from the spatio-temporal transitions in the inter-object visual features. Besides, adopting ambiguous clip-sentence pairs in training, it goes against learning the multi-modal functional mappings owing to the one-to-many nature. In this paper, we propose a novel task to understand the videos in object-level, named object-oriented video captioning. We introduce the video-based object-oriented video captioning network (OVC)-Net via temporal graph and detail enhancement to effectively analyze the activities along time and stably capture the vision-language connections under small-sample condition. The temporal graph provides useful supplement over previous image-based approaches, allowing to reason the activities from the temporal evolution of visual features and the dynamic movement of spatial locations. The detail enhancement helps to capture the discriminative features among different objects, with which the subsequent captioning module can yield more informative and precise descriptions. Thereafter, we construct a new dataset, providing consistent object-sentence pairs, to facilitate effective cross-modal learning. To demonstrate the effectiveness, we conduct experiments on the new dataset and compare it with the state-of-the-art video captioning methods. From the experimental results, the OVC-Net exhibits the ability of precisely describing the concurrent objects, and achieves the state-of-the-art performance." @default.
- W3037297831 created "2020-07-02" @default.
- W3037297831 creator A5003681868 @default.
- W3037297831 creator A5028293681 @default.
- W3037297831 creator A5039812471 @default.
- W3037297831 creator A5044591447 @default.
- W3037297831 creator A5079650655 @default.
- W3037297831 date "2020-03-08" @default.
- W3037297831 modified "2023-10-18" @default.
- W3037297831 title "OVC-Net: Object-Oriented Video Captioning with Temporal Graph and Detail Enhancement." @default.
- W3037297831 cites W1514535095 @default.
- W3037297831 cites W1522734439 @default.
- W3037297831 cites W1586939924 @default.
- W3037297831 cites W1861492603 @default.
- W3037297831 cites W1947481528 @default.
- W3037297831 cites W2064675550 @default.
- W3037297831 cites W2101105183 @default.
- W3037297831 cites W2108598243 @default.
- W3037297831 cites W2110933980 @default.
- W3037297831 cites W2123301721 @default.
- W3037297831 cites W2139501017 @default.
- W3037297831 cites W2142900973 @default.
- W3037297831 cites W2154652894 @default.
- W3037297831 cites W2157331557 @default.
- W3037297831 cites W2164290393 @default.
- W3037297831 cites W2425121537 @default.
- W3037297831 cites W2550553598 @default.
- W3037297831 cites W2584992898 @default.
- W3037297831 cites W2594785588 @default.
- W3037297831 cites W2613718673 @default.
- W3037297831 cites W2621571501 @default.
- W3037297831 cites W2745461083 @default.
- W3037297831 cites W2767073696 @default.
- W3037297831 cites W2796347433 @default.
- W3037297831 cites W2887712318 @default.
- W3037297831 cites W2899879331 @default.
- W3037297831 cites W2948358897 @default.
- W3037297831 cites W2962681491 @default.
- W3037297831 cites W2962934715 @default.
- W3037297831 cites W2963150697 @default.
- W3037297831 cites W2963576560 @default.
- W3037297831 cites W2963616706 @default.
- W3037297831 cites W2963630207 @default.
- W3037297831 cites W2963758027 @default.
- W3037297831 cites W2963942586 @default.
- W3037297831 cites W2964018924 @default.
- W3037297831 cites W2964241990 @default.
- W3037297831 cites W2981393651 @default.
- W3037297831 cites W2981648413 @default.
- W3037297831 cites W2982723417 @default.
- W3037297831 cites W3104915307 @default.
- W3037297831 hasPublicationYear "2020" @default.
- W3037297831 type Work @default.
- W3037297831 sameAs 3037297831 @default.
- W3037297831 citedByCount "0" @default.
- W3037297831 crossrefType "posted-content" @default.
- W3037297831 hasAuthorship W3037297831A5003681868 @default.
- W3037297831 hasAuthorship W3037297831A5028293681 @default.
- W3037297831 hasAuthorship W3037297831A5039812471 @default.
- W3037297831 hasAuthorship W3037297831A5044591447 @default.
- W3037297831 hasAuthorship W3037297831A5079650655 @default.
- W3037297831 hasConcept C115961682 @default.
- W3037297831 hasConcept C132525143 @default.
- W3037297831 hasConcept C154945302 @default.
- W3037297831 hasConcept C157657479 @default.
- W3037297831 hasConcept C185592680 @default.
- W3037297831 hasConcept C188027245 @default.
- W3037297831 hasConcept C199360897 @default.
- W3037297831 hasConcept C204321447 @default.
- W3037297831 hasConcept C2777530160 @default.
- W3037297831 hasConcept C2780801425 @default.
- W3037297831 hasConcept C2781238097 @default.
- W3037297831 hasConcept C31972630 @default.
- W3037297831 hasConcept C41008148 @default.
- W3037297831 hasConcept C71139939 @default.
- W3037297831 hasConcept C80444323 @default.
- W3037297831 hasConcept C97931131 @default.
- W3037297831 hasConceptScore W3037297831C115961682 @default.
- W3037297831 hasConceptScore W3037297831C132525143 @default.
- W3037297831 hasConceptScore W3037297831C154945302 @default.
- W3037297831 hasConceptScore W3037297831C157657479 @default.
- W3037297831 hasConceptScore W3037297831C185592680 @default.
- W3037297831 hasConceptScore W3037297831C188027245 @default.
- W3037297831 hasConceptScore W3037297831C199360897 @default.
- W3037297831 hasConceptScore W3037297831C204321447 @default.
- W3037297831 hasConceptScore W3037297831C2777530160 @default.
- W3037297831 hasConceptScore W3037297831C2780801425 @default.
- W3037297831 hasConceptScore W3037297831C2781238097 @default.
- W3037297831 hasConceptScore W3037297831C31972630 @default.
- W3037297831 hasConceptScore W3037297831C41008148 @default.
- W3037297831 hasConceptScore W3037297831C71139939 @default.
- W3037297831 hasConceptScore W3037297831C80444323 @default.
- W3037297831 hasConceptScore W3037297831C97931131 @default.
- W3037297831 hasLocation W30372978311 @default.
- W3037297831 hasOpenAccess W3037297831 @default.
- W3037297831 hasPrimaryLocation W30372978311 @default.
- W3037297831 hasRelatedWork W2190406907 @default.
- W3037297831 hasRelatedWork W2731627339 @default.
- W3037297831 hasRelatedWork W2751392123 @default.
- W3037297831 hasRelatedWork W2799042952 @default.