Cross-modal graph with meta concepts for video captioning

• المؤلفون الرئيسيون: Wang, Hao, Lin, Guosheng, Hoi, Steven C. H., Miao, Chunyan
• مؤلفون آخرون: School of Computer Science and Engineering
• التنسيق: مقال
• اللغة: English
• منشور في: 2022
• الموضوعات: Engineering::Computer science and engineering; Video Captioning; Vision-and-Language
• الوصول للمادة أونلاين: https://hdl.handle.net/10356/162546
• المؤسسة: Nanyang Technological University

Video captioning targets interpreting the complex visual contents as text descriptions, which requires the model to fully understand video scenes including objects and their interactions. Prevailing methods adopt off-the-shelf object detection networks to give object proposals and use the attention...