HATNet: Hierarchical Attention Transformer With RS-CLIP Patch Tokens for Remote Sensing Image Captioning

Remote sensing image captioning (RSIC) aims to generate natural language descriptions of critical visual content in overhead-view remote sensing images. However, existing methods often produce descriptions with significant omissions and misidentifications of scene types or object counts, particularl...

全面介紹

書目詳細資料

Principais autores:	Zhongle Ren, Jianhua Meng, Cheng Zhang, Shulin Gao, Biao Hou, Weibin Li, Hao Zhu, Licheng Jiao
格式:	Artigo
語言:	Inglês
出版:	IEEE 2025-01-01
叢編:	IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
主題:	Contrastive language-image pretraining (CLIP) remote sensing image captioning (RSIC) Transformer
在線閱讀:	https://ieeexplore.ieee.org/document/11214231/
標簽:	添加標簽 沒有標簽, 成為第一個標記此記錄!