This repository contains a collection of resources and papers on Change Captioning.

To add your work to this repo, feel free to submit the request or contact me at liuchenyang@buaa.edu.cn

🔥 The latest repository will be updated in Github 🥳

🥳 New

🔥 Our survey "Remote Sensing Temporal Vision-Language Models: A Comprehensive Survey": Arxiv || Github 🔥

Remote Sensing Field

Dataset

• Change Captioning Dataset:

| Dataset | Image pairs num| Image sizes| Captions num| Data | Paper | | -------- | :------------: | :--------: | :---------: | :------: | :------: | | LEVIRCC | 10,077 | (256,256) | 50,385 | [data] | [paper] | | DubaiCC | 500 | (50,50) | 2,500 | [data] | [paper] |

• Change Detection and Captioning Dataset:

| Dataset | Image pairs num| Image sizes| Captions num| Mask num| Data | Paper | | -------- | :------------: | :--------: | :---------: | :-----: | :------: | :------: | | LEVIR_MCI | 10,077 | (256,256) | 50,385 | 44,380 |[data] | [paper] |

Paper

• MV-CC: Mask Enhanced Video Model for Remote Sensing Change Caption [paper] [code]

  • Ruixun Liu, Kaiyu Li, Jiayi Song, Dongwei Sun, Xiangyong Cao
  • (2024. 10) Arxiv

• GeoLLaVA: Efficient Fine-Tuned Vision-Language Models for Temporal Change Detection in Remote Sensing [paper] [code]

  • Hosam Elgendy, Ahmed Sharshar, Ahmed Aboeitta, Yasser Ashraf, Mohsen Guizani
  • (2024. 10) Arxiv

• TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data [paper] [code]

  • Jeremy Andrew Irvin, Emily Ruoyu Liu, Joyce Chuyi Chen, Ines Dormoy, Jinyoung Kim, Samar Khanna, Zhuo Zheng, Stefano Ermon
  • (2024. 10) Arxiv

• ChangeMinds: Multi-task Framework for Detecting and Describing Changes in Remote Sensing [paper] [code]

  • Yuduo Wang, Weikang Yu, Michael Kopp, Pedram Ghamisi
  • (2024. 10) Arxiv

• Inter-Temporal Interaction and Symmetric Difference Learning for Remote Sensing Image Change Captioning [paper] [code]

  • Yunpeng Li; Xiangrong Zhang; Xina Cheng; Puhua Chen; Licheng Jiao
  • (2024. 09) IEEE Transactions on Geoscience and Remote Sensing

• CDChat: A Large Multimodal Model for Remote Sensing Change Description [paper] [code]

  • Mubashir Noman, Noor Ahsan, Muzammal Naseer, Hisham Cholakkal, Rao Muhammad Anwer, Salman Khan, Fahad Shahbaz Khan
  • (2024. 09) Arxiv

• Enhancing Perception of Key Changes in Remote Sensing Image Change Captioning [paper] [code]

  • Cong Yang, Zuchao Li, Hongzan Jiao, Zhi Gao, Lefei Zhang
  • (2024. 09) Arxiv

• ChangeChat: An Interactive Model for Remote Sensing Change Analysis via Multimodal Instruction Tuning [paper] [code]

  • Pei Deng, Wenqian Zhou, Hanlin Wu
  • (2024. 09) Arxiv

• MfrNet: A New Multi-Scale Feature Refining Method for Remote Sensing Image Change Captioning [paper]

  • Kaiqi Xu; Yingping Han; Rui Yang; Xiutiao Ye; Yanhe Guo; Hantong Xing; Shuang Wang
  • (2024. 09) 2024 IEEE International Geoscience and Remote Sensing Symposium - IGARSS 2024

• Detection Assisted Change Captioning for Remote Sensing Image [paper]

  • Xiliang Li; Bin Sun; Shutao Li
  • (2024. 09) 2024 IEEE International Geoscience and Remote Sensing Symposium - IGARSS 2024

• Semantic-CC: Boosting Remote Sensing Image Change Captioning via Foundational Knowledge and Semantic Guidance [paper]

  • Yongshuo Zhu, Lu Li, Keyan Chen, Chenyang Liu, Fugen Zhou, Zhenwei Shi
  • (2024. 07) Arxiv

• Scale-wised feature enhancement network for change captioning of remote sensing images [paper]

  • F Zhang, W Zhang, K Xia, H Feng
  • (2024. 07) International Journal of Remote Sensing

• Multi-scale Attentive Fusion Network for Remote Sensing Image Change Captioning [paper]

  • Cai Chen; Yi Wang; Kim-Hui Yap
  • (2024. 07) 2024 IEEE International Symposium on Circuits and Systems (ISCAS)

• Change-Agent: Toward Interactive Comprehensive Remote Sensing Change Interpretation and Analysis [paper] [code]

  • Chenyang Liu; Keyan Chen; Haotian Zhang; Zipeng Qi; Zhengxia Zou; Zhenwei Shi
  • (2024. 07) IEEE Transactions on Geoscience and Remote Sensing

• Towards Temporal Change Explanations from Bi-Temporal Satellite Images [paper]

  • Ryo Tsujimoto, Hiroki Ouchi, Hidetaka Kamigaito, Taro Watanabe
  • (2024. 06) Arxiv

• Intelli-Change Remote Sensing - A Novel Transformer Approach [paper]

  • D Vyshnav, L Gutha, APV Manindra, B Karthikeyan
  • (2024. 06) International Conference on Data Science and Information System (ICDSIS)

• Towards a multimodal framework for remote sensing image change retrieval and captioning [paper] [code]

  • Roger Ferrod, Luigi Di Caro, Dino Ienco
  • (2024. 06) Arxiv

• Context-aware Difference Distilling for Multi-change Captioning [paper] [code]

  • Y Tu, L Li, L Su, ZJ Zha, C Yan, Q Huang
  • (2024. 05) ACL 2024

• Diffusion-RSCC: Diffusion Probabilistic Model for Change Captioning in Remote Sensing Images [paper] [code]

  • X Yu, Y Li, J Ma
  • (2024. 05) Arxiv

• Single-stream Extractor Network with Contrastive Pre-training for Remote Sensing Change Captioning [paper] [code]

  • Q Zhou, J Gao, Y Yuan, Q Wang
  • (2024. 05) IEEE Transactions on Geoscience and Remote Sensing

• A Lightweight Sparse Focus Transformer for Remote Sensing Image Change Captioning [paper] [code]

  • Dongwei Sun; Yajie Bao; Junmin Liu; Xiangyong Cao
  • (2024. 05) IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

• RSCaMa: Remote Sensing Image Change Captioning with State Space Model [paper] [code]

  • C Liu, K Chen, B Chen, H Zhang, Z Zou, Z Shi
  • (2024. 05) IEEE Geoscience and Remote Sensing Letters

• Change Caption for Satellite Images Time Series [paper][code]

  • Wei Peng, Ping Jian, Zhuqing Mao, and Yingying Zhao
  • (2024. 03) IEEE Geoscience and Remote Sensing Letters

• Pixel-Level Change Detection Pseudo-Label Learning for Remote Sensing Change Captioning [paper]

  • Liu C, Chen K, Qi Z, et al.
  • (2024. 01) 2024 IEEE International Geoscience and Remote Sensing Symposium - IGARSS 2024

• Interactive Change-Aware Transformer Network for Remote Sensing Image Change Captioning [paper] [code]

  • Cai C, Wang Y, Yap K H.
  • (2023.11) Remote Sensing

• Changes to Captions: An Attentive Network for Remote Sensing Change Captioning [paper] [code]

  • Chang S, Ghamisi P.
  • (2023. 11) IEEE Trans. Image Process.

• A Decoupling Paradigm with Prompt Learning for Remote Sensing Image Change Captioning [paper] [code]

  • Liu C, Zhao R, Chen J, et al.
  • (2023.10) IEEE Transactions on Geoscience and Remote Sensing

• Progressive Scale-aware Network for Remote sensing Image Change Captioning [paper] [code]

  • Liu C, Yang J, Qi Z, et al.
  • (2023.7) 2023 IEEE International Geoscience and Remote Sensing Symposium IGARSS

• Remote sensing image change captioning with dual-branch transformers: A new method and a large scale dataset [paper] [code]

  • Liu C, Zhao R, Chen H, et al.
  • (2022.11) IEEE Transactions on Geoscience and Remote Sensing

• Change captioning: A new paradigm for multitemporal remote sensing image analysis [paper]

  • Hoxha G, Chouaf S, Melgani F, et al.
  • (2022.08) IEEE Transactions on Geoscience and Remote Sensing

• Captioning changes in bi-temporal remote sensing images [paper]

  • Chouaf S, Hoxha G, Smara Y, et al.
  • (2021.10) 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS

Computer Vision Field

Paper

• OneDiff: A Generalist Model for Image Difference Captioning [paper]

  • Erdong Hu, Longteng Guo, Tongtian Yue, Zijia Zhao, Shuning Xue, Jing Liu
  • (2024) Arxiv

• The STVchrono Dataset: Towards Continuous Change Recognition in Time [paper]

  • Yanjun Sun, Yue Qiu, Mariia Khan, Fumiya Matsuzawa, Kenji Iwata
  • (2024) Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

• Viewpoint-Adaptive Representation Disentanglement Network for Change Captioning [paper]

  • Tu Y, Li L, Su L, et al.
  • (2023) IEEE Transactions on Image Processing

• Self-supervised Cross-view Representation Reconstruction for Change Captioning [paper]

  • Tu Y, Li L, Su L, et al.
  • (2023) ICCV 2023

• Describing and localizing multiple changes with transformers [paper]

  • Qiu Y, Yamamoto S, Nakashima K, et al.
  • (2021) ICCV 2021

• Finding it at another side: A viewpoint-adapted matching encoder for change captioning [paper]

  • Shi X, Yang X, Gu J, et al.
  • (2020) ECCV 2020

• Robust change captioning [paper]

  • Park D H, Darrell T, Rohrbach A.
  • (2019) ICCV 2019