Chunjiang He, Gang Yang. DiffSynth-LVOS: Enhancing Language-Guided Video Object Segmentation via Diffusion-Based Synthetic Data Generation. In Jakub Lokoc, Ladislav Peska, Jan Zahálka, Stevan Rudinac, Marc A. Kastner 0001, Jingjing Chen, Min-Chun Hu 0001, Jiaxin Wu 0001, Ujjwal Sharma 0001, editors, MultiMedia Modeling - 32nd International Conference on Multimedia Modeling, MMM 2026, Prague, Czech Republic, January 29-31, 2026, Proceedings, Part I. Volume 16412 of Lecture Notes in Computer Science, pages 595-608, Springer, 2026. [doi]
@inproceedings{HeY26,
title = {DiffSynth-LVOS: Enhancing Language-Guided Video Object Segmentation via Diffusion-Based Synthetic Data Generation},
author = {Chunjiang He and Gang Yang},
year = {2026},
doi = {10.1007/978-981-95-6950-2_42},
url = {https://doi.org/10.1007/978-981-95-6950-2_42},
researchr = {https://researchr.org/publication/HeY26},
cites = {0},
citedby = {0},
pages = {595-608},
booktitle = {MultiMedia Modeling - 32nd International Conference on Multimedia Modeling, MMM 2026, Prague, Czech Republic, January 29-31, 2026, Proceedings, Part I},
editor = {Jakub Lokoc and Ladislav Peska and Jan Zahálka and Stevan Rudinac and Marc A. Kastner 0001 and Jingjing Chen and Min-Chun Hu 0001 and Jiaxin Wu 0001 and Ujjwal Sharma 0001},
volume = {16412},
series = {Lecture Notes in Computer Science},
publisher = {Springer},
isbn = {978-981-95-6950-2},
}