@article{240800365, title = {Multimodal Fusion and Coherence Modeling for Video Topic Segmentation}, author = {Hai Yu and Chong Deng and Qinglin Zhang and Jiaqing Liu and Qian Chen and Wen Wang}, year = {2024}, eprint = {2408.00365}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2408.00365v2}, }