IntentVLM: Open-Vocabulary Intention Recognition through Forward-Inverse Modeling with Video-Language Models

@misc{rahimi2026intentvlm,
  title = {IntentVLM: Open-Vocabulary Intention Recognition through Forward-Inverse Modeling with Video-Language Models},
  author = {Hamed Rahimi and Clémence Grislain and Adrien Jacquet Crétides and Olivier Sigaud and Mohamed Chetouani},
  year = {2026},
  eprint = {2604.24002},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.24002},
}