Temporal Insight Enhancement: Mitigating Temporal Hallucination in Video Understanding by Multimodal Large Language Models

Li Sun 0007, Liuan Wang, Jun Sun 0004, Takayuki Okatani. Temporal Insight Enhancement: Mitigating Temporal Hallucination in Video Understanding by Multimodal Large Language Models. In Apostolos Antonacopoulos, Subhasis Chaudhuri, Rama Chellappa, Cheng-Lin Liu 0001, Saumik Bhattacharya, Umapada Pal 0001, editors, Pattern Recognition - 27th International Conference, ICPR 2024, Kolkata, India, December 1-5, 2024, Proceedings, Part VII. Volume 15307 of Lecture Notes in Computer Science, pages 455-473, Springer, 2024. [doi]

Abstract

Abstract is missing.