MovieCORE: COgnitive REasoning in Movies
Gueter Josmy Faure, Min-Hung Chen, Jia-Fong Yeh, Ying Cheng, Hung-Ting Su, Yung-Hao Tang, Shang-Hong Lai, Winston H. Hsu
摘要
Contrasts wisdom and warmth (old age) with energy and curiosity (youth). (Q: How are intergenerational themes demonstrated through specific scenes in the video?) Captures shift in emotional state due to external factors. (Q: How do changes in settings impact the elderly character's emotions and sense of identity?) Emotional/Psychological States Character Contrasts Cause-Effect Relationships Figure 1: Beyond Shallow Video Understanding: The proposed benchmark, MovieCORE, challenges visionlanguage models (VLMs) to understand the subtle interplay between emotions (Top, Middle), character dynamics and causality (Middle, Bottom), and psychological complexity (Top, Middle). From empathy to introspection, from wisdom to curiosity MovieCORE tests VLMs' ability to comprehend the deeper elements of movies.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
它引用的顶会 Paper8
- InstructBLIP: Towards General-purpose Vision-Language Models with Instruction TuningWenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong 等NeurIPS 2023 · 被引用 4,013 次
- Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language ModelsMuhammad Maaz, Hanoona Abdul Rasheed, Salman Khan, Fahad KhanACL 2024 · 被引用 279 次
- MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio DescriptionsMattia Soldan, Alejandro Pardo, Juan León Alcázar, Fabian Caba Heilbron 等CVPR 2022 · 被引用 84 次
- HERMES: Temporal-Coherent Long-form Understanding with Episodes and SemanticsGueter Josmy Faure, Jia-Fong Yeh, Min-Hung Chen, Hung-Ting Su 等ICCV 2025 · 被引用 2 次
- Towards Long-Form Video UnderstandingChao-Yuan Wu, Philipp KrähenbühlCVPR 2021
相关 Paper
- HumanVBench: Probing Human-Centric Video Understanding in MLLMs with Automatically Synthesized BenchmarksTing Zhou, Daoyuan Chen, Qirui Jiao, Bolin Ding 等CVPR 2026
- IDA-VLM: Towards Movie Understanding via ID-Aware Large Vision-Language ModelYatai Ji, Shilong Zhang, Jie Wu, Peize Sun 等ICLR 2025
- ShotBench: Expert-Level Cinematic Understanding in Vision-Language ModelsHongbo Liu, Jingwen He, Yi Jin, Dian Zheng 等NeurIPS 2025 · 被引用 24 次
- VidComposition: Can MLLMs Analyze Compositions in Compiled Videos?Yunlong Tang, Junjia Guo, Hang Hua, Susan Liang 等CVPR 2025
- MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language ModelsWenyi Hong, Yean Cheng, Zhuoyi Yang, Weihan Wang 等CVPR 2025
