Learning Interactions and Relationships Between Movie Characters
Anna Kukleva, Makarand Tapaswi, Ivan Laptev
Abstract
I think I'm in love with you. -You mean, as friends? -No. I mean, for real. -Someday, you'll be back here, honey… on your terms. Mac is Juno's father Juno suggests to Mark Vijay runs with Paulie Juno confesses to Paulie Mac consoles Juno (Mac, Juno) (Juno, Paulie) (Juno, Mark) (Vijay, Paulie) Juno and Paulie are lovers Juno and Mark are strangers Vijay and Paulie are classmates Figure 1: The goal of this work is to jointly predict interactions and relationships between all characters in movies. Some interactions are based on dialog (e.g. suggests, confesses), some are primarily visual (e.g. runs with), and others are based on a fusion of both modalities (e.g. consoles). The colored rows at the bottom highlight when a pair of characters appear in the movie timeline. Their (directed) relationships are presented at the right. Example clips obtained from the movie Juno, 2007.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 36b20298-3a93-41fa-98ae-708c27c45679Cited by top-tier papers11
- AutoAD II: The Sequel - Who, When, and What in Movie Audio DescriptionTengda Han, Max Bain, Arsha Nagrani, Gül Varol et al.ICCV 2023 · 55 citations
- Social Fabric: Tubelet Compositions for Video Relation DetectionShuo Chen, Zenglin Shi, Pascal Mettes, Cees G. M. SnoekICCV 2021 · 25 citations
- Social Relation Reasoning Based on Triangular ConstraintsYunfei Guo, Fei Yin, Wei Feng, Xudong Yan et al.AAAI 2023 · 14 citations
- Pairwise Emotional Relationship Recognition in Drama Videos: Dataset and BenchmarkXun Gao, Yin Zhao, Jie Zhang, Longjun CaiACM MM 2021 · 8 citations
- Dilated Context Integrated Network with Cross-Modal Consensus for Temporal Emotion Localization in VideosJuncheng Li, Junlin Xie, Linchao Zhu, Long Qian et al.ACM MM 2022 · 8 citations
Builds on2
Related papers
- Speech2Action: Cross-Modal Supervision for Action RecognitionArsha Nagrani, Chen Sun, David Ross, Rahul Sukthankar et al.CVPR 2020
- Digital Life Project: Autonomous 3D Characters with Social IntelligenceZhongang Cai, Jianping Jiang, Zhongfei Qing, Xinying Guo et al.CVPR 2024
- A Graph-Based Framework to Bridge Movies and SynopsesYu Xiong, Qingqiu Huang, Lingfeng Guo, Hang Zhou et al.ICCV 2019 · 71 citations
- MovieCORE: COgnitive REasoning in MoviesGueter Josmy Faure, Min-Hung Chen, Jia-Fong Yeh, Ying Cheng et al.EMNLP 2025 · 1 citation
- Learning Heterogeneous Interaction Strengths by Trajectory Prediction with Graph Neural NetworkSeungwoong Ha, Hawoong JeongICLR 2023 · 2 citations
