MECD: Unlocking Multi-Event Causal Discovery in Video Reasoning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917879439425536 |
|---|---|
| author | Chen, Tieyuan Liu, Huabin He, Tianyao Chen, Yihang Gan, Chaofan Ma, Xiao Zhong, Cheng Zhang, Yang Wang, Yingxue Lin, Hui Lin, Weiyao |
| author_facet | Chen, Tieyuan Liu, Huabin He, Tianyao Chen, Yihang Gan, Chaofan Ma, Xiao Zhong, Cheng Zhang, Yang Wang, Yingxue Lin, Hui Lin, Weiyao |
| contents | Video causal reasoning aims to achieve a high-level understanding of video content from a causal perspective. However, current video reasoning tasks are limited in scope, primarily executed in a question-answering paradigm and focusing on short videos containing only a single event and simple causal relationships, lacking comprehensive and structured causality analysis for videos with multiple events. To fill this gap, we introduce a new task and dataset, Multi-Event Causal Discovery (MECD). It aims to uncover the causal relationships between events distributed chronologically across long videos. Given visual segments and textual descriptions of events, MECD requires identifying the causal associations between these events to derive a comprehensive, structured event-level video causal diagram explaining why and how the final result event occurred. To address MECD, we devise a novel framework inspired by the Granger Causality method, using an efficient mask-based event prediction model to perform an Event Granger Test, which estimates causality by comparing the predicted result event when premise events are masked versus unmasked. Furthermore, we integrate causal inference techniques such as front-door adjustment and counterfactual inference to address challenges in MECD like causality confounding and illusory causality. Experiments validate the effectiveness of our framework in providing causal relationships in multi-event videos, outperforming GPT-4o and VideoLLaVA by 5.7% and 4.1%, respectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_17647 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MECD: Unlocking Multi-Event Causal Discovery in Video Reasoning Chen, Tieyuan Liu, Huabin He, Tianyao Chen, Yihang Gan, Chaofan Ma, Xiao Zhong, Cheng Zhang, Yang Wang, Yingxue Lin, Hui Lin, Weiyao Computer Vision and Pattern Recognition Video causal reasoning aims to achieve a high-level understanding of video content from a causal perspective. However, current video reasoning tasks are limited in scope, primarily executed in a question-answering paradigm and focusing on short videos containing only a single event and simple causal relationships, lacking comprehensive and structured causality analysis for videos with multiple events. To fill this gap, we introduce a new task and dataset, Multi-Event Causal Discovery (MECD). It aims to uncover the causal relationships between events distributed chronologically across long videos. Given visual segments and textual descriptions of events, MECD requires identifying the causal associations between these events to derive a comprehensive, structured event-level video causal diagram explaining why and how the final result event occurred. To address MECD, we devise a novel framework inspired by the Granger Causality method, using an efficient mask-based event prediction model to perform an Event Granger Test, which estimates causality by comparing the predicted result event when premise events are masked versus unmasked. Furthermore, we integrate causal inference techniques such as front-door adjustment and counterfactual inference to address challenges in MECD like causality confounding and illusory causality. Experiments validate the effectiveness of our framework in providing causal relationships in multi-event videos, outperforming GPT-4o and VideoLLaVA by 5.7% and 4.1%, respectively. |
| title | MECD: Unlocking Multi-Event Causal Discovery in Video Reasoning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.17647 |