Beyond Isolated Facts: Synthesizing Narrative and Grounded Supervision for VideoQA

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liang, Jianxin, Yue, Tan, Wang, Yuxuan, Wang, Yueqian, Yin, Zhihan, Zhang, Huishuai, Zhao, Dongyan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916976204447744
author Liang, Jianxin
Yue, Tan
Wang, Yuxuan
Wang, Yueqian
Yin, Zhihan
Zhang, Huishuai
Zhao, Dongyan
author_facet Liang, Jianxin
Yue, Tan
Wang, Yuxuan
Wang, Yueqian
Yin, Zhihan
Zhang, Huishuai
Zhao, Dongyan
contents The performance of Video Question Answering (VideoQA) models is fundamentally constrained by the nature of their supervision, which typically consists of isolated, factual question-answer pairs. This "bag-of-facts" approach fails to capture the underlying narrative and causal structure of events, limiting models to a shallow understanding of video content. To move beyond this paradigm, we introduce a framework to synthesize richer supervisory signals. We propose two complementary strategies: Question-Based Paraphrasing (QBP), which synthesizes the diverse inquiries (what, how, why) from a video's existing set of question-answer pairs into a holistic narrative paragraph that reconstructs the video's event structure; and Question-Based Captioning (QBC), which generates fine-grained visual rationales, grounding the answer to each question in specific, relevant evidence. Leveraging powerful generative models, we use this synthetic data to train VideoQA models under a unified next-token prediction objective. Extensive experiments on STAR and NExT-QA validate our approach, demonstrating significant accuracy gains and establishing new state-of-the-art results, such as improving a 3B model to 72.5\% on STAR (+4.9\%) and a 7B model to 80.8\% on NExT-QA. Beyond accuracy, our analysis reveals that both QBP and QBC substantially enhance cross-dataset generalization, with QBP additionally accelerating model convergence by over 2.5x. These results demonstrate that shifting data synthesis from isolated facts to narrative coherence and grounded rationales yields a more accurate, efficient, and generalizable training paradigm.
format Preprint
id arxiv_https___arxiv_org_abs_2509_24445
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Beyond Isolated Facts: Synthesizing Narrative and Grounded Supervision for VideoQA
Liang, Jianxin
Yue, Tan
Wang, Yuxuan
Wang, Yueqian
Yin, Zhihan
Zhang, Huishuai
Zhao, Dongyan
Computer Vision and Pattern Recognition
Computation and Language
The performance of Video Question Answering (VideoQA) models is fundamentally constrained by the nature of their supervision, which typically consists of isolated, factual question-answer pairs. This "bag-of-facts" approach fails to capture the underlying narrative and causal structure of events, limiting models to a shallow understanding of video content. To move beyond this paradigm, we introduce a framework to synthesize richer supervisory signals. We propose two complementary strategies: Question-Based Paraphrasing (QBP), which synthesizes the diverse inquiries (what, how, why) from a video's existing set of question-answer pairs into a holistic narrative paragraph that reconstructs the video's event structure; and Question-Based Captioning (QBC), which generates fine-grained visual rationales, grounding the answer to each question in specific, relevant evidence. Leveraging powerful generative models, we use this synthetic data to train VideoQA models under a unified next-token prediction objective. Extensive experiments on STAR and NExT-QA validate our approach, demonstrating significant accuracy gains and establishing new state-of-the-art results, such as improving a 3B model to 72.5\% on STAR (+4.9\%) and a 7B model to 80.8\% on NExT-QA. Beyond accuracy, our analysis reveals that both QBP and QBC substantially enhance cross-dataset generalization, with QBP additionally accelerating model convergence by over 2.5x. These results demonstrate that shifting data synthesis from isolated facts to narrative coherence and grounded rationales yields a more accurate, efficient, and generalizable training paradigm.
title Beyond Isolated Facts: Synthesizing Narrative and Grounded Supervision for VideoQA
topic Computer Vision and Pattern Recognition
Computation and Language
url https://arxiv.org/abs/2509.24445