Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA

Activitynet-qa: A dataset for understanding complex web videos via question answering

Original

Zhou Yu, D. Xu, Jun Yu, Ting Yu, Zhou Zhao, Yueting Zhuang, and Dacheng Tao. 2019a · 1906

Earlier work this paper cites.

Actions and events in interval temporal logic

James F Allen and George Ferguson. 1994 · 1994

Earlier work this paper cites.

The representation and recognition of action using temporal templates

James Davis and Aaron Bobick. 1997 · 1997

Earlier work this paper cites.

Recognition of visual activities and interactions by stochastic parsing

Yuri A. Ivanov and Aaron F. Bobick. 2000 · 2000

Earlier work this paper cites.

Video-based event recognition: activity representation and probabilistic recognition methods

Somboon Hongeng, Ram Nevatia, and Francois Bremond. 2004 · 2004

Earlier work this paper cites.

Propagation networks for recognition of partially ordered sequential action

Yifan Shi, Yan Huang, David Minnen, Aaron Bobick, and Irfan Essa. 2004 · 2004

Earlier work this paper cites.

Recognition of composite human activities through context-free grammar based representation

Michael S. Ryoo and Jake K. Aggarwal. 2006 · 2006

Earlier work this paper cites.

Human activity analysis

Jake K. Aggarwal and Michael S. Ryoo. 2011 · 2011

Earlier work this paper cites.

Vqa: Visual question answering

Aishwarya Agrawal, Jiasen Lu, Stanislaw Antol, Margaret Mitchell, C. Lawrence Zitnick, Devi Parikh, and Dhruv Batra. 2015 · 2015

Earlier work this paper cites.

MovieQA: Understanding stories in movies through question-answering

Makarand Tapaswi, Yukun Zhu, Rainer Stiefelhagen, Antonio Torralba, Raquel Urtasun, and Sanja Fidler. 2016 · 2016

Earlier work this paper cites.

Video question answering via gradually refined attention over appearance and motion

Dejing Xu, Zhou Zhao, Jun Xiao, Fei Wu, Hanwang Zhang, Xiangnan He, and Yueting Zhuang. 2017 · 2017

Earlier work this paper cites.

Leveraging video descriptions to learn video question answering

Kuo-Hao Zeng, Tseng-Hung Chen, Ching-Yao Chuang, Yuan-Hong Liao, Juan Carlos Niebles, and Min Sun. 2017 · 2017

Earlier work this paper cites.

Single image action recognition using semantic body part actions

Zhichen Zhao, Huimin Ma, and Shaodi You. 2017 · 2017

Earlier work this paper cites.

TVQA: Localized, compositional video question answering

Jie Lei, Licheng Yu, Mohit Bansal, and Tamara Berg. 2018 · 2018

Earlier work this paper cites.

TVQA+: Spatio-temporal grounding for video question answering

Jie Lei, Licheng Yu, Tamara Berg, and Mohit Bansal. 2020 · 2020

Earlier work this paper cites.

NExT-QA: Next phase of question-answering to explaining temporal actions

Junbin Xiao, Xindi Shang, Angela Yao, and Tat-Seng Chua. 2021 · 2021

Earlier work this paper cites.

Revisiting the “video” in video-language understanding

S. Buch, Cristobal Eyzaguirre, Adrien Gaidon, Jiajun Wu, Li Fei-Fei, and Juan Carlos Niebles. 2022 · 2022

Cited alongside, same era.

Knowledge-augmented language models for cause-effect relation classification

Pedram Hosseini, David A. Broniatowski, and Mona Diab. 2022 · 2022

Cited alongside, same era.

From representation to reasoning: Towards both evidence and commonsense reasoning for video question-answering

Jiangtong Li, Li Niu, and Liqing Zhang. 2022 · 2022

Cited alongside, same era.

Zero-shot video question answering via frozen bidirectional language models

Antoine Yang, Antoine Miech, Josef Sivic, Ivan Laptev, and Cordelia Schmid. 2022 · 2022

Cited alongside, same era.

Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond

Original

Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, and Jingren Zhou. 2023 · 2023

Cited alongside, same era.

Vamos: Versatile action models for video understanding

Original

Shijie Wang, Qi Zhao, Minh Quan Do, Nakul Agarwal, Kwonjoon Lee, and Chen Sun. 2023 · 2023

Later among the works it cites.

mplug-owl: Modularization empowers large language models with multimodality

Original

Qinghao Ye, Haiyang Xu, Guohai Xu, Jiabo Ye, Ming Yan, Yiyang Zhou, Junyang Wang, Anwen Hu, Pengcheng Shi, Yaya Shi, et al. 2023 · 2023

Later among the works it cites.

Self-chained image-language model for video localization and question answering

Original

Shoubin Yu, Jaemin Cho, Prateek Yadav, and Mohit Bansal. 2023 · 2023

Later among the works it cites.

A simple llm framework for long-range video question-answering

Original

Ce Zhang, Taixi Lu, Md Mohaiminul Islam, Ziyang Wang, Shoubin Yu, Mohit Bansal, and Gedas Bertasius. 2023 · 2023

Later among the works it cites.