paper-with-me

홈 › Papers

Knowledge-Based Video Question Answering with Unsupervised Scene Descriptions

2020-07-17 · ECCV 2020 8 · Noa Garcia, Yuta Nakashima

To understand movies, humans constantly reason over the dialogues and actions shown in specific scenes and relate them to the overall storyline already seen. Inspired by this behaviour, we design ROLL, a model for knowledge-based video story question answering that leverages three crucial aspects of movie understanding: dialog comprehension, scene reasoning, and storyline recalling. In ROLL, each of these tasks is in charge of extracting rich and diverse information by 1) processing scene dialogues, 2) generating unsupervised video scene descriptions, and 3) obtaining external knowledge in a weakly supervised fashion. To answer a given question correctly, the information generated by each inspired-cognitive task is encoded via Transformers and fused through a modality weighting mechanism, which balances the information from the different sources. Exhaustive evaluation demonstrates the effectiveness of our approach, which yields a new state-of-the-art on two challenging video question answering datasets: KnowIT VQA and TVQA+.

📄 PDF Abstract BibTeX arXiv:2007.08751

Code (1)

noagarcia/ROLL-VideoQA 공식 구현 pytorch

Tasks

Question AnsweringVideo Question AnsweringVisual Question Answering (VQA)

Similar Papers 제목 키워드 기반

Equivariant and Invariant Grounding for Video Question Answering

2022-07-26 · Yicong Li, Xiang Wang, Junbin Xiao, Tat-Seng Chua

Video Question Answering (VideoQA) is the task of answering the natural language questions about a video. Producing an answer requires understanding the interplay across visual scenes in video and linguistic semantics in…

Question AnsweringVideo Question Answering

Recent Advances in Video Question Answering: A Review of Datasets and Methods

2021-01-15 · Devshree Patel, Ratnam Parikh, Yesha Shastri

Video Question Answering (VQA) is a recent emerging challenging task in the field of Computer Vision. Several visual information retrieval techniques like Video Captioning/Description and Video-guided Machine Translation…

Information RetrievalMachine TranslationQuestion AnsweringRetrieval+6

Learning Question-Guided Video Representation for Multi-Turn Video Question Answering

2019-07-31 · WS 2019 9 · Guan-Lin Chao, Abhinav Rastogi, Semih Yavuz, Dilek Hakkani-Tür 외

Understanding and conversing about dynamic scenes is one of the key capabilities of AI agents that navigate the environment and convey useful information to humans. Video question answering is a specific scenario of such…

NavigateQuestion AnsweringText GenerationVideo Question Answering

Invariant Grounding for Video Question Answering

2022-06-06 · CVPR 2022 1 · Yicong Li, Xiang Wang, Junbin Xiao, Wei Ji 외

Video Question Answering (VideoQA) is the task of answering questions about a video. At its core is understanding the alignments between visual scenes in video and linguistic semantics in question to yield the answer. In…

Question AnsweringVideo Question Answering

NEWSKVQA: Knowledge-Aware News Video Question Answering

2022-02-08 · Pranay Gupta, Manish Gupta

Answering questions in the context of videos can be helpful in video indexing, video retrieval systems, video summarization, learning management systems and surveillance video analysis. Although there exists a large body…

Common Sense ReasoningManagementMultiple-choiceQuestion Answering+6