中文
相关论文

相关论文: Just Ask: Learning to Answer Questions from Millio…

200 篇论文

Reasoning about causal and temporal event relations in videos is a new destination of Video Question Answering (VideoQA).The major stumbling block to achieve this purpose is the semantic gap between language and video since they are at…

计算机视觉与模式识别 · 计算机科学 2022-11-03 Shaoning Xiao , Long Chen , Kaifeng Gao , Zhao Wang , Yi Yang , Zhimeng Zhang , Jun Xiao

We introduce a novel task, Video Question Generation (Video QG). A Video QG model automatically generates questions given a video clip and its corresponding dialogues. Video QG requires a range of skills -- sentence comprehension, temporal…

计算机视觉与模式识别 · 计算机科学 2020-02-18 Yu-Siang Wang , Hung-Ting Su , Chen-Hsi Chang , Zhe-Yu Liu , Winston H. Hsu

Methodologies for training visual question answering (VQA) models assume the availability of datasets with human-annotated \textit{Image-Question-Answer} (I-Q-A) triplets. This has led to heavy reliance on datasets and a lack of…

计算机视觉与模式识别 · 计算机科学 2021-05-31 Pratyay Banerjee , Tejas Gokhale , Yezhou Yang , Chitta Baral

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…

计算机视觉与模式识别 · 计算机科学 2025-09-30 Jianxin Liang , Tan Yue , Yuxuan Wang , Yueqian Wang , Zhihan Yin , Huishuai Zhang , Dongyan Zhao

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 have preceded the…

计算机视觉与模式识别 · 计算机科学 2021-03-19 Devshree Patel , Ratnam Parikh , Yesha Shastri

Despite their importance in training artificial intelligence systems, large datasets remain challenging to acquire. For example, the ImageNet dataset required fourteen million labels of basic human knowledge, such as whether an image…

计算机视觉与模式识别 · 计算机科学 2020-08-31 Jihyeon Lee , Sho Arora

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 AI-human…

计算与语言 · 计算机科学 2019-08-01 Guan-Lin Chao , Abhinav Rastogi , Semih Yavuz , Dilek Hakkani-Tür , Jindong Chen , Ian Lane

This paper proposes a Video Graph Transformer (VGT) model for Video Quetion Answering (VideoQA). VGT's uniqueness are two-fold: 1) it designs a dynamic graph transformer module which encodes video by explicitly capturing the visual objects,…

计算机视觉与模式识别 · 计算机科学 2022-07-22 Junbin Xiao , Pan Zhou , Tat-Seng Chua , Shuicheng Yan

Remote work and online courses have become important methods of knowledge dissemination, leading to a large number of document-based instructional videos. Unlike traditional video datasets, these videos mainly feature rich-text images and…

计算机视觉与模式识别 · 计算机科学 2025-03-21 Haochen Wang , Kai Hu , Liangcai Gao

Visual Question Answering (VQA) is a fundamental multimodal task that requires models to jointly understand visual and textual information. Early VQA systems relied heavily on language biases, motivating subsequent work to emphasize visual…

计算机视觉与模式识别 · 计算机科学 2026-03-12 Nguyen Anh Tuong , Phan Ba Duc , Nguyen Trung Quoc , Tran Dac Thinh , Dang Duy Lan , Nguyen Quoc Thinh , Tung Le

Visual Question Answering (VQA) is a challenging task that has received increasing attention from both the computer vision and the natural language processing communities. Given an image and a question in natural language, it requires…

计算机视觉与模式识别 · 计算机科学 2016-07-21 Qi Wu , Damien Teney , Peng Wang , Chunhua Shen , Anthony Dick , Anton van den Hengel

Video question answering has recently received a lot of attention from multimodal video researchers. Most video question answering datasets are usually in the form of multiple-choice. But, the model for the multiple-choice task does not…

计算机视觉与模式识别 · 计算机科学 2021-08-12 Donggeon Lee , Seongho Choi , Youwon Jang , Byoung-Tak Zhang

Though beneficial for encouraging the Visual Question Answering (VQA) models to discover the underlying knowledge by exploiting the input-output correlation beyond image and text contexts, the existing knowledge VQA datasets are mostly…

计算机视觉与模式识别 · 计算机科学 2020-12-15 Qingxing Cao , Bailin Li , Xiaodan Liang , Keze Wang , Liang Lin

Methods for teaching machines to answer visual questions have made significant progress in recent years, but current methods still lack important human capabilities, including integrating new visual classes and concepts in a modular manner,…

计算机视觉与模式识别 · 计算机科学 2020-05-27 Ben-Zion Vatashsky , Shimon Ullman

The ideal form of Visual Question Answering requires understanding, grounding and reasoning in the joint space of vision and language and serves as a proxy for the AI task of scene understanding. However, most existing VQA benchmarks are…

计算机视觉与模式识别 · 计算机科学 2023-03-07 Kang Chen , Xiangqian Wu

Video question answering that requires external knowledge beyond the visual content remains a significant challenge in AI systems. While models can effectively answer questions based on direct visual observations, they often falter when…

信息检索 · 计算机科学 2025-02-19 Md Zarif Ul Alam , Hamed Zamani

Visual understanding requires interpreting both natural scenes and the textual information that appears within them, motivating tasks such as Visual Question Answering (VQA). However, current VQA benchmarks overlook scenarios with visually…

计算机视觉与模式识别 · 计算机科学 2025-12-02 Jianing An , Luyang Jiang , Jie Luo , Wenjun Wu , Lei Huang

Question answering (QA) systems are designed to answer natural language questions. Visual QA (VQA) and Spoken QA (SQA) systems extend the textual QA system to accept visual and spoken input respectively. This work aims to create a system…

音频与语音处理 · 电气工程与系统科学 2025-05-30 Nimrod Shabtay , Zvi Kons , Avihu Dekel , Hagai Aronowitz , Ron Hoory , Assaf Arbelle

Deep neural networks facilitate video question answering (VideoQA), but the real-world applications on video streams such as CCTV and live cast place higher demands on the solver. To address the challenges of VideoQA on long videos of…

多媒体 · 计算机科学 2023-03-08 Weikai Kong , Shuhong Ye , Chenglin Yao , Jianfeng Ren

Annotating videos is cumbersome, expensive and not scalable. Yet, many strong video models still rely on manually annotated data. With the recent introduction of the HowTo100M dataset, narrated videos now offer the possibility of learning…

计算机视觉与模式识别 · 计算机科学 2020-08-25 Antoine Miech , Jean-Baptiste Alayrac , Lucas Smaira , Ivan Laptev , Josef Sivic , Andrew Zisserman