中文
相关论文

相关论文: Co-attentional Transformers for Story-Based Video …

200 篇论文

We propose a novel video understanding task by fusing knowledge-based and video question answering. First, we introduce KnowIT VQA, a video dataset with 24,282 human-generated question-answer pairs about a popular sitcom. The dataset…

计算机视觉与模式识别 · 计算机科学 2019-12-25 Noa Garcia , Mayu Otani , Chenhui Chu , Yuta Nakashima

While VideoQA Transformer models demonstrate competitive performance on standard benchmarks, the reasons behind their success are not fully understood. Do these models capture the rich multimodal structures and dynamics from video and text…

计算机视觉与模式识别 · 计算机科学 2024-06-10 Ishaan Singh Rawal , Alexander Matyasko , Shantanu Jaiswal , Basura Fernando , Cheston Tan

Despite advancements in multimodal large language models (MLLMs), current approaches struggle in medium-to-long video understanding due to frame and context length limitations. As a result, these models often depend on frame sampling, which…

计算机视觉与模式识别 · 计算机科学 2025-04-25 Shehreen Azad , Vibhav Vineet , Yogesh Singh Rawat

Recent developments in modeling language and vision have been successfully applied to image question answering. It is both crucial and natural to extend this research direction to the video domain for video question answering (VideoQA).…

计算机视觉与模式识别 · 计算机科学 2019-06-07 Zhou Yu , Dejing Xu , Jun Yu , Ting Yu , Zhou Zhao , Yueting Zhuang , Dacheng Tao

Question-answering (QA) on video contents is a significant challenge for achieving human-level intelligence as it involves both vision and language in real-world settings. Here we demonstrate the possibility of an AI agent performing video…

计算机视觉与模式识别 · 计算机科学 2017-07-05 Kyung-Min Kim , Min-Oh Heo , Seong-Ho Choi , Byoung-Tak Zhang

Devising intelligent agents able to live in an environment and learn by observing the surroundings is a longstanding goal of Artificial Intelligence. From a bare Machine Learning perspective, challenges arise when the agent is prevented…

计算机视觉与模式识别 · 计算机科学 2022-04-27 Matteo Tiezzi , Simone Marullo , Lapo Faggi , Enrico Meloni , Alessandro Betti , Stefano Melacci

Most TextVQA approaches focus on the integration of objects, scene texts and question words by a simple transformer encoder. But this fails to capture the semantic relations between different modalities. The paper proposes a Scene Graph…

计算机视觉与模式识别 · 计算机科学 2023-08-08 Feiqi Cao , Siwen Luo , Felipe Nunez , Zean Wen , Josiah Poon , Caren Han

Significant advancements in video question answering (VideoQA) have been made thanks to thriving large image-language pretraining frameworks. Although these image-language models can efficiently represent both video and language branches,…

计算机视觉与模式识别 · 计算机科学 2024-04-02 Bo Zou , Chao Yang , Yu Qiao , Chengbin Quan , Youjian Zhao

Recent methods for visual question answering rely on large-scale annotated datasets. Manual annotation of questions and answers for videos, however, is tedious, expensive and prevents scalability. In this work, we propose to avoid manual…

计算机视觉与模式识别 · 计算机科学 2021-08-13 Antoine Yang , Antoine Miech , Josef Sivic , Ivan Laptev , Cordelia Schmid

Visual attention plays an important role to understand images and demonstrates its effectiveness in generating natural language descriptions of images. On the other hand, recent studies show that language associated with an image can steer…

计算机视觉与模式识别 · 计算机科学 2016-12-13 Jonghwan Mun , Minsu Cho , Bohyung Han

Recent advancements in attention mechanisms have replaced recurrent neural networks and its variants for machine translation tasks. Transformer using attention mechanism solely achieved state-of-the-art results in sequence modeling. Neural…

计算与语言 · 计算机科学 2020-04-02 Prakhar Thapak , Prodip Hore

Long-form video understanding remains challenging for Vision-Language Models (VLMs) due to the inherent tension between computational constraints and the need to capture information distributed across thousands of frames. Existing…

计算机视觉与模式识别 · 计算机科学 2026-02-05 Junbo Zou , Ziheng Huang , Shengjie Zhang , Liwen Zhang , Weining Shen

Egocentric temporal action segmentation in videos is a crucial task in computer vision with applications in various fields such as mixed reality, human behavior analysis, and robotics. Although recent research has utilized advanced…

计算机视觉与模式识别 · 计算机科学 2023-05-25 Sakib Reza , Balaji Sundareshan , Mohsen Moghaddam , Octavia Camps

Current work on Visual Question Answering (VQA) explore deterministic approaches conditioned on various types of image and question features. We posit that, in addition to image and question pairs, other modalities are useful for teaching…

计算机视觉与模式识别 · 计算机科学 2021-09-28 Zixu Wang , Yishu Miao , Lucia Specia

Transformer is a ubiquitous model for natural language processing and has attracted wide attentions in computer vision. The attention maps are indispensable for a transformer model to encode the dependencies among input tokens. However,…

机器学习 · 计算机科学 2021-02-26 Yujing Wang , Yaming Yang , Jiangang Bai , Mingliang Zhang , Jing Bai , Jing Yu , Ce Zhang , Gao Huang , Yunhai Tong

Attention mechanism has gained huge popularity due to its effectiveness in achieving high accuracy in different domains. But attention is opportunistic and is not justified by the content or usability of the content. Transformer like…

计算机视觉与模式识别 · 计算机科学 2020-06-26 Chiranjib Sur

We introduce Knowledge Fusion Transformers for video action classification. We present a self-attention based feature enhancer to fuse action knowledge in 3D inception based spatio-temporal context of the video clip intended to be…

计算机视觉与模式识别 · 计算机科学 2020-10-01 Ganesh Samarth , Sheetal Ojha , Nikhil Pareek

Video Question Answering (VideoQA) requires identifying sparse critical moments in long videos and reasoning about their causal relationships to answer semantically complex questions. While recent advances in multimodal learning have…

计算机视觉与模式识别 · 计算机科学 2025-08-19 Xinxin Dong , Baoyun Peng , Haokai Ma , Yufei Wang , Zixuan Dong , Fei Hu , Xiaodong Wang

The predominant approach to Visual Question Answering (VQA) demands that the model represents within its weights all of the information required to answer any question about any image. Learning this information from any real training set…

计算机视觉与模式识别 · 计算机科学 2017-11-23 Damien Teney , Anton van den Hengel

Document-based Visual Question Answering poses a challenging task between linguistic sense disambiguation and fine-grained multimodal retrieval. Although there has been encouraging progress in document-based question answering due to the…

计算与语言 · 计算机科学 2023-10-20 Jieting Long , Zewei Shi , Penghao Jiang , Yidong Gan