中文
相关论文

相关论文: Cut to the Chase: Training-free Multimodal Summari…

200 篇论文

Multimedia summarization with multimodal output can play an essential role in real-world applications, i.e., automatically generating cover images and titles for news articles or providing introductions to online videos. In this work, we…

计算机视觉与模式识别 · 计算机科学 2022-04-11 Jielin Qiu , Jiacheng Zhu , Mengdi Xu , Franck Dernoncourt , Trung Bui , Zhaowen Wang , Bo Li , Ding Zhao , Hailin Jin

Large Vision-Language Models (LVLMs) face a fundamental dilemma in video reasoning: they are caught between the prohibitive computational costs of verbose reasoning and the hallucination risks of efficient, ungrounded approaches. To resolve…

计算机视觉与模式识别 · 计算机科学 2026-01-13 Yanxiang Huang , Guohua Gao , Zhaoyang Wei , Jianyuan Ni

The rapid increase in multimedia data has spurred advancements in Multimodal Summarization with Multimodal Output (MSMO), which aims to produce a multimodal summary that integrates both text and relevant images. The inherent heterogeneity…

计算机视觉与模式识别 · 计算机科学 2024-08-07 Yanghai Zhang , Ye Liu , Shiwei Wu , Kai Zhang , Xukai Liu , Qi Liu , Enhong Chen

Large Language Models (LLMs) are increasingly using external web content. However, much of this content is not easily digestible by LLMs due to LLM-unfriendly formats and limitations of context length. To address this issue, we propose a…

人工智能 · 计算机科学 2026-02-18 William Brach , Kristián Košťál , Lukas Galke Poech

Multimedia summarization with multimodal output (MSMO) is a recently explored application in language grounding. It plays an essential role in real-world applications, i.e., automatically generating cover images and titles for news articles…

计算机视觉与模式识别 · 计算机科学 2022-10-11 Jielin Qiu , Jiacheng Zhu , Mengdi Xu , Franck Dernoncourt , Trung Bui , Zhaowen Wang , Bo Li , Ding Zhao , Hailin Jin

Events describe happenings in our world that are of importance. Naturally, understanding events mentioned in multimedia content and how they are related forms an important way of comprehending our world. Existing literature can infer if…

计算机视觉与模式识别 · 计算机科学 2023-12-21 Hammad A. Ayyubi , Christopher Thomas , Lovish Chum , Rahul Lokesh , Long Chen , Yulei Niu , Xudong Lin , Xuande Feng , Jaywon Koo , Sounak Ray , Shih-Fu Chang

The increasing volume of video content in educational, professional, and social domains necessitates effective summarization techniques that go beyond traditional unimodal approaches. This paper proposes a behaviour-aware multimodal video…

计算机视觉与模式识别 · 计算机科学 2025-07-01 Md Moinul Islam , Sofoklis Kakouros , Janne Heikkilä , Mourad Oussalah

Event extraction is essential for event understanding and analysis. It supports tasks such as document summarization and decision-making in emergency scenarios. However, existing event extraction approaches have limitations: (1)…

计算与语言 · 计算机科学 2026-04-24 Praval Sharma

Multi-modal Large Language Models (MLLMs) struggle with long videos due to the need for excessive visual tokens. These tokens exceed massively the context length of MLLMs, resulting in filled by redundant task-irrelevant shots. How to…

计算机视觉与模式识别 · 计算机科学 2025-02-12 Jian Hu , Zixu Cheng , Chenyang Si , Wei Li , Shaogang Gong

Visual data and text data are composed of information at multiple granularities. A video can describe a complex scene that is composed of multiple clips or shots, where each depicts a semantically coherent event or action. Similarly, a…

计算机视觉与模式识别 · 计算机科学 2018-10-18 Bowen Zhang , Hexiang Hu , Fei Sha

Traditional temporal action localization (TAL) methods rely on large amounts of detailed annotated data, whereas few-shot TAL reduces this dependence by using only a few training samples to identify unseen action categories. However,…

计算机视觉与模式识别 · 计算机科学 2025-12-29 Mengshi Qi , Hongwei Ji , Wulian Yun , Xianlin Zhang , Huadong Ma

Multimodal abstractive summarization (MAS) aims to produce a concise summary given the multimodal data (text and vision). Existing studies mainly focus on how to effectively use the visual features from the perspective of an article, having…

计算机视觉与模式识别 · 计算机科学 2023-05-05 Yunlong Liang , Fandong Meng , Jinan Xu , Jiaan Wang , Yufeng Chen , Jie Zhou

Multimodal information extraction (MIE) aims to extract structured information from unstructured multimedia content. Due to the diversity of tasks and settings, most current MIE models are task-specific and data-intensive, which limits…

计算与语言 · 计算机科学 2023-10-05 Yuxuan Sun , Kai Zhang , Yu Su

With the advancement of multimedia technologies, news documents and user-generated content are often represented as multiple modalities, making Multimedia Event Extraction (MEE) an increasingly important challenge. However, recent MEE…

计算与语言 · 计算机科学 2024-10-03 Philipp Seeberger , Dominik Wagner , Korbinian Riedhammer

Recent multimodal retrieval methods have endowed text-based retrievers with multimodal capabilities by utilizing pre-training strategies for visual-text alignment. They often directly fuse the two modalities for cross-reference during the…

计算机视觉与模式识别 · 计算机科学 2025-05-22 Yeong-Joon Ju , Ho-Joong Kim , Seong-Whan Lee

We introduce a new task, MultiMedia Event Extraction (M2E2), which aims to extract events and their arguments from multimedia documents. We develop the first benchmark and collect a dataset of 245 multimedia news articles with extensively…

多媒体 · 计算机科学 2020-05-07 Manling Li , Alireza Zareian , Qi Zeng , Spencer Whitehead , Di Lu , Heng Ji , Shih-Fu Chang

The ability to extract compact, meaningful summaries from large-scale and multimodal data is critical for numerous applications, ranging from video analytics to medical reports. Prior methods in cross-modal summarization have often suffered…

计算与语言 · 计算机科学 2025-07-31 Hannah Kim , Sofia Martinez , Jason Lee

Multimedia information retrieval from videos remains a challenging problem. While recent systems have advanced multimodal search through semantic, object, and OCR queries - and can retrieve temporally consecutive scenes - they often rely on…

Multimodal reasoning is a critical component in the pursuit of artificial intelligence systems that exhibit human-like intelligence, especially when tackling complex tasks. While the chain-of-thought (CoT) technique has gained considerable…

人工智能 · 计算机科学 2023-09-26 Jingxuan Wei , Cheng Tan , Zhangyang Gao , Linzhuang Sun , Siyuan Li , Bihui Yu , Ruifeng Guo , Stan Z. Li

Many motion-centric video analysis tasks, such as atomic actions, detecting atypical motor behavior in individuals with autism, or analyzing articulatory motion in real-time MRI of human speech, require efficient and interpretable temporal…

计算机视觉与模式识别 · 计算机科学 2025-06-03 Hong Nguyen , Dung Tran , Hieu Hoang , Phong Nguyen , Shrikanth Narayanan
‹ 上一页 1 2 3 10 下一页 ›