中文
相关论文

相关论文: Espresso: High Compression For Rich Extraction Fro…

200 篇论文

Recent years have witnessed a significant increase in the performance of Vision and Language tasks. Foundational Vision-Language Models (VLMs), such as CLIP, have been leveraged in multiple settings and demonstrated remarkable performance…

计算机视觉与模式识别 · 计算机科学 2024-03-04 Santiago Castro , Amir Ziai , Avneesh Saluja , Zhuoning Yuan , Rada Mihalcea

Transformer-based language models (LMs) are powerful and widely-applicable tools, but their usefulness is constrained by a finite context window and the expensive computational cost of processing long text documents. We propose to adapt…

计算与语言 · 计算机科学 2023-11-07 Alexis Chevalier , Alexander Wettig , Anirudh Ajith , Danqi Chen

The proliferation of deep learning-based machine vision applications has given rise to a new type of compression, so called video coding for machine (VCM). VCM differs from traditional video coding in that it is optimized for machine vision…

计算机视觉与模式识别 · 计算机科学 2023-08-09 Yeongwoong Kim , Hyewon Jeong , Janghyun Yu , Younhee Kim , Jooyoung Lee , Se Yoon Jeong , Hui Yong Kim

Today's strongest video-language models (VLMs) remain proprietary. The strongest open-weight models either rely on synthetic data from proprietary VLMs, effectively distilling from them, or do not disclose their training data or recipe. As…

The rapid advancement of Large Language Models (LLMs) has spurred significant progress in Large Speech-Language Models (LSLMs), enhancing their capabilities in both speech understanding and generation. While existing LSLMs often concentrate…

计算与语言 · 计算机科学 2025-11-03 Shoutao Guo , Shaolei Zhang , Qingkai Fang , Zhengrui Ma , Min Zhang , Yang Feng

Large Multimodal Models (LMMs) uniformly perceive video frames, creating computational inefficiency for videos with inherently varying temporal information density. This paper present \textbf{Quicksviewer}, an LMM with new perceiving…

计算机视觉与模式识别 · 计算机科学 2025-04-22 Ji Qi , Yuan Yao , Yushi Bai , Bin Xu , Juanzi Li , Zhiyuan Liu , Tat-Seng Chua

Large Language Models (LLMs) have demonstrated effectiveness not only in language tasks but also in video reasoning. This paper introduces a novel dataset, Tropes in Movies (TiM), designed as a testbed for exploring two critical yet…

计算机视觉与模式识别 · 计算机科学 2024-06-18 Hung-Ting Su , Chun-Tong Chao , Ya-Ching Hsu , Xudong Lin , Yulei Niu , Hung-Yi Lee , Winston H. Hsu

In the past year, video-based large language models (Video LLMs) have achieved impressive progress, particularly in their ability to process long videos through extremely extended context lengths. However, this comes at the cost of…

计算机视觉与模式识别 · 计算机科学 2026-05-04 Shangkun Sun , Ruyang Liu , Haoran Tang , Yixiao Ge , Haibo Lu , Wei Gao , Jiankun Yang , Chen Li

Large Language Models (LLMs) often experience performance degradation during long-running interactions due to increasing context length, memory saturation, and computational overhead. This paper presents an adaptive context compression…

计算机视觉与模式识别 · 计算机科学 2026-04-01 Payal Fofadiya , Sunil Tiwari

We propose an efficient framework to compress massive video-frame features before feeding them into large multimodal models, thereby mitigating the severe token explosion arising from hour-long videos. Our design leverages a bidirectional…

计算机视觉与模式识别 · 计算机科学 2026-02-10 Geewook Kim , Minjoon Seo

Vision-language models (VLMs) could power real-time assistants and autonomous agents, but they face a critical challenge: understanding near-infinite video streams without escalating latency and memory usage. Processing entire videos with…

计算机视觉与模式识别 · 计算机科学 2025-10-13 Ruyi Xu , Guangxuan Xiao , Yukang Chen , Liuning He , Kelly Peng , Yao Lu , Song Han

Transformer-based Large Language Models (LLMs) often impose limitations on the length of the text input to ensure the generation of fluent and relevant responses. This constraint restricts their applicability in scenarios involving long…

计算与语言 · 计算机科学 2023-12-18 Weizhi Fei , Xueyan Niu , Pingyi Zhou , Lu Hou , Bo Bai , Lei Deng , Wei Han

Driven by the wave of large language models, Video-Language Models (VLMs) have become a significant yet challenging technology to bridge the gap between videos and texts. Although previous VLM works have made significant progress, almost…

计算机视觉与模式识别 · 计算机科学 2026-05-28 Xiang Fang , Wanlong Fang , Changshuo Wang , Xiaoye Qu , Daizong Liu

Following the recent popularity of Large Language Models (LLMs), several attempts have been made to extend them to the visual domain. From having a visual assistant that could guide us through unfamiliar environments to generative models…

Traditional video compression technologies have been developed over decades in pursuit of higher coding efficiency. Efficient temporal information representation plays a key role in video coding. Thus, in this paper, we propose to exploit…

图像与视频处理 · 电气工程与系统科学 2019-12-16 Haojie Liu , Han shen , Lichao Huang , Ming Lu , Tong Chen , Zhan Ma

Enabling large language models (LLMs) to read videos is vital for multimodal LLMs. Existing works show promise on short videos whereas long video (longer than e.g.~1 minute) comprehension remains challenging. The major problem lies in the…

计算机视觉与模式识别 · 计算机科学 2024-02-20 Yu Wang , Zeyuan Zhang , Julian McAuley , Zexue He

Rapid advancements have been made in extending Large Language Models (LLMs) to Large Multi-modal Models (LMMs). However, extending input modality of LLMs to video data remains a challenging endeavor, especially for long videos. Due to…

计算机视觉与模式识别 · 计算机科学 2024-08-29 Jiajun Liu , Yibing Wang , Hanghang Ma , Xiaoping Wu , Xiaoqi Ma , Xiaoming Wei , Jianbin Jiao , Enhua Wu , Jie Hu

Long video understanding is still challenging for recent Large Video-Language Models (LVLMs) due to the conflict between long-form temporal understanding and detailed spatial perception. LVLMs with a uniform frame sampling mechanism, which…

计算机视觉与模式识别 · 计算机科学 2025-09-30 Shenghao Fu , Qize Yang , Yuan-Ming Li , Xihan Wei , Xiaohua Xie , Wei-Shi Zheng

Vision language models (VLMs) demonstrate impressive capabilities in visual question answering and image captioning, acting as a crucial link between visual and language models. However, existing open-source VLMs heavily rely on pretrained…

计算机视觉与模式识别 · 计算机科学 2024-07-24 Aristeidis Panos , Rahaf Aljundi , Daniel Olmeda Reino , Richard E Turner

Video-Language Models (VLMs), powered by the advancements in Large Language Models (LLMs), are charting new frontiers in video understanding. A pivotal challenge is the development of an efficient method to encapsulate video content into a…

计算机视觉与模式识别 · 计算机科学 2024-02-21 Jiaqi Xu , Cuiling Lan , Wenxuan Xie , Xuejin Chen , Yan Lu