中文
相关论文

相关论文: Video Fill In the Blank using LR/RL LSTMs with Spa…

200 篇论文

Understanding how the brain encodes visual information is a central challenge in neuroscience and machine learning. A promising approach is to reconstruct visual stimuli, essentially images, from functional Magnetic Resonance Imaging (fMRI)…

计算机视觉与模式识别 · 计算机科学 2026-05-15 Zheng Huang , Enpei Zhang , Weikang Qiu , Yinghao Cai , Carl Yang , Elynn Chen , Xiang Zhang , Rex Ying , Dawei Zhou , Yujun Yan

We introduce TemporalVLM, a video large language model (video LLM) for temporal reasoning and fine-grained understanding in long videos. Our approach includes a visual encoder for mapping a long-term video into features which are time-aware…

计算机视觉与模式识别 · 计算机科学 2026-04-21 Fawad Javed Fateh , Umer Ahmed , Hamza Khan , M. Zeeshan Zia , Quoc-Huy Tran

Accurate video moment retrieval (VMR) requires universal visual-textual correlations that can handle unknown vocabulary and unseen scenes. However, the learned correlations are likely either biased when derived from a limited amount of…

计算机视觉与模式识别 · 计算机科学 2023-09-06 Dezhao Luo , Jiabo Huang , Shaogang Gong , Hailin Jin , Yang Liu

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

Detecting video moments and highlights from natural-language queries have been unified by transformer-based methods. Other works use generative Multimodal LLM (MLLM) to predict moments and/or highlights as text timestamps, utilizing its…

计算机视觉与模式识别 · 计算机科学 2025-12-16 I Putu Andika Bagas Jiwanta , Ayu Purwarianti

Vision-language models (VLMs) are often deployed on text-only inputs, although they are trained with images. We find that removing the vision modality causes large drops in accuracy and severe miscalibration, and the model does not behave…

计算与语言 · 计算机科学 2026-05-14 Mingyeong Kim , Jungwon Choi , Chaeyun Jang , Juho Lee

Language models such as RNN, LSTM or other variants have been widely used as generative models in natural language processing. In last few years, taking source code as natural languages, parsing source code into a token sequence and using a…

软件工程 · 计算机科学 2019-10-28 Yixiao Yang

This paper studies the problem of temporal moment localization in a long untrimmed video using natural language as the query. Given an untrimmed video and a sentence as the query, the goal is to determine the starting, and the ending, of…

计算机视觉与模式识别 · 计算机科学 2020-03-13 Cristian Rodriguez-Opazo , Edison Marrese-Taylor , Fatemeh Sadat Saleh , Hongdong Li , Stephen Gould

Multi-modal Large language models (MLLMs) show remarkable ability in video understanding. Nevertheless, understanding long videos remains challenging as the models can only process a finite number of frames in a single inference,…

计算机视觉与模式识别 · 计算机科学 2025-03-27 Yucheng Suo , Fan Ma , Linchao Zhu , Tianyi Wang , Fengyun Rao , Yi Yang

Current video-language models struggle with long-video understanding due to limited context lengths and reliance on sparse frame subsampling, often leading to information loss. This paper introduces $\infty$-Video, which can process…

计算机视觉与模式识别 · 计算机科学 2025-05-20 Saul Santos , António Farinhas , Daniel C. McNamee , André F. T. Martins

Multimodal Large Language Models (MLLMs) have shown strong performance in video understanding tasks. However, they continue to struggle with long-form videos because of an inefficient perception of temporal intervals. Unlike humans, who can…

计算机视觉与模式识别 · 计算机科学 2025-07-08 Chenglin Li , Qianglong Chen , fengtao , Yin Zhang

Recurrent Neural Networks (RNNs) are widely used in the field of natural language processing (NLP), ranging from text categorization to question answering and machine translation. However, RNNs generally read the whole text from beginning…

计算与语言 · 计算机科学 2019-05-29 Ting Huang , Gehui Shen , Zhi-Hong Deng

Temporal sentence grounding in videos (TSGV), \aka natural language video localization (NLVL) or video moment retrieval (VMR), aims to retrieve a temporal moment that semantically corresponds to a language query from an untrimmed video.…

计算机视觉与模式识别 · 计算机科学 2023-04-26 Hao Zhang , Aixin Sun , Wei Jing , Joey Tianyi Zhou

Video text-based visual question answering (Video TextVQA) task aims to answer questions about videos by leveraging the visual text appearing within the videos. This task poses significant challenges, requiring models to accurately perceive…

计算机视觉与模式识别 · 计算机科学 2025-11-26 Haibin He , Qihuang Zhong , Juhua Liu , Bo Du , Peng Wang , Jing Zhang

Large Multimodal Models (LMMs) have demonstrated impressive performance in short video understanding tasks but face great challenges when applied to long video understanding. In contrast, Large Language Models (LLMs) exhibit outstanding…

计算机视觉与模式识别 · 计算机科学 2024-10-03 Hongchen Wei , Zhenzhong Chen

To address computational and memory limitations of Large Multimodal Models in the Video Question-Answering task, several recent methods extract textual representations per frame (e.g., by captioning) and feed them to a Large Language Model…

计算机视觉与模式识别 · 计算机科学 2025-04-08 Andreas Goulas , Vasileios Mezaris , Ioannis Patras

In this paper we address the following problem in web document and information retrieval (IR): How can we use long-term context information to gain better IR performance? Unlike common IR methods that use bag of words representation for…

信息检索 · 计算机科学 2015-03-02 H. Palangi , L. Deng , Y. Shen , J. Gao , X. He , J. Chen , X. Song , R. Ward

Recent progress has been made in using attention based encoder-decoder framework for video captioning. However, most existing decoders apply the attention mechanism to every generated word including both visual words (e.g., "gun" and…

计算机视觉与模式识别 · 计算机科学 2017-06-06 Jingkuan Song , Zhao Guo , Lianli Gao , Wu Liu , Dongxiang Zhang , Heng Tao Shen

Video Large Language Models (VideoLLMs) are increasingly deployed on numerous critical applications, where users rely on auto-generated summaries while casually skimming the video stream. We show that this interaction hides a critical…

多媒体 · 计算机科学 2025-11-18 Yuxin Cao , Wei Song , Derui Wang , Jingling Xue , Jin Song Dong

Multimodal large language models (MLLMs) demonstrate exceptional performance in vision-language tasks, yet their processing of long videos is constrained by input context length and high computational costs. Sparse frame sampling thus…

计算机视觉与模式识别 · 计算机科学 2026-04-13 Jianxiang He , Meisheng Hong , Jungang Li , Weiyu Guo , Xuming Hu , Hui Xiong