中文
相关论文

相关论文: PREGEN: Uncovering Latent Thoughts in Composed Vid…

200 篇论文

The autonomous synthesis of deep research reports represents a critical frontier for Large Language Models (LLMs), demanding sophisticated information orchestration and non-linear narrative logic. Current approaches rely on rigid predefined…

多智能体系统 · 计算机科学 2026-04-22 Kuo Tian , Pengfei Sun , Zhen Wu , Junran Ding , Xinyu Dai

Visual reinforcement learning (RL) suffers from poor sample efficiency due to high-dimensional observations in complex tasks. While existing works have shown that vision-language models (VLMs) can assist RL, they often focus on knowledge…

计算机视觉与模式识别 · 计算机科学 2026-01-13 Canming Xia , Peixi Peng , Guang Tan , Zhan Su , Haoran Xu , Zhenxian Liu , Luntong Li

Selective prediction minimizes incorrect predictions from vision-language models (VLMs) by allowing them to abstain from answering when uncertain. However, when deploying a vision-language system with low tolerance for inaccurate…

In recent years, video compression techniques have been significantly challenged by the rapidly increased demands associated with high quality and immersive video content. Among various compression tools, post-processing can be applied on…

图像与视频处理 · 电气工程与系统科学 2021-01-21 Fan Zhang , Di Ma , Chen Feng , David R. Bull

There has been a growing trend in compressing and transmitting videos from terminals for machine vision tasks. Nevertheless, most video coding optimization method focus on minimizing distortion according to human perceptual metrics,…

多媒体 · 计算机科学 2025-12-18 Fei Zhao , Mengxi Guo , Shijie Zhao , Junlin Li , Li Zhang , Xiaodong Xie

Although CNN has reached satisfactory performance in image-related tasks, using CNN to process videos is much more challenging due to the enormous size of raw video streams. In this work, we propose to use motion vectors and residuals from…

图像与视频处理 · 电气工程与系统科学 2019-10-08 Haoyuan Cao , Shining Yu , Jiashi Feng

In this paper, we propose an efficient and high-performance method for partially relevant video retrieval, which aims to retrieve long videos that contain at least one moment relevant to the input text query. The challenge lies in encoding…

计算机视觉与模式识别 · 计算机科学 2024-03-13 Taichi Nishimura , Shota Nakada , Masayoshi Kondo

A remarkable ability of human beings resides in compositional reasoning, i.e., the capacity to make "infinite use of finite means". However, current large vision-language foundation models (VLMs) fall short of such compositional abilities…

计算机视觉与模式识别 · 计算机科学 2023-11-07 Junyan Li , Delin Chen , Yining Hong , Zhenfang Chen , Peihao Chen , Yikang Shen , Chuang Gan

Medical retrieval-augmented generation (RAG) systems typically operate on text chunks extracted from biomedical literature, discarding the rich visual content (tables, figures, structured layouts) of original document pages. We propose…

人工智能 · 计算机科学 2026-05-01 Xupeng Chen , Binbin Shi , Chenqian Le , Jiaqi Zhang , Kewen Wang , Ran Gong , Jinhan Zhang , Chihang Wang

Vision-Language Models often struggle with complex visual reasoning due to the visual information loss in textual CoT. Existing methods either add the cost of tool calls or rely on localized patch-based embeddings that are insufficient to…

计算与语言 · 计算机科学 2026-04-10 Mengdan Zhu , Senhao Cheng , Liang Zhao

Recent deep-learning-based video compression methods brought coding gains over conventional codecs such as AVC and HEVC. However, learning-based codecs generally require considerable computation time and model complexity. In this paper, we…

图像与视频处理 · 电气工程与系统科学 2023-03-22 Hochang Rhee , Seyun Kim , Nam Ik Cho

We introduce CogVLM, a powerful open-source visual language foundation model. Different from the popular shallow alignment method which maps image features into the input space of language model, CogVLM bridges the gap between the frozen…

计算机视觉与模式识别 · 计算机科学 2024-02-06 Weihan Wang , Qingsong Lv , Wenmeng Yu , Wenyi Hong , Ji Qi , Yan Wang , Junhui Ji , Zhuoyi Yang , Lei Zhao , Xixuan Song , Jiazheng Xu , Bin Xu , Juanzi Li , Yuxiao Dong , Ming Ding , Jie Tang

Interleaved image-text generation has emerged as a crucial multimodal task, aiming at creating sequences of interleaved visual and textual content given a query. Despite notable advancements in recent multimodal large language models…

计算机视觉与模式识别 · 计算机科学 2025-04-03 Wei Chen , Lin Li , Yongqi Yang , Bin Wen , Fan Yang , Tingting Gao , Yu Wu , Long Chen

In this paper, we introduce LightVLM, a simple but effective method that can be seamlessly deployed upon existing Vision-Language Models (VLMs) to greatly accelerate the inference process in a training-free manner. We divide the inference…

计算机视觉与模式识别 · 计算机科学 2025-09-03 Lianyu Hu , Fanhua Shang , Wei Feng , Liang Wan

Recent advancements in video understanding within visual large language models (VLLMs) have led to notable progress. However, the complexity of video data and contextual processing limitations still hinder long-video comprehension. A common…

计算机视觉与模式识别 · 计算机科学 2025-04-30 Yanan Guo , Wenhui Dong , Jun Song , Shiding Zhu , Xuan Zhang , Hanqing Yang , Yingbo Wang , Yang Du , Xianing Chen , Bo Zheng

Large Multimodal Models (LMMs) have shown significant visual reasoning capabilities by connecting a visual encoder and a large language model. LMMs typically take in a fixed and large amount of visual tokens, such as the penultimate layer…

计算机视觉与模式识别 · 计算机科学 2026-02-03 Yuzhang Shang , Mu Cai , Bingxin Xu , Yong Jae Lee , Yan Yan

Implicit Neural Networks (INRs) have emerged as powerful representations to encode all forms of data, including images, videos, audios, and scenes. With video, many INRs for video have been proposed for the compression task, and recent…

计算机视觉与模式识别 · 计算机科学 2024-08-06 Shishira R Maiya , Anubhav Gupta , Matthew Gwilliam , Max Ehrlich , Abhinav Shrivastava

Vision-language models (VLMs) have demonstrated impressive multimodal comprehension capabilities and are being deployed in an increasing number of online video understanding applications. While recent efforts extensively explore advancing…

分布式、并行与集群计算 · 计算机科学 2026-01-08 Shengyuan Ye , Bei Ouyang , Tianyi Qian , Liekang Zeng , Mu Yuan , Xiaowen Chu , Weijie Hong , Xu Chen

Recent progress in 3D reconstruction has enabled realistic 3D models from dense image captures, yet challenges persist with sparse views, often leading to artifacts in unseen areas. Recent works leverage Video Diffusion Models (VDMs) to…

计算机视觉与模式识别 · 计算机科学 2025-08-11 Wenbin Teng , Gonglin Chen , Haiwei Chen , Yajie Zhao

Vision-Language Models (VLMs) process thousands of visual tokens per image alongside comparatively few text tokens, yet existing compression methods treat both modalities uniformly. We observe that the two modalities have fundamentally…

机器学习 · 计算机科学 2026-05-29 Yilin Feng , Ahmed Burak Gulhan , Mahmut Taylan Kandemir