中文
相关论文

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

200 篇论文

Video large language models have demonstrated remarkable capabilities in video understanding tasks. However, the redundancy of video tokens introduces significant computational overhead during inference, limiting their practical deployment.…

计算机视觉与模式识别 · 计算机科学 2026-03-03 Yinchao Ma , Qiang Zhou , Zhibin Wang , Xianing Chen , Hanqing Yang , Jun Song , Bo Zheng

Recent developments in Video Large Language Models (Video LLMs) have enabled models to process hour-long videos and exhibit exceptional performance. Nonetheless, the Key-Value (KV) cache expands linearly over time, leading to substantial…

计算机视觉与模式识别 · 计算机科学 2026-04-24 Zhenyu Ning , Guangda Liu , Qihao Jin , Chengwei Li , Wenchao Ding , Minyi Guo , Jieru Zhao

The rapid progress of large Vision-Language Models (VLMs) has enabled a wide range of applications, such as image understanding and Visual Question Answering (VQA). Query images are often uploaded to the cloud, where VLMs are typically…

图像与视频处理 · 电气工程与系统科学 2026-04-02 Bardia Azizian , Ivan V. Bajic

Masked Image Modeling (MIM) with Vector Quantization (VQ) has achieved great success in both self-supervised pre-training and image generation. However, most existing methods struggle to address the trade-off in shared latent space for…

计算机视觉与模式识别 · 计算机科学 2025-04-02 Siyuan Li , Luyuan Zhang , Zedong Wang , Juanxi Tian , Cheng Tan , Zicheng Liu , Chang Yu , Qingsong Xie , Haonan Lu , Haoqian Wang , Zhen Lei

Video large language models (Vid-LLMs) have shown strong capabilities in understanding video content. However, their reliance on dense video token representations introduces substantial memory and computational overhead in both prefilling…

计算机视觉与模式识别 · 计算机科学 2025-08-29 Yicheng Ji , Jun Zhang , Heming Xia , Jinpeng Chen , Lidan Shou , Gang Chen , Huan Li

Vision-language models (VLMs) have achieved impressive performance on multimodal reasoning tasks such as visual question answering, image captioning and so on, but their inference cost remains a significant challenge due to the large number…

计算机视觉与模式识别 · 计算机科学 2026-01-06 Weichen Zhang , Zhui Zhu , Ningbo Li , Shilong Tao , Kebin Liu , Yunhao Liu

Vision encoders serve as the cornerstone of multimodal understanding. Single-encoder architectures like CLIP exhibit inherent constraints in generalizing across diverse multimodal tasks, while recent multi-encoder fusion methods introduce…

计算机视觉与模式识别 · 计算机科学 2025-07-29 Yuchen Liu , Yaoming Wang , Bowen Shi , Xiaopeng Zhang , Wenrui Dai , Chenglin Li , Hongkai Xiong , Qi Tian

Text-to-video generation has trailed behind text-to-image generation in terms of quality and diversity, primarily due to the inherent complexities of spatio-temporal modeling and the limited availability of video-text datasets. Recent…

计算机视觉与模式识别 · 计算机科学 2024-10-04 Xiefan Guo , Jinlin Liu , Miaomiao Cui , Liefeng Bo , Di Huang

In content-based video retrieval (CBVR), dealing with large-scale collections, efficiency is as important as accuracy; thus, several video-level feature-based studies have actively been conducted. Nevertheless, owing to the severe…

计算机视觉与模式识别 · 计算机科学 2023-12-20 Won Jo , Geuntaek Lim , Gwangjin Lee , Hyunwoo Kim , Byungsoo Ko , Yukyung Choi

In this paper, we present VideoGen, a text-to-video generation approach, which can generate a high-definition video with high frame fidelity and strong temporal consistency using reference-guided latent diffusion. We leverage an…

计算机视觉与模式识别 · 计算机科学 2023-09-08 Xin Li , Wenqing Chu , Ye Wu , Weihang Yuan , Fanglong Liu , Qi Zhang , Fu Li , Haocheng Feng , Errui Ding , Jingdong Wang

Multimodal large language models (MLLMs) have made significant progress in visual-language reasoning, but their ability to efficiently handle long videos remains limited. Despite recent advances in long-context MLLMs, storing and attending…

计算机视觉与模式识别 · 计算机科学 2025-08-22 Yanlai Yang , Zhuokai Zhao , Satya Narayan Shukla , Aashu Singh , Shlok Kumar Mishra , Lizhu Zhang , Mengye Ren

Vision language models (VLMs) demonstrate strong capabilities in jointly processing visual and textual data. However, they often incur substantial computational overhead due to redundant visual information, particularly in long-form video…

机器学习 · 计算机科学 2025-04-25 Yudong Liu , Jingwei Sun , Yueqian Lin , Jingyang Zhang , Ming Yin , Qinsi Wang , Jianyi Zhang , Hai Li , Yiran Chen

Composed video retrieval (CoVR) searches for target videos using a reference video and a modification text, but existing methods are restricted to a single interaction round and cannot support the progressive nature of real-world visual…

信息检索 · 计算机科学 2026-05-12 Bingqing Zhang , Yi Zhang , Zhuo Cao , Yang Li , Xue Li , Jiajun Liu , Sen Wang

Visual token pruning is a promising approach for reducing the computational cost of vision-language models (VLMs), and existing methods often rely on early pruning decisions to improve efficiency. While effective on coarse-grained reasoning…

计算机视觉与模式识别 · 计算机科学 2026-02-04 Chen Qian , Xinran Yu , Danyang Li , Guoxuan Chi , Zheng Yang , Qiang Ma , Xin Miao

Existing super-resolution (SR) models primarily focus on restoring local texture details, often neglecting the global semantic information within the scene. This oversight can lead to the omission of crucial semantic details or the…

计算机视觉与模式识别 · 计算机科学 2023-12-22 Haoze Sun , Wenbo Li , Jianzhuang Liu , Haoyu Chen , Renjing Pei , Xueyi Zou , Youliang Yan , Yujiu Yang

The limited capacity for fine-grained visual perception presents a critical bottleneck for Vision-Language Models (VLMs) in real-world applications. Addressing this is challenging due to the scarcity of high-quality data and the limitations…

计算机视觉与模式识别 · 计算机科学 2025-10-29 Juntian Zhang , Song Jin , Chuanqi Cheng , Yuhan Liu , Yankai Lin , Xun Zhang , Yufei Zhang , Fei Jiang , Guojun Yin , Wei Lin , Rui Yan

The video grounding (VG) task aims to locate the queried action or event in an untrimmed video based on rich linguistic descriptions. Existing proposal-free methods are trapped in complex interaction between video and query, overemphasizing…

计算机视觉与模式识别 · 计算机科学 2023-08-14 Kun Li , Dan Guo , Meng Wang

In light of recent advances in multimodal Large Language Models (LLMs), there is increasing attention to scaling them from image-text data to more informative real-world videos. Compared to static images, video poses unique challenges for…

计算机视觉与模式识别 · 计算机科学 2024-06-04 Yang Jin , Zhicheng Sun , Kun Xu , Kun Xu , Liwei Chen , Hao Jiang , Quzhe Huang , Chengru Song , Yuliang Liu , Di Zhang , Yang Song , Kun Gai , Yadong Mu

Vision-Language Models (VLMs) have demonstrated strong performance on multimodal reasoning tasks, but their deployment remains challenging due to high inference latency and computational cost, particularly when processing high-resolution…

计算机视觉与模式识别 · 计算机科学 2025-12-25 Putu Indah Githa Cahyani , Komang David Dananjaya Suartana , Novanto Yudistira

This paper explores the possibility of learning custom tokens for representing new concepts in Vision-Language Models (VLMs). Our aim is to learn tokens that can be effective for both discriminative and generative tasks while composing well…

计算机视觉与模式识别 · 计算机科学 2025-02-18 Pramuditha Perera , Matthew Trager , Luca Zancato , Alessandro Achille , Stefano Soatto