中文
相关论文

相关论文: Token Merging via Spatiotemporal Information Minin…

200 篇论文

Robotic motor control necessitates the ability to predict the dynamics of environments and interaction objects. However, advanced self-supervised pre-trained visual representations in robotic motor control, leveraging large-scale egocentric…

机器人学 · 计算机科学 2024-11-25 Jiange Yang , Bei Liu , Jianlong Fu , Bocheng Pan , Gangshan Wu , Limin Wang

Video Large Language Models (VLLMs) excel in video understanding, but their excessive visual tokens pose a significant computational challenge for real-world applications. Current methods aim to enhance inference efficiency by visual token…

计算机视觉与模式识别 · 计算机科学 2025-08-29 Junpeng Ma , Qizhe Zhang , Ming Lu , Zhibin Wang , Qiang Zhou , Jun Song , Shanghang Zhang

Semantic video segmentation is a key challenge for various applications. This paper presents a new model named Noisy-LSTM, which is trainable in an end-to-end manner, with convolutional LSTMs (ConvLSTMs) to leverage the temporal coherency…

计算机视觉与模式识别 · 计算机科学 2020-10-20 Bowen Wang , Liangzhi Li , Yuta Nakashima , Ryo Kawasaki , Hajime Nagahara , Yasushi Yagi

Pre-trained on tremendous image-text pairs, vision-language models like CLIP have demonstrated promising zero-shot generalization across numerous image-based tasks. However, extending these capabilities to video tasks remains challenging…

计算机视觉与模式识别 · 计算机科学 2025-03-26 Zichen Liu , Kunlun Xu , Bing Su , Xu Zou , Yuxin Peng , Jiahuan Zhou

Surgical video segmentation is a critical task in computer-assisted surgery and is vital for enhancing surgical quality and patient outcomes. Recently, the Segment Anything Model 2 (SAM2) framework has shown superior advancements in image…

计算机视觉与模式识别 · 计算机科学 2025-03-12 Haofeng Liu , Erli Zhang , Junde Wu , Mingxuan Hong , Yueming Jin

Effective modeling of complex spatiotemporal dependencies in long-form videos remains an open problem. The recently proposed Structured State-Space Sequence (S4) model with its linear complexity offers a promising direction in this space.…

计算机视觉与模式识别 · 计算机科学 2023-03-28 Jue Wang , Wentao Zhu , Pichao Wang , Xiang Yu , Linda Liu , Mohamed Omar , Raffay Hamid

Learning descriptive spatio-temporal object models from data is paramount for the task of semi-supervised video object segmentation. Most existing approaches mainly rely on models that estimate the segmentation mask based on a reference…

计算机视觉与模式识别 · 计算机科学 2019-03-29 Sergi Caelles , Albert Pumarola , Francesc Moreno-Noguer , Alberto Sanfeliu , Luc Van Gool

The exponential growth of Large Multimodal Models (LMMs) has driven advancements in cross-modal reasoning but at significant computational costs. In this work, we focus on visual language models. We highlight the redundancy and inefficiency…

计算机视觉与模式识别 · 计算机科学 2025-04-28 Yasmine Omri , Parth Shroff , Thierry Tambe

Recently, learned video compression has achieved exciting performance. Following the traditional hybrid prediction coding framework, most learned methods generally adopt the motion estimation motion compensation (MEMC) method to remove…

图像与视频处理 · 电气工程与系统科学 2023-10-20 Yiming Wang , Qian Huang , Bin Tang , Huashan Sun , Xing Li

Real-time video analysis remains a challenging problem in computer vision, requiring efficient processing of both spatial and temporal information while maintaining computational efficiency. Existing approaches often struggle to balance…

计算机视觉与模式识别 · 计算机科学 2025-07-31 Shahla John

Remote sensing spatiotemporal fusion (STF) addresses the fundamental trade-off between temporal and spatial resolution by combining high temporal-low spatial and high spatial-low temporal imagery. This paper presents the first comprehensive…

计算机视觉与模式识别 · 计算机科学 2025-07-14 Enzhe Sun , Yongchuan Cui , Peng Liu , Jining Yan

Stable diffusion is an outstanding image generation model for text-to-image, but its time-consuming generation process remains a challenge due to the quadratic complexity of attention operations. Recent token merging methods improve…

计算机视觉与模式识别 · 计算机科学 2025-07-18 Min-Jeong Lee , Hee-Dong Kim , Seong-Whan Lee

Existing semi-supervised video object segmentation methods either focus on temporal feature matching or spatial-temporal feature modeling. However, they do not address the issues of sufficient target interaction and efficient parallel…

计算机视觉与模式识别 · 计算机科学 2024-04-10 Deshui Miao , Xin Li , Zhenyu He , Huchuan Lu , Ming-Hsuan Yang

Traffic prediction, an essential component for intelligent transportation systems, endeavours to use historical data to foresee future traffic features at specific locations. Although existing traffic prediction models often emphasize…

机器学习 · 计算机科学 2024-07-09 Chenxi Liu , Sun Yang , Qianxiong Xu , Zhishuai Li , Cheng Long , Ziyue Li , Rui Zhao

The increasing ubiquity of video content and the corresponding demand for efficient access to meaningful information have elevated video summarization and video highlights as a vital research area. However, many state-of-the-art methods…

计算机视觉与模式识别 · 计算机科学 2026-05-05 Pritam Mishra , Coloma Ballester , Dimosthenis Karatzas

State Space Models (SSMs) have the advantage of keeping linear computational complexity compared to attention modules in transformers, and have been applied to vision tasks as a new type of powerful vision foundation model. Inspired by the…

计算机视觉与模式识别 · 计算机科学 2024-09-30 Zheng Zhan , Zhenglun Kong , Yifan Gong , Yushu Wu , Zichong Meng , Hangyu Zheng , Xuan Shen , Stratis Ioannidis , Wei Niu , Pu Zhao , Yanzhi Wang

While Large Language Models (LLMs) dominate tasks like natural language processing and computer vision, harnessing their power for spatial-temporal forecasting remains challenging. The disparity between sequential text and complex…

机器学习 · 计算机科学 2024-05-20 Lei Liu , Shuo Yu , Runze Wang , Zhenxun Ma , Yanming Shen

Within the scope of this contribution we propose a novel efficient spatio-temporal prediction algorithm for video coding. The algorithm operates in two stages. First, motion compensation is performed on the block to be predicted in order to…

图像与视频处理 · 电气工程与系统科学 2022-07-21 Jürgen Seiler , Haricharan Lakshman , André Kaup

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

Dynamic magnetic resonance imaging (MRI) plays an indispensable role in cardiac diagnosis. To enable fast imaging, the k-space data can be undersampled but the image reconstruction poses a great challenge of high-dimensional processing.…

图像与视频处理 · 电气工程与系统科学 2024-10-03 Zi Wang , Min Xiao , Yirong Zhou , Chengyan Wang , Naiming Wu , Yi Li , Yiwen Gong , Shufu Chang , Yinyin Chen , Liuhong Zhu , Jianjun Zhou , Congbo Cai , He Wang , Di Guo , Guang Yang , Xiaobo Qu