中文
相关论文

相关论文: Token Merging via Spatiotemporal Information Minin…

200 篇论文

Existing multi-modal fusion methods typically apply static frame-based image fusion techniques directly to video fusion tasks, neglecting inherent temporal dependencies and leading to inconsistent results across frames. To address this…

计算机视觉与模式识别 · 计算机科学 2025-08-26 Meiqi Gong , Hao Zhang , Xunpeng Yi , Linfeng Tang , Jiayi Ma

Diverse actions give rise to rich audio-visual signals in long videos. Recent works showcase that the two modalities of audio and video exhibit different temporal extents of events and distinct labels. We address the interplay between the…

计算机视觉与模式识别 · 计算机科学 2024-04-10 Jacob Chalk , Jaesung Huh , Evangelos Kazakos , Andrew Zisserman , Dima Damen

This paper presents VideoStreaming, an advanced vision-language large model (VLLM) for video understanding, that capably understands arbitrary-length video with a constant number of video tokens streamingly encoded and adaptively selected.…

计算机视觉与模式识别 · 计算机科学 2024-05-28 Rui Qian , Xiaoyi Dong , Pan Zhang , Yuhang Zang , Shuangrui Ding , Dahua Lin , Jiaqi Wang

Multimodal image fusion and semantic segmentation are critical for autonomous driving. Despite advancements, current models often struggle with segmenting densely packed elements due to a lack of comprehensive fusion features for guidance…

计算机视觉与模式识别 · 计算机科学 2025-06-25 Daixun Li , Weiying Xie , Mingxiang Cao , Yunke Wang , Yusi Zhang , Leyuan Fang , Yunsong Li , Chang Xu

Vision-language models (VLMs) excel at image understanding tasks, but the large number of visual tokens imposes significant computational costs, hindering deployment on mobile devices. Many pruning methods rely solely on token importance…

计算机视觉与模式识别 · 计算机科学 2026-02-27 Zhenkai Wu , Xiaowen Ma , Zhenliang Ni , Dengming Zhang , Han Shu , Xin Jiang , Xinghao Chen

This work presents Adaptive Local-then-Global Merging (ALGM), a token reduction method for semantic segmentation networks that use plain Vision Transformers. ALGM merges tokens in two stages: (1) In the first network layer, it merges…

计算机视觉与模式识别 · 计算机科学 2024-06-17 Narges Norouzi , Svetlana Orlova , Daan de Geus , Gijs Dubbelman

This paper proposes a spatiotemporal (ST) fusion framework robust against diverse noise for satellite images, named Temporally-Similar Structure-Aware ST fusion (TSSTF). ST fusion is a promising approach to address the trade-off between the…

信号处理 · 电气工程与系统科学 2026-01-30 Ryosuke Isono , Shunsuke Ono

In this contribution, a novel spatio-temporal prediction algorithm for video coding is introduced. This algorithm exploits temporal as well as spatial redundancies for effectively predicting the signal to be encoded. To achieve this, the…

图像与视频处理 · 电气工程与系统科学 2022-07-05 Jürgen Seiler , André Kaup

Spatio-temporal feature learning is of central importance for action recognition in videos. Existing deep neural network models either learn spatial and temporal features independently (C2D) or jointly with unconstrained parameters (C3D).…

计算机视觉与模式识别 · 计算机科学 2019-03-05 Chao Li , Qiaoyong Zhong , Di Xie , Shiliang Pu

Multimodal large language models (MLLMs) suffer from high computational costs due to excessive visual tokens, particularly in high-resolution and video-based scenarios. Existing token reduction methods typically focus on isolated pipeline…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Hanxun Yu , Wentong Li , Xuan Qu , Song Wang , Junbo Chen , Jianke Zhu

Modern one-stage video instance segmentation networks suffer from two limitations. First, convolutional features are neither aligned with anchor boxes nor with ground-truth bounding boxes, reducing the mask sensitivity to spatial location.…

计算机视觉与模式识别 · 计算机科学 2021-04-13 Minghan Li , Shuai Li , Lida Li , Lei Zhang

Utilizing transformer architectures for semantic segmentation of high-resolution images is hindered by the attention's quadratic computational complexity in the number of tokens. A solution to this challenge involves decreasing the number…

计算机视觉与模式识别 · 计算机科学 2024-05-24 Daniel Kienzle , Marco Kantonis , Robin Schön , Rainer Lienhart

Recently, Vision Large Language Models (VLLMs) integrated with vision encoders have shown promising performance in vision understanding. The key of VLLMs is to encode visual content into sequences of visual tokens, enabling VLLMs to…

计算机视觉与模式识别 · 计算机科学 2025-08-12 Zhuqiang Lu , Zhenfei Yin , Mengwei He , Zhihui Wang , Zicheng Liu , Zhiyong Wang , Kun Hu

In this dissertation, I present my work towards exploring temporal information for better video understanding. Specifically, I have worked on two problems: action recognition and semantic segmentation. For action recognition, I have…

计算机视觉与模式识别 · 计算机科学 2019-05-28 Yi Zhu

Promptable video object segmentation and tracking (VOST) has seen significant advances with the emergence of foundation models like Segment Anything Model 2 (SAM2); however, their application in surgical video analysis remains challenging…

计算机视觉与模式识别 · 计算机科学 2025-08-11 Guoping Xu , Hua-Chieh Shao , You Zhang

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

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

This paper addresses the task of segmenting class-agnostic objects in semi-supervised setting. Although previous detection based methods achieve relatively good performance, these approaches extract the best proposal by a greedy strategy,…

计算机视觉与模式识别 · 计算机科学 2020-12-11 Daizong Liu , Shuangjie Xu , Xiao-Yang Liu , Zichuan Xu , Wei Wei , Pan Zhou

While recent large-scale video-language pre-training made great progress in video question answering, the design of spatial modeling of video-language models is less fine-grained than that of image-language models; existing practices of…

计算机视觉与模式识别 · 计算机科学 2022-10-11 Hsin-Ying Lee , Hung-Ting Su , Bing-Chen Tsai , Tsung-Han Wu , Jia-Fong Yeh , Winston H. Hsu

Visual-spatial understanding, the ability to infer object relationships and layouts from visual input, is fundamental to downstream tasks such as robotic navigation and embodied interaction. However, existing methods face spatial…

计算机视觉与模式识别 · 计算机科学 2025-09-22 Haoyu Zhang , Meng Liu , Zaijing Li , Haokun Wen , Weili Guan , Yaowei Wang , Liqiang Nie
‹ 上一页 1 8 9 10 下一页 ›