中文
相关论文

相关论文: Token Merging via Spatiotemporal Information Minin…

200 篇论文

Analyzing surgical workflow is crucial for surgical assistance robots to understand surgeries. With the understanding of the complete surgical workflow, the robots are able to assist the surgeons in intra-operative events, such as by giving…

计算机视觉与模式识别 · 计算机科学 2021-05-12 Yutong Ban , Guy Rosman , Thomas Ward , Daniel Hashimoto , Taisei Kondo , Hidekazu Iwaki , Ozanan Meireles , Daniela Rus

The increasing availability of large clinical datasets collected from patients can enable new avenues for computational characterization of complex diseases using different analytic algorithms. One of the promising new methods for…

机器学习 · 计算机科学 2023-09-13 Jonas Hügel , Ulrich Sax , Shawn N. Murphy , Hossein Estiri

Recent token reduction methods for Vision Transformers (ViTs) incorporate token merging, which measures the similarities between token embeddings and combines the most similar pairs. However, their merging policies are directly dependent on…

计算机视觉与模式识别 · 计算机科学 2024-12-17 Dong Hoon Lee , Seunghoon Hong

Video large language models (VideoLLMs) show strong capability in video understanding, yet long-context inference is still dominated by massive redundant visual tokens in the prefill stage. We revisit token compression for VideoLLMs under a…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Xinying Lin , Xuyang Liu , Yiyu Wang , Teng Ma , Wenqi Ren

Large Vision-Language Models (VLMs) have been extended to understand both images and videos. Visual token compression is leveraged to reduce the considerable token length of visual inputs. To meet the needs of different tasks, existing…

计算机视觉与模式识别 · 计算机科学 2024-12-13 Chenyu Yang , Xuan Dong , Xizhou Zhu , Weijie Su , Jiahao Wang , Hao Tian , Zhe Chen , Wenhai Wang , Lewei Lu , Jifeng Dai

Video-language alignment is a crucial multi-modal task that benefits various downstream applications, e.g., video-text retrieval and video question answering. Existing methods either utilize multi-modal information in video-text pairs or…

计算机视觉与模式识别 · 计算机科学 2024-07-25 Shi-Xue Zhang , Hongfa Wang , Xiaobin Zhu , Weibo Gu , Tianjin Zhang , Chun Yang , Wei Liu , Xu-Cheng Yin

Surgical procedures are inherently complex and risky, requiring extensive expertise and constant focus to navigate evolving intraoperative scenes. Computer-assisted systems such as surgical visual question answering (VQA) offer promises for…

计算机视觉与模式识别 · 计算机科学 2026-05-05 Shi Li , Vinkle Srivastav , Nicolas Chanel , Saurav Sharma , Nabani Banik , Lorenzo Arboit , Kun Yuan , Pietro Mascagni , Nicolas Padoy

Although Video Large Language Models (VLLMs) have shown remarkable capabilities in video understanding, they are required to process high volumes of visual tokens, causing significant computational inefficiency. Existing VLLMs acceleration…

计算机视觉与模式识别 · 计算机科学 2026-02-10 Ziyang Fan , Keyu Chen , Ruilong Xing , Yulin Li , Li Jiang , Zhuotao Tian

Video Foundation Models (VFMs) exhibit remarkable visual generation performance, but struggle in compositional scenarios (e.g., motion, numeracy, and spatial relation). In this work, we introduce Test-Time Optimization and Memorization…

计算机视觉与模式识别 · 计算机科学 2026-03-03 Leigang Qu , Ziyang Wang , Na Zheng , Wenjie Wang , Liqiang Nie , Tat-Seng Chua

Although Vision Transformers (ViTs) have become the standard architecture in computer vision, their massive sizes lead to significant computational overhead. Token compression techniques have attracted considerable attention to address this…

计算机视觉与模式识别 · 计算机科学 2026-04-02 Jaeyeon Lee , Dong-Wan Choi

Recognizing various surgical tools, actions and phases from surgery videos is an important problem in computer vision with exciting clinical applications. Existing deep-learning-based methods for this problem either process each surgical…

计算机视觉与模式识别 · 计算机科学 2024-04-09 Haifeng Wang , Hao Xu , Jun Wang , Jian Zhou , Ke Deng

Automatic surgical scene segmentation is fundamental for facilitating cognitive intelligence in the modern operating theatre. Previous works rely on conventional aggregation modules (e.g., dilated convolution, convolutional LSTM), which…

计算机视觉与模式识别 · 计算机科学 2022-06-27 Yueming Jin , Yang Yu , Cheng Chen , Zixu Zhao , Pheng-Ann Heng , Danail Stoyanov

The performance of video saliency estimation techniques has achieved significant advances along with the rapid development of Convolutional Neural Networks (CNNs). However, devices like cameras and drones may have limited computational…

计算机视觉与模式识别 · 计算机科学 2020-01-08 Jia Li , Kui Fu , Shengwei Zhao , Shiming Ge

Reliable monitoring of surgical instrument exchanges is essential for maintaining procedural efficiency and patient safety in the operating room. Automatic detection of instrument handovers in intraoperative video remains challenging due to…

Reasoning Video Object Segmentation (ReasonVOS) is a challenging task that requires stable object segmentation across video sequences using implicit and complex textual inputs. Previous methods fine-tune Multimodal Large Language Models…

计算机视觉与模式识别 · 计算机科学 2026-03-03 Zhengtong Zhu , Jiaqing Fan , Zhixuan Liu , Fanzhang Li

Recently, large-scale pre-training methods like CLIP have made great progress in multi-modal research such as text-video retrieval. In CLIP, transformers are vital for modeling complex multi-modal relations. However, in the vision…

计算机视觉与模式识别 · 计算机科学 2022-05-03 Shuai Zhao , Linchao Zhu , Xiaohan Wang , Yi Yang

In this report, our approach to tackling the task of ActivityNet 2018 Kinetics-600 challenge is described in detail. Though spatial-temporal modelling methods, which adopt either such end-to-end framework as I3D \cite{i3d} or two-stage…

计算机视觉与模式识别 · 计算机科学 2018-06-28 Dongliang He , Fu Li , Qijie Zhao , Xiang Long , Yi Fu , Shilei Wen

Temporal human action detection aims to identify and localize action segments within untrimmed videos, serving as a pivotal task in video understanding. Despite the progress achieved by prior architectures like CNN and Transformer models,…

计算机视觉与模式识别 · 计算机科学 2026-04-13 Yicheng Qiu , Keiji Yanai

The past year has witnessed a rapid development of masked image modeling (MIM). MIM is mostly built upon the vision transformers, which suggests that self-supervised visual representations can be done by masking input image parts while…

计算机视觉与模式识别 · 计算机科学 2022-03-29 Yunjie Tian , Lingxi Xie , Jiemin Fang , Mengnan Shi , Junran Peng , Xiaopeng Zhang , Jianbin Jiao , Qi Tian , Qixiang Ye

Despite recent advances in subquadratic attention mechanisms or state-space models, processing long token sequences still imposes significant computational requirements. Token merging has emerged as a solution to increase computational…

机器学习 · 计算机科学 2025-08-06 Leon Götz , Marcel Kollovieh , Stephan Günnemann , Leo Schwinn