中文
相关论文

相关论文: CSS-Segment: 2nd Place Report of LSVOS Challenge V…

200 篇论文

This technical report describes our 2nd-place solution for the ECCV 2022 YouTube-VIS Long Video Challenge. We adopt the previously proposed online video instance segmentation method IDOL for this challenge. In addition, we use pseudo labels…

计算机视觉与模式识别 · 计算机科学 2022-11-21 Junfeng Wu , Yi Jiang , Qihao Liu , Xiang Bai , Song Bai

Video object segmentation (VOS) is a challenging task with wide applications such as video editing and autonomous driving. While Cutie provides strong query-based segmentation and SAM2 offers enriched representations via a pretrained ViT…

计算机视觉与模式识别 · 计算机科学 2025-09-22 Chang Soo Lim , Joonyoung Moon , Donghyeon Cho

Video Panoptic Segmentation (VPS) is a challenging task that is extends from image panoptic segmentation.VPS aims to simultaneously classify, track, segment all objects in a video, including both things and stuff. Due to its wide…

计算机视觉与模式识别 · 计算机科学 2024-06-04 Biao Wu , Diankai Zhang , Si Gao , Chengjian Zheng , Shaoli Liu , Ning Wang

Tracking and segmenting multiple similar objects with distinct or complex parts in long-term videos is particularly challenging due to the ambiguity in identifying target components and the confusion caused by occlusion, background clutter,…

计算机视觉与模式识别 · 计算机科学 2025-04-08 Xin Li , Deshui Miao , Zhenyu He , Yaowei Wang , Huchuan Lu , Ming-Hsuan Yang

Online video object segmentation is a challenging task as it entails to process the image sequence timely and accurately. To segment a target object through the video, numerous CNN-based methods have been developed by heavily finetuning on…

计算机视觉与模式识别 · 计算机科学 2018-06-07 Jingchun Cheng , Yi-Hsuan Tsai , Wei-Chih Hung , Shengjin Wang , Ming-Hsuan Yang

Audio-based video object segmentation aims to locate and segment objects in videos conditioned on audio cues, requiring precise understanding of both appearance and motion. Recent audio-driven video segmentation methods extend MLLMs by…

计算机视觉与模式识别 · 计算机科学 2026-04-28 Zhiyu Wang , Xudong Kang , Shutao Li

Instance segmentation in videos, which aims to segment and track multiple objects in video frames, has garnered a flurry of research attention in recent years. In this paper, we present a novel weakly supervised framework with…

计算机视觉与模式识别 · 计算机科学 2022-12-16 Liqi Yan , Qifan Wang , Siqi Ma , Jingang Wang , Changbin Yu

Video object segmentation (VOS) describes the task of segmenting a set of objects in each frame of a video. In the semi-supervised setting, the first mask of each object is provided at test time. Following the one-shot principle,…

计算机视觉与模式识别 · 计算机科学 2020-12-04 Tim Meinhardt , Laura Leal-Taixe

Segmentation of video objects in complex scenarios is highly challenging, and the MOSE dataset has significantly contributed to the development of this field. This technical report details the STSeg solution proposed by the "imaplus"…

计算机视觉与模式识别 · 计算机科学 2025-04-14 Kehuan Song , Xinglin Xie , Kexin Zhang , Licheng Jiao , Lingling Li , Shuyuan Yang

As a milestone for video object segmentation, one-shot video object segmentation (OSVOS) has achieved a large margin compared to the conventional optical-flow based methods regarding to the segmentation accuracy. Its excellent performance…

计算机视觉与模式识别 · 计算机科学 2019-08-21 Yu Liu , Yutong Dai , Anh-Dzung Doan , Lingqiao Liu , Ian Reid

Learning long-term spatial-temporal features are critical for many video analysis tasks. However, existing video segmentation methods predominantly rely on static image segmentation techniques, and methods capturing temporal dependency for…

计算机视觉与模式识别 · 计算机科学 2018-09-05 Ning Xu , Linjie Yang , Yuchen Fan , Jianchao Yang , Dingcheng Yue , Yuchen Liang , Brian Price , Scott Cohen , Thomas Huang

We segment moving objects in videos by ranking spatio-temporal segment proposals according to "moving objectness": how likely they are to contain a moving object. In each video frame, we compute segment proposals using multiple…

计算机视觉与模式识别 · 计算机科学 2015-05-11 Katerina Fragkiadaki , Pablo Arbelaez , Panna Felsen , Jitendra Malik

Significant progress has been made in Video Object Segmentation (VOS), the video object tracking task in its finest level. While the VOS task can be naturally decoupled into image semantic segmentation and video object tracking,…

计算机视觉与模式识别 · 计算机科学 2020-07-14 Xuhua Huang , Jiarui Xu , Yu-Wing Tai , Chi-Keung Tang

We propose a light-weight variational framework for online tracking of object segmentations in videos based on optical flow and image boundaries. While high-end computer vision methods on this task rely on sequence specific training of…

计算机视觉与模式识别 · 计算机科学 2020-08-17 Amirhossein Kardoost , Sabine Müller , Joachim Weickert , Margret Keuper

Referring Video Object Segmentation (RVOS) aims to segment target objects throughout a video based on a text description. This task has attracted increasing attention in the field of computer vision due to its promising applications in…

计算机视觉与模式识别 · 计算机科学 2025-05-30 Tianming Liang , Haichao Jiang , Wei-Shi Zheng , Jian-Fang Hu

Video segmentation requires consistently segmenting and tracking objects over time. Due to the quadratic dependency on input size, directly applying self-attention to video segmentation with high-resolution input features poses significant…

计算机视觉与模式识别 · 计算机科学 2024-06-13 Ju He , Qihang Yu , Inkyu Shin , Xueqing Deng , Alan Yuille , Xiaohui Shen , Liang-Chieh Chen

In this report, we describe our approach to egocentric video object segmentation. Our method combines large-scale visual pretraining from SAM2 with depth-based geometric cues to handle complex scenes and long-term tracking. By integrating…

计算机视觉与模式识别 · 计算机科学 2025-06-10 Mingqi Gao , Haoran Duan , Tianlu Zhang , Jungong Han

In this work we propose a capsule-based approach for semi-supervised video object segmentation. Current video object segmentation methods are frame-based and often require optical flow to capture temporal consistency across frames which can…

计算机视觉与模式识别 · 计算机科学 2019-10-02 Kevin Duarte , Yogesh S Rawat , Mubarak Shah

In this paper, we present a unified, end-to-end trainable spatiotemporal CNN model for VOS, which consists of two branches, i.e., the temporal coherence branch and the spatial segmentation branch. Specifically, the temporal coherence branch…

计算机视觉与模式识别 · 计算机科学 2019-04-05 Kai Xu , Longyin Wen , Guorong Li , Liefeng Bo , Qingming Huang

Video object segmentation aims at accurately segmenting the target object regions across consecutive frames. It is technically challenging for coping with complicated factors (e.g., shape deformations, occlusion and out of the lens). Recent…

计算机视觉与模式识别 · 计算机科学 2019-07-03 Peng Sun , Peiwen Lin , Guangliang Cheng , Jianping Shi , Jiawan Zhang , Xi Li