中文
相关论文

相关论文: Re-Prompting SAM 3 via Object Retrieval: 3rd of th…

200 篇论文

This report presents an overview of the 7th Large-scale Video Object Segmentation (LSVOS) Challenge held in conjunction with ICCV 2025. Besides the two traditional tracks of LSVOS that jointly target robustness in realistic video scenarios:…

Autonomous-driving perception systems require robust Multi-Object Tracking (MOT) to operate reliably in dynamic environments. MOT maintains consistent object identities across frames while preserving spatial accuracy. Recent foundation…

计算机视觉与模式识别 · 计算机科学 2026-03-03 Diogo Mendonça , Tiago Barros , Cristiano Premebida , Urbano J. Nunes

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

The problem of video object segmentation can become extremely challenging when multiple instances co-exist. While each instance may exhibit large scale and pose variations, the problem is compounded when instances occlude each other causing…

计算机视觉与模式识别 · 计算机科学 2018-03-15 Xiaoxiao Li , Chen Change Loy

We present Segment Anything Model (SAM) 3, a unified model that detects, segments, and tracks objects in images and videos based on concept prompts, which we define as either short noun phrases (e.g., "yellow school bus"), image exemplars,…

Referring Video Object Segmentation (RVOS) is a challenging task due to its requirement for temporal understanding. Due to the obstacle of computational complexity, many state-of-the-art models are trained on short time intervals. During…

计算机视觉与模式识别 · 计算机科学 2024-08-23 Tuyen Tran

Video Object Segmentation (VOS) aims to track and segment specific objects across entire video sequences, yet it remains highly challenging under complex real-world scenarios. The MOSEv1 and LVOS dataset, adopted in the MOSEv1 challenge on…

计算机视觉与模式识别 · 计算机科学 2025-10-01 Tingmin Li , Yixuan Li , Yang Yang

In this paper, we propose MOTRv2, a simple yet effective pipeline to bootstrap end-to-end multi-object tracking with a pretrained object detector. Existing end-to-end methods, MOTR and TrackFormer are inferior to their tracking-by-detection…

计算机视觉与模式识别 · 计算机科学 2023-04-20 Yuang Zhang , Tiancai Wang , Xiangyu Zhang

Motion Expression guided Video Segmentation is a challenging task that aims at segmenting objects in the video based on natural language expressions with motion descriptions. Unlike the previous referring video object segmentation (RVOS),…

计算机视觉与模式识别 · 计算机科学 2024-06-21 Bin Cao , Yisi Zhang , Xuanxu Lin , Xingjian He , Bo Zhao , Jing Liu

3D multiple object tracking (MOT) plays a crucial role in autonomous driving perception. Recent end-to-end query-based trackers simultaneously detect and track objects, which have shown promising potential for the 3D MOT task. However,…

计算机视觉与模式识别 · 计算机科学 2025-05-16 Tao Tang , Lijun Zhou , Pengkun Hao , Zihang He , Kalok Ho , Shuo Gu , Zhihui Hao , Haiyang Sun , Kun Zhan , Peng Jia , XianPeng Lang , Xiaodan Liang

Referring video object segmentation (RVOS) commonly grounds targets in videos based on static textual cues. MeViS benchmark extends this by incorporating motion-centric expressions (referring & reasoning motion expressions) and introducing…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Dengxian Gong , Quanzhu Niu , Shihao Chen , Yuanzheng Wu , Yikang Zhou , Tao Zhang , Haobo Yuan , Lu Qi , Shunping Ji

Multi-object tracking (MOT) is a fundamental task in computer vision that requires continuously tracking multiple targets while maintaining consistent identities across frames. However, most existing approaches primarily rely on…

计算机视觉与模式识别 · 计算机科学 2026-05-12 Yanchao Wang , Dawei Zhang , Chengzhuan Yang , Wei Liu , Minglu Li , Hua Wang , Zhonglong Zheng , Ming-Hsuan Yang

The referring video object segmentation task (RVOS) aims to segment object instances in a given video referred by a language expression in all video frames. Due to the requirement of understanding cross-modal semantics within individual…

计算机视觉与模式识别 · 计算机科学 2022-06-27 Leilei Cao , Zhuang Li , Bo Yan , Feng Zhang , Fengliang Qi , Yuchen Hu , Hongbin Wang

We introduce ReConvNet, a recurrent convolutional architecture for semi-supervised video object segmentation that is able to fast adapt its features to focus on any specific object of interest at inference time. Generalization to new…

计算机视觉与模式识别 · 计算机科学 2018-06-19 Francesco Lattari , Marco Ciccone , Matteo Matteucci , Jonathan Masci , Francesco Visin

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

Referring video object segmentation (RVOS) requires segmenting and tracking objects in videos conditioned on natural-language expressions, demanding fine-grained understanding of both appearance and motion. Building on Sa2VA, which couples…

计算机视觉与模式识别 · 计算机科学 2025-10-21 Quanzhu Niu , Dengxian Gong , Shihao Chen , Tao Zhang , Yikang Zhou , Haobo Yuan , Lu Qi , Xiangtai Li , Shunping Ji

Referential Video Object Segmentation (RVOS) aims to segment all objects in a video that match a given natural language description, bridging the gap between vision and language understanding. Recent work, such as Sa2VA, combines Large…

计算机视觉与模式识别 · 计算机科学 2025-09-22 Ran Hong , Feng Lu , Leilei Cao , An Yan , Youhai Jiang , Fengjie Zhu

Object tracking and 3D reconstruction are often performed together, with tracking used as input for reconstruction. However, the obtained reconstructions also provide useful information for improving tracking. We propose a novel method that…

计算机视觉与模式识别 · 计算机科学 2020-04-21 Jonathon Luiten , Tobias Fischer , Bastian Leibe

Event cameras are bio-inspired, motion-activated sensors that demonstrate substantial potential in handling challenging situations, such as motion blur and high-dynamic range. In this paper, we proposed EVI-SAM to tackle the problem of 6…

计算机视觉与模式识别 · 计算机科学 2024-05-24 Weipeng Guan , Peiyu Chen , Huibin Zhao , Yu Wang , Peng Lu

Interactive segmentation models such as the Segment Anything Model (SAM) have demonstrated remarkable generalization on natural images, but they perform suboptimally on remote sensing imagery (RSI) due to severe domain shifts and the…

计算机视觉与模式识别 · 计算机科学 2026-03-31 M. Naseer Subhani