paper-with-me

홈 › Papers

Fast Video Object Segmentation With Temporal Aggregation Network and Dynamic Template Matching

2020-07-11 · CVPR 2020 6 · Xuhua Huang, Jiarui Xu, Yu-Wing Tai, Chi-Keung Tang

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, significantly much more research effort has been made in segmentation than tracking. In this paper, we introduce "tracking-by-detection" into VOS which can coherently integrate segmentation into tracking, by proposing a new temporal aggregation network and a novel dynamic time-evolving template matching mechanism to achieve significantly improved performance. Notably, our method is entirely online and thus suitable for one-shot learning, and our end-to-end trainable model allows multiple object segmentation in one forward pass. We achieve new state-of-the-art performance on the DAVIS benchmark without complicated bells and whistles in both speed and accuracy, with a speed of 0.14 second per frame and J&F measure of 75.9% respectively.

📄 PDF Abstract BibTeX arXiv:2007.05687

Code (0)

등록된 구현이 없습니다.

Tasks

ObjectObject TrackingOne-Shot LearningSegmentationSemantic SegmentationSemi-Supervised Video Object SegmentationTemplate MatchingVideo Object SegmentationVideo Object TrackingVideo Semantic Segmentation

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

VVitCutLER: Towards Unsupervised Object Detection and Segmentation in Videos

2026-05-11 · Zhijing Lu, Khurram Azeem Hashmi, Didier Stricker, Muhammad Zeshan Afzal arxiv

Unsupervised pixel-level video understanding remains challenging in real-world scenarios, where motion blur, occlusion, and fast object dynamics often cause temporal drift and flickering pseudo-labels.We propose VVitCutL…

Video Object DetectionInstance Segmentation

Attention-guided Temporally Coherent Video Object Matting

2021-05-24 · Yunke Zhang, Chi Wang, Miaomiao Cui, Peiran Ren 외

This paper proposes a novel deep learning-based video object matting method that can achieve temporally coherent matting results. Its key component is an attention-based temporal aggregation module that maximizes image m…

Image MattingObjectSemantic SegmentationVideo Matting+2

CompFeat: Comprehensive Feature Aggregation for Video Instance Segmentation

2020-12-07 · Yang Fu, Linjie Yang, Ding Liu, Thomas S. Huang 외

Video instance segmentation is a complex task in which we need to detect, segment, and track each object for any given video. Previous approaches only utilize single-frame features for the detection, segmentation, and tr…

Instance SegmentationSegmentationSemantic SegmentationVideo Instance Segmentation

STAC: Selective Spatiotemporal Aggregation and Compression for Video Reasoning Segmentation

2026-07-03 · Syed Ariff Syed Hesham, Yun Liu, Guolei Sun, Jing Yang 외 arxiv

Video reasoning segmentation demands pixel-accurate object tracking across hundreds of frames under complex natural language queries, producing dense spatiotemporal tokens whose quadratic self-attention cost makes long-v…

Natural Language QueriesObject Tracking

Flow-Guided Feature Aggregation for Video Object Detection

2017-03-29 · ICCV 2017 10 · Xizhou Zhu, Yujie Wang, Jifeng Dai, Lu Yuan 외

Extending state-of-the-art object detectors from image to video is challenging. The accuracy of detection suffers from degenerated object appearances in videos, e.g., motion blur, video defocus, rare poses, etc. Existing…

Objectobject-detectionObject DetectionVideo Object Detection+1