paper-with-me

Papers

Space-time Reinforcement Network for Video Object Segmentation

2024-05-07 · Yadang Chen, Wentao Zhu, Zhi-Xin Yang, Enhua Wu

Recently, video object segmentation (VOS) networks typically use memory-based methods: for each query frame, the mask is predicted by space-time matching to memory frames. Despite these methods having superior performance, they suffer from two issues: 1) Challenging data can destroy the space-time coherence between adjacent video frames. 2) Pixel-level matching will lead to undesired mismatching caused by the noises or distractors. To address the aforementioned issues, we first propose to generate an auxiliary frame between adjacent frames, serving as an implicit short-temporal reference for the query one. Next, we learn a prototype for each video object and prototype-level matching can be implemented between the query and memory. The experiment demonstrated that our network outperforms the state-of-the-art method on the DAVIS 2017, achieving a J&F score of 86.4%, and attains a competitive result 85.0% on YouTube VOS 2018. In addition, our network exhibits a high inference speed of 32+ FPS.

📄 PDF Abstract BibTeX arXiv:2405.04042

Code (0)

등록된 구현이 없습니다.

Tasks

ObjectSemantic SegmentationVideo Object SegmentationVideo 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…
VOS VOS is a type of video object segmentation model consisting of two network components. The target appearance model consists of a light-weight module, which is learned during…

Similar Papers 제목 키워드 기반

ALBA : Reinforcement Learning for Video Object Segmentation

2020-05-26 · Shreyank N Gowda, Panagiotis Eustratiadis, Timothy Hospedales, Laura Sevilla-Lara

We consider the challenging problem of zero-shot video object segmentation (VOS). That is, segmenting and tracking multiple moving objects within a video fully automatically, without any manual initialization. We treat t…

ObjectOne-shot visual object segmentationreinforcement-learningReinforcement Learning+6

Learning a Fast 3D Spectral Approach to Object Segmentation and Tracking over Space and Time

2022-12-15 · Elena Burceanu, Marius Leordeanu

We pose video object segmentation as spectral graph clustering in space and time, with one graph node for each pixel and edges forming local space-time neighborhoods. We claim that the strongest cluster in this video gra…

ClusteringGPUGraph ClusteringObject+6

A Simple Video Segmenter by Tracking Objects Along Axial Trajectories

2023-11-30 · Ju He, Qihang Yu, Inkyu Shin, Xueqing Deng 외

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 feature…

GPUObjectObject TrackingPanoptic Segmentation+5

Unsupervised Learning of Object Keypoints for Perception and Control

2019-06-19 · NeurIPS 2019 12 · Tejas Kulkarni, Ankush Gupta, Catalin Ionescu, Sebastian Borgeaud 외

The study of object representations in computer vision has primarily focused on developing representations that are useful for image classification, object detection, or semantic segmentation as downstream tasks. In this…

3D Action Recognitionimage-classificationImage ClassificationObject+6

Towards Good Practices for Video Object Segmentation

2019-09-30 · Dongdong Yu, Kai Su, Hengkai Guo, Jian Wang 외

Semi-supervised video object segmentation is an interesting yet challenging task in machine learning. In this work, we conduct a series of refinements with the propagation-based video object segmentation method and empir…

BIG-bench Machine LearningObjectOne-shot visual object segmentationSegmentation+4