paper-with-me

Papers Unsupervised Video Object Segmentation

“Unsupervised Video Object Segmentation” 태그가 달린 논문 93편 · 필터 해제

EpO-Net: Exploiting Geometric Constraints on Dense Trajectories for Motion Saliency

2019-09-29 · WACV 2020 3 · Muhammad Faisal, Ijaz Akhter, Mohsen Ali, Richard Hartley

The existing approaches for salient motion segmentation are unable to explicitly learn geometric cues and often give false detections on prominent static objects. We exploit multiview geometric constraints to avoid such …

Motion SegmentationOptical Flow EstimationUnsupervised Video Object SegmentationVideo Object Segmentation

Joint-task Self-supervised Learning for Temporal Correspondence

2019-09-26 · NeurIPS 2019 12 · Xueting Li, Sifei Liu, Shalini De Mello, Xiaolong Wang 외

This paper proposes to learn reliable dense correspondence from videos in a self-supervised manner. Our learning process integrates two highly related tasks: tracking large image regions \emph{and} establishing fine-grai…

Object TrackingSelf-Supervised LearningSemi-Supervised Video Object SegmentationUnsupervised Video Object Segmentation

Semi-Supervised Video Salient Object Detection Using Pseudo-Labels

2019-08-12 · ICCV 2019 10 · Pengxiang Yan, Guanbin Li, Yuan Xie, Zhen Li 외

Deep learning-based video salient object detection has recently achieved great success with its performance significantly outperforming any other unsupervised methods. However, existing data-driven approaches heavily rel…

object-detectionRGB Salient Object DetectionSalient Object DetectionUnsupervised Video Object Segmentation+1

Global Optimality Guarantees for Nonconvex Unsupervised Video Segmentation

2019-07-09 · Brendon G. Anderson, Somayeh Sojoudi

In this paper, we consider the problem of unsupervised video object segmentation via background subtraction. Specifically, we pose the nonsemantic extraction of a video's moving objects as a nonconvex optimization proble…

ObjectSegmentationSemantic SegmentationUnsupervised Video Object Segmentation+3

A 3D Convolutional Approach to Spectral Object Segmentation in Space and Time

2019-07-05 · Elena Burceanu, Marius Leordeanu

We formulate object segmentation in video as a graph partitioning problem in space and time, in which nodes are pixels and their relations form local neighborhoods. We claim that the strongest cluster in this pixel-level…

ClusteringGPUgraph partitioningInstance Segmentation+3

Key Instance Selection for Unsupervised Video Object Segmentation

2019-06-18 · Donghyeon Cho, Sungeun Hong, Sungil Kang, Jiwon Kim

This paper proposes key instance selection based on video saliency covering objectness and dynamics for unsupervised video object segmentation (UVOS). Our method takes frames sequentially and extracts object proposals wi…

ObjectSegmentationSemantic SegmentationUnsupervised Video Object Segmentation+2

Learning Unsupervised Video Object Segmentation Through Visual Attention

2019-06-01 · CVPR 2019 6 · Wenguan Wang, Hongmei Song, Shuyang Zhao, Jianbing Shen 외

This paper conducts a systematic study on the role of visual attention in Unsupervised Video Object Segmentation (UVOS) tasks. By elaborately annotating three popular video segmentation datasets (DAVIS, Youtube-Objects a…

ObjectSegmentationSemantic SegmentationUnsupervised Video Object Segmentation+3

Self-supervised Learning for Video Correspondence Flow

2019-05-02 · Zihang Lai, Weidi Xie

The objective of this paper is self-supervised learning of feature embeddings that are suitable for matching correspondences along the videos, which we term correspondence flow. By leveraging the natural spatial-temporal…

Self-Supervised LearningSemi-Supervised Video Object SegmentationUnsupervised Video Object SegmentationVideo Correspondence Flow+2

Learning Correspondence from the Cycle-Consistency of Time

2019-03-18 · CVPR 2019 6 · Xiaolong Wang, Allan Jabri, Alexei A. Efros

We introduce a self-supervised method for learning visual correspondence from unlabeled video. The main idea is to use cycle-consistency in time as free supervisory signal for learning visual representations from scratch…

Optical Flow EstimationSemantic SegmentationSemi-Supervised Video Object SegmentationUnsupervised Video Object Segmentation+2

RVOS: End-to-End Recurrent Network for Video Object Segmentation

2019-03-13 · CVPR 2019 6 · Carles Ventura, Miriam Bellver, Andreu Girbau, Amaia Salvador 외

Multiple object video object segmentation is a challenging task, specially for the zero-shot case, when no object mask is given at the initial frame and the model has to find the objects to be segmented along the sequenc…

GPUObjectOne-shot visual object segmentationSegmentation+4

Unsupervised Moving Object Detection via Contextual Information Separation

2019-01-10 · CVPR 2019 6 · Yanchao Yang, Antonio Loquercio, Davide Scaramuzza, Stefano Soatto

We propose an adversarial contextual model for detecting moving objects in images. A deep neural network is trained to predict the optical flow in a region using information from everywhere else but that region (context)…

Moving Object DetectionObjectobject-detectionObject Detection+2

Unsupervised Video Object Segmentation with Distractor-Aware Online Adaptation

2018-12-19 · Ye Wang, Jongmoo Choi, Yueru Chen, Siyang Li 외

Unsupervised video object segmentation is a crucial application in video analysis without knowing any prior information about the objects. It becomes tremendously challenging when multiple objects occur and interact in a…

Instance SegmentationObjectSegmentationSemantic Segmentation+3

Design Pseudo Ground Truth with Motion Cue for Unsupervised Video Object Segmentation

2018-12-13 · Ye Wang, Jongmoo Choi, Yueru Chen, Qin Huang 외

One major technique debt in video object segmentation is to label the object masks for training instances. As a result, we propose to prepare inexpensive, yet high quality pseudo ground truth corrected with motion cue fo…

Instance SegmentationObjectObject TrackingSegmentation+4

Tukey-Inspired Video Object Segmentation

2018-11-19 · Brent A. Griffin, Jason J. Corso

We investigate the problem of strictly unsupervised video object segmentation, i.e., the separation of a primary object from background in video without a user-provided object mask or any training on an annotated dataset…

ObjectSegmentationSemantic SegmentationUnsupervised Video Object Segmentation+2

Video Object Segmentation using Teacher-Student Adaptation in a Human Robot Interaction (HRI) Setting

2018-10-17 · Mennatullah Siam, Chen Jiang, Steven Lu, Laura Petrich 외

Video object segmentation is an essential task in robot manipulation to facilitate grasping and learning affordances. Incremental learning is important for robotics in unstructured environments, since the total number of…

Incremental LearningRobot ManipulationSegmentationSemantic Segmentation+3

Unsupervised Online Video Object Segmentation with Motion Property Understanding

2018-10-09 · IEEE Transactions on Image Processing 2019 8 · Tao Zhuo, Zhiyong Cheng, Peng Zhang, Yongkang Wong 외

Unsupervised video object segmentation aims to automatically segment moving objects over an unconstrained video without any user annotation. So far, only few unsupervised online methods have been reported in literature a…

Motion DetectionObjectSegmentationSemantic Segmentation+3

Unsupervised Video Object Segmentation using Motion Saliency-Guided Spatio-Temporal Propagation

2018-09-04 · ECCV 2018 9 · Yuan-Ting Hu, Jia-Bin Huang, Alexander G. Schwing

Unsupervised video segmentation plays an important role in a wide variety of applications from object identification to compression. However, to date, fast motion, motion blur and occlusions pose significant challenges. …

Deep LearningOptical Flow EstimationSaliency PredictionSegmentation+6

Unsupervised Video Object Segmentation with Motion-based Bilateral Networks

2018-09-01 · ECCV 2018 9 · Siyang Li, Bryan Seybold, Alexey Vorobyov, Xuejing Lei 외

In this work, we study the unsupervised video object segmentation problem where moving objects are segmented without prior knowledge of these objects. First, we propose a motion-based bilateral network to estimate the ba…

ObjectSegmentationSemantic SegmentationUnsupervised Video Object Segmentation+3

Pyramid Dilated Deeper ConvLSTM for Video Salient Object Detection

2018-09-01 · ECCV 2018 9 · Hongmei Song, Wenguan Wang, Sanyuan Zhao, Jianbing Shen 외

This paper proposes a fast video salient object detection model, based on a novel recurrent network architecture, named Pyramid Dilated Bidirectional ConvLSTM (PDB-ConvLSTM). A Pyramid Dilated Convolution (PDC) module is…

GPUObjectobject-detectionObject Detection+7

Extending Layered Models to 3D Motion

2018-09-01 · ECCV 2018 9 · Dong Lao, Ganesh Sundaramoorthi

We consider the problem of inferring a layered representa-tion, its depth ordering and motion segmentation from a video in whichobjects may undergo 3D non-planar motion relative to the camera. Wegeneralize layered infere…

Motion SegmentationObjectSegmentationUnsupervised Video Object Segmentation
← 이전 61–80 / 93 다음 →