Filters








514 Hits in 6.3 sec

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

Ye Wang, Jongmoo Choi, Yueru Chen, Qin Huang, Siyang Li, Ming-Sui Lee, C.-C. Jay Kuo
2018 arXiv   pre-print
As a result, we propose to prepare inexpensive, yet high quality pseudo ground truth corrected with motion cue for video object segmentation training.  ...  Our method conducts semantic segmentation using instance segmentation networks and, then, selects the segmented object of interest as the pseudo ground truth based on the motion information.  ...  There are two important cues in video object segmentations: appearance and motion.  ... 
arXiv:1812.05206v1 fatcat:frprtbqbqbeofd34mzjkiozqma

Unsupervised Video Object Segmentation with Distractor-Aware Online Adaptation [article]

Ye Wang, Jongmoo Choi, Yueru Chen, Siyang Li, Qin Huang, Kaitai Zhang, Ming-Sui Lee, C.-C. Jay Kuo
2018 arXiv   pre-print
Unsupervised video object segmentation is a crucial application in video analysis without knowing any prior information about the objects.  ...  In this paper, a novel unsupervised video object segmentation approach via distractor-aware online adaptation (DOA) is proposed.  ...  Therefore, motion cues are essen-tial to be incorporated to tackle unsupervised video object segmentation.  ... 
arXiv:1812.07712v1 fatcat:sztkyovztfdjlgeto4tu6j5kuu

Semi-Supervised Video Salient Object Detection Using Pseudo-Labels [article]

Pengxiang Yan, Guanbin Li, Yuan Xie, Zhen Li, Chuan Wang, Tianshui Chen, Liang Lin
2019 arXiv   pre-print
By utilizing the generated pseudo-labels together with a part of manual annotations, our video saliency detector learns spatial and temporal cues for both contrast inference and coherence enhancement,  ...  Deep learning-based video salient object detection has recently achieved great success with its performance significantly outperforming any other unsupervised methods.  ...  Video Object Segmentation Video object segmentation tasks can be divided into two categories, including semi-supervised video object segmentation [16, 7] and unsupervised video object segmentation [  ... 
arXiv:1908.04051v2 fatcat:yyedrrc2lnfq7gfz6ecfnu4usq

Learning Features by Watching Objects Move

Deepak Pathak, Ross Girshick, Piotr Dollar, Trevor Darrell, Bharath Hariharan
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
Specifically, we use unsupervised motion-based segmentation on videos to obtain segments, which we use as 'pseudo ground truth' to train a convolutional network to segment objects from a single frame.  ...  When used for transfer learning on object detection, our representation significantly outperforms previous unsupervised approaches across multiple settings, especially when training data for the target  ...  Thus in our second setting we train with automatically generated 'pseudo ground truth' obtained through unsupervised motion segmentation on uncurated videos from the Yahoo Flickr Creative Commons 100 million  ... 
doi:10.1109/cvpr.2017.638 dblp:conf/cvpr/PathakGDDH17 fatcat:teizzuwtkzbhrfiwm2zh4xoqde

Learning Features by Watching Objects Move [article]

Deepak Pathak, Ross Girshick, Piotr Dollár, Trevor Darrell, Bharath Hariharan
2017 arXiv   pre-print
Specifically, we use unsupervised motion-based segmentation on videos to obtain segments, which we use as 'pseudo ground truth' to train a convolutional network to segment objects from a single frame.  ...  When used for transfer learning on object detection, our representation significantly outperforms previous unsupervised approaches across multiple settings, especially when training data for the target  ...  Thus in our second setting we train with automatically generated 'pseudo ground truth' obtained through unsupervised motion segmentation on uncurated videos from the Yahoo Flickr Creative Commons 100 million  ... 
arXiv:1612.06370v2 fatcat:h6pqo6j4cvh5xo2gagxscw7v5y

Unsupervised Surgical Instrument Segmentation via Anchor Generation and Semantic Diffusion [article]

Daochang Liu, Yuhui Wei, Tingting Jiang, Yizhou Wang, Rulin Miao, Fei Shan, Ziyu Li
2020 arXiv   pre-print
To train our model, we first generate anchors as pseudo labels for instruments and background tissues respectively by fusing coarse handcrafted cues.  ...  using a single manual annotation, which is promising to show the potential of unsupervised learning for surgical tool segmentation.  ...  Thank Boshuo Wang for making the video demo.  ... 
arXiv:2008.11946v1 fatcat:5jirbaiv7vcwdowjjv2q6twacm

Disentangling Motion, Foreground and Background Features in Videos [article]

Xunyu Lin, Victor Campos, Xavier Giro-i-Nieto, Jordi Torres and Cristian Canton Ferrer
2017 arXiv   pre-print
A preliminary supervised experiment was conducted to verify the feasibility of proposed method by training the model with a fraction of videos from the UCF-101 dataset taking as ground truth the bounding  ...  Inspired by how the human visual system groups objects based on motion cues, we propose a deep convolutional neural network that disentangles motion, foreground and background information.  ...  The pseudo ground truth for this task is obtained by getting first foreground features from the encoder fed with the temporally reversed clip.  ... 
arXiv:1707.04092v2 fatcat:rfzk4sazbzaghaino5nfwxbc2m

FusionSeg: Learning to Combine Motion and Appearance for Fully Automatic Segmentation of Generic Objects in Videos

Suyog Dutt Jain, Bo Xiong, Kristen Grauman
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
We propose an end-to-end learning framework for segmenting generic objects in videos.  ...  Our method learns to combine appearance and motion information to produce pixel level segmentation masks for all prominent objects.  ...  For videos with multiple objects with individual ground-truth segmentations, we treat them as a single foreground for evaluation.  ... 
doi:10.1109/cvpr.2017.228 dblp:conf/cvpr/JainXG17 fatcat:zbvjxxwj65abldg5bnodcu4cle

Implicit Motion Handling for Video Camouflaged Object Detection [article]

Xuelian Cheng, Huan Xiong, Deng-Ping Fan, Yiran Zhong, Mehrtash Harandi, Tom Drummond, Zongyuan Ge
2022 arXiv   pre-print
We also provide a large-scale VCOD dataset named MoCA-Mask with pixel-level handcrafted ground-truth masks and construct a comprehensive VCOD benchmark with previous methods to facilitate research in this  ...  Therefore, effectively handling temporal dynamics in videos becomes the key for the VCOD task as the camouflaged objects will be noticeable when they move.  ...  Also, since the features used to form the correlation pyramid will be updated with the segmentation ground truth, we can use the segmentation ground truth to optimize motion estimations and detection results  ... 
arXiv:2203.07363v2 fatcat:wnba2jnwjndx5ddtcqpkeijntq

Target-Aware Object Discovery and Association for Unsupervised Video Multi-Object Segmentation [article]

Tianfei Zhou, Jianwu Li, Xueyi Li, Ling Shao
2021 arXiv   pre-print
This paper addresses the task of unsupervised video multi-object segmentation.  ...  For temporal association, we complement current video object segmentation architectures with a discriminative appearance model, capable of capturing more fine-grained target-specific information.  ...  To address this, in our approach, the segment proposal from D-Net for each target serves as the pseudo ground-truth labely 0 for initial model learning.  ... 
arXiv:2104.04782v1 fatcat:7qa2244w7rgl5ez26euybjcrlq

FusionSeg: Learning to combine motion and appearance for fully automatic segmention of generic objects in videos [article]

Suyog Dutt Jain, Bo Xiong, Kristen Grauman
2017 arXiv   pre-print
Our method learns to combine appearance and motion information to produce pixel level segmentation masks for all prominent objects in videos.  ...  We propose an end-to-end learning framework for segmenting generic objects in videos.  ...  For videos with multiple objects with individual ground-truth segmentations, we treat them as a single foreground for evaluation.  ... 
arXiv:1701.05384v2 fatcat:hm3axkp4svbmlot7kx66664try

Self-supervised classification of dynamic obstacles using the temporal information provided by videos [article]

Sid Ali Hamideche, Florent Chiaroni, Mohamed-Cherif Rahal
2020 arXiv   pre-print
On another note, some self-supervised learning approaches can deal with detection and segmentation of dynamic obstacles using the temporal information available in video sequences.  ...  The presented model outperforms state-of-the-art unsupervised image classification methods on large-scale diverse driving video dataset BDD100K.  ...  It consists of finding the best oneto-one mapping between the ground truth labels and the clusters.  ... 
arXiv:1910.09094v2 fatcat:nooqptmxbbdnhlg6nctvzoabzy

Unsupervised Segmentation in Real-World Images via Spelke Object Inference [article]

Honglin Chen, Rahul Venkatesh, Yoni Friedman, Jiajun Wu, Joshua B. Tenenbaum, Daniel L. K. Yamins, Daniel M. Bear
2022 arXiv   pre-print
Correlations between independent sources of motion (e.g. robot arms) and objects they move are resolved into separate segments through a bootstrapping training process.  ...  Self-supervised category-agnostic segmentation of real-world images into objects is a challenging open problem in computer vision.  ...  multiple ground truth segments.  ... 
arXiv:2205.08515v1 fatcat:bwbznulc4vhdnmutod3qp52mte

Occlusion boundary detection and figure/ground assignment from optical flow

Patrik Sundberg, Thomas Brox, Michael Maire, Pablo Arbelaez, Jitendra Malik
2011 CVPR 2011  
In this work, we propose a contour and region detector for video data that exploits motion cues and distinguishes occlusion boundaries from internal boundaries based on optical flow.  ...  computational models for occlusion boundary detection, depth ordering and segmentation in video sequences.  ...  Unsupervised segmentation from static images is not currently possible, but motion is a very reliable cue for this task.  ... 
doi:10.1109/cvpr.2011.5995364 dblp:conf/cvpr/SundbergBMAM11 fatcat:wtclg5hmsbgebeberq5h2xw54q

Attention Embedded Spatio-Temporal Network for Video Salient Object Detection

Lili Huang, Pengxiang Yan, Guanbin Li, Qing Wang, Liang Lin
2019 IEEE Access  
Moreover, an experiment on the extended application to unsupervised video object segmentation further demonstrates the generalization ability and stability of our proposed method.  ...  The main challenge in video salient object detection is how to model object motion and dramatic changes in appearance contrast.  ...  PERFORMANCE ON UNSUPERVISED VIDEO OBJECT SEGMENTATION Unsupervised video object segmentation, which aims to segment primary objects from input video sequences, has almost the same problem setting as that  ... 
doi:10.1109/access.2019.2953046 fatcat:rciq4rmf5nhc5icsvkdmlqdchq
« Previous Showing results 1 — 15 out of 514 results