Video Object Segmentation by Learning Location-Sensitive Embeddings

Ci, Hai; Wang, Qianqian; Wang, Yizhou

doi:10.1007/978-3-030-01252-6_31

Cited by 58 publications

(38 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compare our method to existing methods that are trained on Youtube-VOS training set by [13,37]. As shown in Table 1 [11] 80.7 80.9 -VideoMatch [12] 81.0 -0.32s FEELVOS (+YV) [33] 81.1 82.2 0.45s RGMP [24] 81.5 82.0 0.13s A-GAME (+YV) [13] 82.0 82.2 0.07s FAVOS [4] 82.4 79.5 1.8s LSE [6] 82.9 80.3 -CINN [1] 83.4 85.0 >30s PReMVOS [20] 84.9 88.6 >30s OSVOS S [21] 85.6 86.4 4.5s OnAVOS [34] 86.1 84.9 13s DyeNet [18] 86. target object. We compare our method with state-of-the-art methods in Table 2.…”

Section: Youtube-vosmentioning

confidence: 99%

Video Object Segmentation Using Space-Time Memory Networks

Lee

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

531

417

View full text Add to dashboard Cite

We propose a novel solution for semi-supervised video object segmentation. By the nature of the problem, available cues (e.g. video frame(s) with object masks) become richer with the intermediate predictions. However, the existing methods are unable to fully exploit this rich source of information. We resolve the issue by leveraging memory networks and learn to read relevant information from all available sources. In our framework, the past frames with object masks form an external memory, and the current frame as the query is segmented using the mask information in the memory. Specifically, the query and the memory are densely matched in the feature space, covering all the space-time pixel locations in a feed-forward fashion. Contrast to the previous approaches, the abundant use of the guidance information allows us to better handle the challenges such as appearance changes and occlussions. We validate our method on the latest benchmark sets and achieved the state-of-the-art performance (overall score of 79.4 on Youtube-VOS val set, J of 88.7 and 79.2 on DAVIS 2016/2017 val set respectively) while having a fast runtime (0.16 second/frame on DAVIS 2016 val set).

show abstract

Section: Youtube-vosmentioning

confidence: 99%

Video Object Segmentation Using Space-Time Memory Networks

Lee

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

531

417

View full text Add to dashboard Cite

show abstract

“…MaskRNN [16] uses a recurrent neural network to fuse the output of two deep networks. Location-sensitive embeddings used to refine an initial foreground prediction are explored in LSE [9]. MoNet [38] exploits optical flow motion cues by feature alignment and a distance transform layer.…”

Section: Related Workmentioning

confidence: 99%

FEELVOS: Fast End-To-End Embedding Learning for Video Object Segmentation

Voigtlaender

Chai

Schroff

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

415

329

View full text Add to dashboard Cite

Many of the recent successful methods for video object segmentation (VOS) are overly complicated, heavily rely on fine-tuning on the first frame, and/or are slow, and are hence of limited practical use. In this work, we propose FEELVOS as a simple and fast method which does not rely on fine-tuning. In order to segment a video, for each frame FEELVOS uses a semantic pixel-wise embedding together with a global and a local matching mechanism to transfer information from the first frame and from the previous frame of the video to the current frame. In contrast to previous work, our embedding is only used as an internal guidance of a convolutional network. Our novel dynamic segmentation head allows us to train the network, including the embedding, end-to-end for the multiple object segmentation task with a cross entropy loss. We achieve a new state of the art in video object segmentation without fine-tuning with a J &F measure of 71.5% on the DAVIS 2017 validation set. We make our code and models available at https://github.com/tensorflow/ models/tree/master/research/feelvos. * Work done during an internship at Google Inc.† Now at Waymo LLC. Simple Fast End-to-end Strong PML [6] OSMN [40] FAVOS [7] VideoMatch [17] RGMP [37] FEELVOS (ours) PReMVOS [26] OnAVOS [35]

show abstract

“…Segmentation of small objects is challenging and zooming in on regions of the frame has been explored to overcome this problem. The authors in [7] demonstrated the effectiveness of processing only a tight region around the foreground object. Although this allows for improved segmentations, it assumes the object moves smoothly within the video -in cases of large motions, this may fail.…”

Section: Related Workmentioning

confidence: 99%

CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing

Duarte

Rawat

Shah

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

In this work we propose a capsule-based approach for semi-supervised video object segmentation. Current video object segmentation methods are frame-based and often require optical flow to capture temporal consistency across frames which can be difficult to compute. To this end, we propose a video based capsule network, CapsuleVOS, which can segment several frames at once conditioned on a reference frame and segmentation mask. This conditioning is performed through a novel routing algorithm for attention-based efficient capsule selection. We address two challenging issues in video object segmentation: 1) segmentation of small objects and 2) occlusion of objects across time. The issue of segmenting small objects is addressed with a zooming module which allows the network to process small spatial regions of the video. Apart from this, the framework utilizes a novel memory module based on recurrent networks which helps in tracking objects when they move out of frame or are occluded. The network is trained end-to-end and we demonstrate its effectiveness on two benchmark video object segmentation datasets; it outperforms current offline approaches on the Youtube-VOS dataset while having a run-time that is almost twice as fast as competing methods. The code is publicly available at https://github.com/KevinDuarte/CapsuleVOS.

show abstract

Video Object Segmentation by Learning Location-Sensitive Embeddings

Cited by 58 publications

References 24 publications

Video Object Segmentation Using Space-Time Memory Networks

Video Object Segmentation Using Space-Time Memory Networks

FEELVOS: Fast End-To-End Embedding Learning for Video Object Segmentation

CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing

Contact Info

Product

Resources

About