Skip to content

Latest commit

 

History

History
219 lines (188 loc) · 39.3 KB

2-VOS.md

File metadata and controls

219 lines (188 loc) · 39.3 KB

2. Deep Learning-based Video Object Segmentation

2.1 Automatic Video Object Segmentation (AVOS)

2.1.1 Deep Learning Module based

Year Publication Paper Title Project
2015 CVPR Learning to segment moving objects in videos --
2016 CVPR Video segmentation via object flow Code, Project
2017 CVPR Learning motion patterns in videos Project
2017 ICCV Primary video object segmentation via complementary cnns and neighborhood reversible flow --
2018 TIP Video salient object detection via fully convolutional networks Code

2.1.2 Pixel Instance Embedding based

Year Publication Paper Title Project
2017 arXiv Semantic instance segmentation via deep metric learning --
2018 CVPR Instance embedding transfer to unsupervised video object segmentation --
2018 ECCV video object segmentation with motion-based bilateral networks --

2.1.3 Short-term Information Encoding

Year Publication Paper Title Project
2017 CVPR Fusionseg: Learning to combine motion and appearance for fully automatic segmention of generic objects in videos Code, Project
2017 ICCV Segflow: Joint learning for video object segmentation and optical flow Code, Project
2017 ICCV Learning video object segmentation with visual memory --
2018 ECCV Pyramid dilated deeper convlstm for video salient object detection Code
2018 CVPR Flow guided recurrent neural encoder for video salient object detection --
2019 ICCV Zero-shot video object segmentation via attentive graph neural networks Code
2019 ICCV Motion guided attention for video salient object detection Code
2019 IJCV Learning to segment moving objects --
2020 AAAI Motion attentive transition for zero-shot video object segmentation Code

2.1.4 Long-term Context Encoding

Year Publication Paper Title Project
2019 CVPR See more, know more: Unsupervised video object segmentation with co-attention siamese networks Code
2019 ICCV Anchor diffusion for unsupervised video object segmentation Code
2019 ICCV Zero-shot video object segmentation via attentive graph neural networks Code
2020 AAAI Pyramid constrained network for fast video salient object detection Code
2020 ECCV Unsupervised video object segmentation with joint hotspot tracking Code
2020 ECCV Learning discriminative feature with crf for unsupervised video object segmentation --
2020 TPAMI Zero-Shot Video Object Segmentation with Co-Attention Siamese Networks Code
2021 AAAI F2net: Learning to focus on the foreground for unsupervised video object segmentation --
2021 CVPR Reciprocal transformations for unsupervised video object segmentation Code
2021 TPAMI Segmenting objects from relational visual data Code

2.1.5 Un-/Weakly-supervised based

Year Publication Paper Title Project
2019 CVPR Learning unsupervised video object segmentation through visual attention Code
2019 CVPR Unsupervised moving object detection via contextual information separation Code, Project
2020 CVPR Learning video object segmentation from unlabeled videos Code
2021 CVPR Dystab: Unsupervised object segmentation via dynamic-static bootstrapping Code

2.1.6 Instance-level AVOS

Year Publication Paper Title Project
2019 CVPR See more, know more: Unsupervised video object segmentation with co-attention siamese networks Code
2019 CVPR Rvos: End-to-end recurrent network for video object segmentation Code，Project
2019 ICCV Zero-shot video object segmentation via attentive graph neural networks Code
2020 TPAMI Zero-Shot Video Object Segmentation with Co-Attention Siamese Networks Code
2020 WACV Unovost: Unsupervised offline video object segmentation and tracking --
2021 CVPR Target-aware object discovery and association for unsupervised video multi-object segmentation --
2021 TPAMI Paying attention to video object pattern understanding Code

2.2 Semi-automatic Video Object Segmentation (SVOS)

2.2.1 Online Fine-tuning based

Year Publication Paper Title Project
2017 CVPR One-shot video object segmentation Code
2017 BMVC Online adaptation of convolutional neural networks for video object segmentation Code
2018 CVPR Monet: Deep motion exploitation for video object segmentation --
2018 CVPR Efficient video object segmentation via network modulation Code
2018 TPAMI Video object segmentation without temporal information Project
2019 TPAMI Online meta adaptation for fast video object segmentation Code
2020 NeurIPS Make one-shot video object segmentation efficient again Code

2.2.2 Propagation-based

Year Publication Paper Title Project
2017 CVPR Learning video object segmentation from static images --
2017 CVPR Online video object segmentation via convolutional trident network --
2017 CVPR Video propagation networks Code
2018 CVPR Motion-guided cascaded refinement network for video object segmentation --
2018 CVPR Reinforcement cutting-agent learning for video object segmentation --
2018 CVPR CNN in MRF: Video object segmentation via inference in a CNN-based higher-order spatio-temporal MRF --
2018 CVPR Fast and accurate online video object segmentation via tracking parts Code
2018 CVPR Fast video object segmentation by reference-guided mask propagation --
2018 ECCV Video object segmentation with joint reidentification and attention-aware mask propagation Project
2018 ECCV Video object segmentation by learning location-sensitive embeddings --
2018 arXiv Youtube-vos: A large-scale video object segmentation benchmark Project
2019 IJCV Lucid data dreaming for video object segmentation Code, Project
2019 CVPR Mhp-vos: Multiple hypotheses propagation for video object segmentation Code
2019 CVPR A generative appearance model for end-to-end video object segmentation Code
2019 ICCV Fast video object segmentation via dynamic targeting network --
2019 ICCV Agss-vos: Attention guided single-shot video object segmentation Code
2020 CVPR State-aware tracker for real-time video object segmentation Code
2020 CVPR Fast video object segmentation with temporal aggregation network and dynamic template matching Project
2022 AAAI Reliable Propagation-Correction Modulation for Video Object Segmentation Code

2.2.3 Matching-based

Year Publication Paper Title Project
2015 ICCV Visual tracking with fully convolutional networks --
2017 ICCV Pixel-level matching for video object segmentation using convolutional neural networks --
2017 CVPR Learning video object segmentation from static images --
2018 CVPR Fast and accurate online video object segmentation via tracking parts Code
2018 CVPR CNN in MRF: Video object segmentation via inference in a CNN-based higher-order spatio-temporal MRF --
2018 CVPR Motion-guided cascaded refinement network for video object segmentation --
2018 ECCV Video object segmentation with joint reidentification and attention-aware mask propagation Project
2018 ECCV Videomatch: Matching based video object segmentation --
2018 arXiv Youtube-vos: A large-scale video object segmentation benchmark Project
2019 CVPR Feelvos: Fast end-to-end embedding learning for video object segmentation --
2019 CVPR Mhp-vos: Multiple hypotheses propagation for video object segmentation Code
2019 ICCV Ranet: Ranking attention network for fast video object segmentation Code
2019 ICCV Video object segmentation using space-time memory networks --
2019 ICCV Capsulevos: Semisupervised video object segmentation using capsule routing Code
2020 CVPR A transductive approach for video object segmentation Code
2020 CVPR Learning fast and robust target models for video object segmentation Code
2020 ECCV Collaborative video object segmentation by foreground-background integration Code
2020 ECCV Video object segmentation with episodic graph memory networks Code
2020 ECCV Learning what to learn for video object segmentation Code
2020 ECCV Kernelized memory network for video object segmentation --
2020 ECCV Fast video object segmentation using the global context module --
2020 ECCV Memory selection network for video propagation --
2020 NeurIPS Video object segmentation with adaptive feature bank and uncertain-region refinement Code
2021 CVPR Learning position and target consistency for memory-based video object segmentation --
2021 CVPR Efficient regional memory network for video object segmentation Code, Project
2021 CVPR Video object segmentation using global and instance embedding learning --
2021 CVPR Sstvos: Sparse spatiotemporal transformers for video object segmentation Code
2021 CVPR Swiftnet: Realtime video object segmentation Code

2.2.4 Box-initialization based

Year Publication Paper Title Project
2019 CVPR Fast online object tracking and segmentation: A unifying approach Code, Project
2020 CVPR Fast template matching and update for video object tracking and segmentation Code
2021 AAAI Query-memory reaggregation for weakly-supervised video object segmentation --

2.2.5 Un-/Weakly-supervised based

Year Publication Paper Title Project
2018 ECCV Tracking emerges by colorizing videos --
2019 CVPR Learning correspondence from the cycle-consistency of time Code, Project
2019 NeurIPS Joint-task self-supervised learning for temporal correspondence Code, Project
2020 CVPR Mast: A memory-augmented selfsupervised tracker Code
2020 CVPR Learning video object segmentation from unlabeled videos Code
2020 NeurIPS Space-time correspondence as a contrastive random walk Code, Project
2022 CVPR Locality-Aware Inter-and Intra-Video Reconstruction for Self-Supervised Correspondence Learning Code, Project

2.2.6 Other Specific Methods

Year Publication Paper Title Project
2019 ICCV Dmm-net: Differentiable mask-matching network for video object segmentation Code
2019 CVPR Bubblenets: Learning to select the guidance frame in video object segmentation by deep sorting frames Code
2020 NeurIPS Delving into the cyclic mechanism in semi-supervised video object segmentation --
2021 CVPR Learning dynamic network using a reuse gate function in semi-supervised video object segmentation Code

2.3 Interactive Video Object Segmentation (IVOS)

2.3.1 Interaction-propagation based

Year Publication Paper Title Project
2016 CVPR Deep interactive object selection --
2017 CVPR One-shot video object segmentation Code
2017 arXiv Interactive video object segmentation in the wild --
2019 CVPR Fast user-guided video object segmentation by interaction-and-propagation networks --
2020 CVPR Memory aggregation networks for efficient interactive video object segmentation Code
2020 ECCV Interactive video object segmentation using global and local transfer modules Code, Project
2021 CVPR Guided interactive video object segmentation using reliability-based attention maps Code
2021 CVPR Modular interactive video object segmentation: Interaction-to-mask, propagation and difference-aware fusion Code, Project

2.3.2 Other Methods

Year Publication Paper Title Project
2018 CVPR Blazingly fast video object segmentation with pixel-wise metric learning Code
2018 CVPR Fast and accurate online video object segmentation via tracking parts Code
2020 ECCV Scribblebox: Interactive annotation framework for video object segmentation Project
2021 CVPR Learning to recommend frame for interactive video object segmentation in the wild Code

2.4 Language-guided Video Object Segmentation (LVOS)

2.4.1 Dynamic Convolution-based

Year Publication Paper Title Project
2017 CVPR Tracking by natural language specification Project
2018 CVPR Actor and action video segmentation from a sentence Project
2019 ICCV Asymmetric cross-guided attention network for actor and action video segmentation from natural language query --
2020 AAAI Context modulated dynamic networks for actor and action video segmentation with language queries --
2020 IJCAI Polar relative positional encoding for video-language segmentation --

2.4.2 Capsule Routing-based

Year Publication Paper Title Project
2018 ICLR Matrix capsules with em routing Code
2020 CVPR Visual-textual capsule routing for text-based video segmentation --

2.4.3 Attention-based

Year Publication Paper Title Project
2018 ACCV Video object segmentation with language referring expressions --
2019 ICCV Asymmetric cross-guided attention network for actor and action video segmentation from natural language query --
2020 ECCV Urvos: Unified referring video object segmentation network with a large-scale benchmark Code
2021 CVPR Collaborative spatial-temporal modeling for language-queried video actor segmentation --
2021 TPAMI Referring segmentation in images and videos with cross-modal self-attention network --
2021 TPAMI Cross-modal progressive comprehension for referring segmentation Code