The 2018 DAVIS Challenge on Video Object Segmentation

Abstract

We present the 2018 DAVIS Challenge on Video Object Segmentation, a public competition specifically designed for the task of video object segmentation. It builds upon the DAVIS 2017 dataset, which was presented in the previous edition of the DAVIS Challenge, and added 100 videos with multiple objects per sequence to the original DAVIS 2016 dataset. Motivated by the analysis of the results of the 2017 edition, the main track of the competition will be the same than in the previous edition (segmentation given the full mask of the objects in the first frame -- semi-supervised scenario). This edition, however, also adds an interactive segmentation teaser track, where the participants will interact with a web service simulating the input of a human that provides scribbles to iteratively improve the result.

arXiv commentChallenge website: http://davischallenge.org/

References in corpus (2)

• FusionSeg: Learning to combine motion and appearance for fully automatic segmention of generic objects in videos
• Learning Video Object Segmentation with Visual Memory

Cited by in corpus (32)

• DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images
• A Survey of Human-in-the-loop for Machine Learning
• RANet: Ranking Attention Network for Fast Video Object Segmentation
• Motion-Attentive Transition for Zero-Shot Video Object Segmentation
• STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos
• VLT: Vision-Language Transformer and Query Generation for Referring Segmentation
• The 2019 DAVIS Challenge on VOS: Unsupervised Multi-Object Segmentation
• One-Shot Instance Segmentation
• Video Object Segmentation and Tracking: A Survey
• FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation
• AlignNet-3D: Fast Point Cloud Registration of Partially Observed Objects
• HODOR: High-level Object Descriptors for Object Re-segmentation in Video Learned from Static Images
• Learning Joint Spatial-Temporal Transformations for Video Inpainting
• MHP-VOS: Multiple Hypotheses Propagation for Video Object Segmentation
• Memory Aggregation Networks for Efficient Interactive Video Object Segmentation
• Key Instance Selection for Unsupervised Video Object Segmentation
• Foreground-Aware Stylization and Consensus Pseudo-Labeling for Domain Adaptation of First-Person Hand Segmentation
• Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion
• Progressive Motion Context Refine Network for Efficient Video Frame Interpolation
• SpVOS: Efficient Video Object Segmentation with Triple Sparse Convolution
• Value of Temporal Dynamics Information in Driving Scene Segmentation
• End-to-end Deep Object Tracking with Circular Loss Function for Rotated Bounding Box
• Progressive Temporal Feature Alignment Network for Video Inpainting
• ScribbleBox: Interactive Annotation Framework for Video Object Segmentation
• Fast Video Object Segmentation With Temporal Aggregation Network and Dynamic Template Matching
• Learning-Based Human Segmentation and Velocity Estimation Using Automatic Labeled LiDAR Sequence for Training
• Dynamic Matrix Recovery
• Guided Interactive Video Object Segmentation Using Reliability-Based Attention Maps
• Interactive Video Object Segmentation Using Global and Local Transfer Modules
• Learning to Recommend Frame for Interactive Video Object Segmentation in the Wild
• Learning a Weakly-Supervised Video Actor-Action Segmentation Model with a Wise Selection
• One-Shot Texture Retrieval with Global Context Metric