Online Video SEEDS for Temporal Window Objectness

By Michel van den Bergh, Gemma Roig, Xavier Boix, Santiago Manen, Luc Van Gool. 2013

94 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

What Makes for Effective Detection Proposals? (2015, background): “The authors show that using multiple superpixel maps signiﬁcantly improves recall.”
Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinity (2022, background): “, [1, 4, 6, 18, 51, 58]), before deep learning for supervised object detection took off, were quite category-agnostic.”
STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos (2020, methodology): “Several bottomup methods segment moving regions by grouping based on optical flow [2,98] or point trajectories [7,62,69,97].”
Efficient Image and Video Co-localization with Frank-Wolfe Algorithm (2014, result): “This is likely because object proposals in the image domain have received a great deal of attention and study [1, 8, 30, 41] compared to video [5, 7].”
Superpixels: An evaluation of the state-of-the-art (2016, methodology): “Finally, several superpixel algorithms (among others [38], [39] and [40]) have been adapted to videos and image volumes – a survey and comparison of some of these so-called supervoxel algorithms can be found in [41].”
Track and Segment: An Iterative Unsupervised Approach for Video Object Proposals (2016, methodology): “However, most methods either attempt to group pixels from all frames [19, 57, 11] or track regions that are initialized from arbitrary frames (e.”
Encouraging LSTMs to Anticipate Actions Very Early (2017, background): “This is in contrast to existing methods that typically extract either global representations for the entire image [6, 41, 42, 7] or video sequence [35, 14], thus not focusing on the action itself, or localize the feature extraction process to the action itself via dense trajectories [39, 38, 9], opt”
Actionness Estimation Using Hybrid Fully Convolutional Networks (2016, background): “However, these classification methods are only able to answer “is there an action of certain type present in the video”, but fail to provide the information about “where is it if there is an action in the video”.”
Video Segmentation by Non-Local Consensus voting (2014, methodology): “Advancement in handling non-rigid motions has been made by supervoxel-based methods [3, 10, 15, 21, 36].”
Robust video segment proposals with painless occlusion handling (2015, background): “Many approaches focus on separating one foreground object from the background, using semi-supervised or unsupervised methods [4, 18, 28, 37, 38, 41, 45].”
Fast action proposals for human action detection and search (2015, background): “However, these action proposal approaches highly rely on relatively accurate video segmentation [37, 38], which itself is a challenging problem.”