computer-vision-1

Foreground Segmentation

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in foreground-segmentation-1

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find foreground-segmentation-1 models and implementations

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

One-Shot Video Object Segmentation

L. Gool, D. Cremers, J. Pont-Tuset, L. Leal-Taixé, Kevis-Kokitsi Maninis, Sergi Caelles•Tue Nov 15 2016

One-Shot Video Object Segmentation (OSVOS), based on a fully-convolutional neural network architecture that is able to successively transfer generic semantic information, learned on ImageNet, to the task of foreground segmentation, and finally to learning the appearance of a single annotated object of the test sequence (hence one-shot).

970

Content

0

Paper Graph

Neural Head Reenactment with Latent Pose Descriptors

V. Lempitsky, Egor Burkov, A. Grigorev, I. Pasechnik•Thu Apr 23 2020

A neural head reenactment system, which is driven by a latent pose representation and is capable of predicting the foreground segmentation alongside the RGB image, and shows that the learned descriptors are useful for other pose-related tasks, such as keypoint prediction and pose-based retrieval.

146 0

Paper Graph

Explicit Visual Prompting for Universal Foreground Segmentations

Chi-Man Pun, Weihuang Liu, Xiaodong Cun, Xi Shen•Sun May 28 2023

This paper takes inspiration from the widely-used pre-training and then prompt tuning protocols in NLP and proposes a new visual prompting model, named Explicit Visual Prompting (EVP), which freezes a pre-trained model and then learns task-specific knowledge using a few extra parameters.

23 0

Paper Graph

PartSTAD: 2D-to-3D Part Segmentation Task Adaptation

Hyunjin Kim, Minhyuk Sung•Wed Jan 10 2024

This work introduces PartSTAD, a method designed for the task adaptation of 2D-to-3D segmentation lifting that finetunes a 2D bounding box prediction model with an objective function for 3D segmentation.

18 0

Paper Graph

Foreground Segmentation Using a Triplet Convolutional Neural Network for Multiscale Feature Encoding

H. Keles, Long Ang Lim•Sat Jan 06 2018

Two robust encoder-decoder type neural networks that generate multi-scale feature encodings in different ways and can be trained end-to-end using only a few training samples are proposed.

209 0

Paper Graph

One-Shot Segmentation in Clutter

M. Bethge, Claudio Michaelis, Alexander S. Ecker•Sun Mar 25 2018

An improved model that attends to multiple candidate locations, generates segmentation proposals to mask out background clutter and selects among the segmented objects is introduced, suggesting that such image recognition models based on an iterative refinement of object detection and foreground segmentation may provide a way to deal with highly cluttered scenes.

41 0

Paper Graph

Learning multi-scale features for foreground segmentation

H. Keles, Long Ang Lim•Fri Aug 03 2018

This work proposes a variation of the formerly proposed FgSegNet method that can be trained end-to-end using only a few training examples, and outperforms all existing state-of-the-art methods in CDnet2014 datasets by an average overall F-measure.

190 0

Paper Graph

Online Mutual Foreground Segmentation for Multispectral Stereo Videos

Guillaume-Alexandre Bilodeau, P. St-Charles, R. Bergevin•Fri Sep 07 2018

A new method to simultaneously tackle multispectral segmentation and stereo registration is presented, based on the alternating minimization of two energy functions that are linked through the use of dynamic priors.

12 0

Paper Graph

Illumination-Based Data Augmentation for Robust Background Subtraction

Hubert P. H. Shum, Dimitrios Sakkos, Edmond S. L. Ho•Wed Jun 19 2019

This method performs data augmentation that not only creates endless data on the fly, but also features semantic transformations of illumination which enhance the generalisation of the model.

16 0

Paper Graph

Adding a benchmark result helps the community track progress.