paper-with-me

Papers

Iteratively Selecting an Easy Reference Frame Makes Unsupervised Video Object Segmentation Easier

2021-12-23 · Youngjo Lee, Hongje Seong, Euntai Kim

Unsupervised video object segmentation (UVOS) is a per-pixel binary labeling problem which aims at separating the foreground object from the background in the video without using the ground truth (GT) mask of the foreground object. Most of the previous UVOS models use the first frame or the entire video as a reference frame to specify the mask of the foreground object. Our question is why the first frame should be selected as a reference frame or why the entire video should be used to specify the mask. We believe that we can select a better reference frame to achieve the better UVOS performance than using only the first frame or the entire video as a reference frame. In our paper, we propose Easy Frame Selector (EFS). The EFS enables us to select an 'easy' reference frame that makes the subsequent VOS become easy, thereby improving the VOS performance. Furthermore, we propose a new framework named as Iterative Mask Prediction (IMP). In the framework, we repeat applying EFS to the given video and selecting an 'easier' reference frame from the video than the previous iteration, increasing the VOS performance incrementally. The IMP consists of EFS, Bi-directional Mask Prediction (BMP), and Temporal Information Updating (TIU). From the proposed framework, we achieve state-of-the-art performance in three UVOS benchmark sets: DAVIS16, FBMS, and SegTrack-V2.

📄 PDF Abstract BibTeX arXiv:2112.12402

Code (0)

등록된 구현이 없습니다.

Tasks

ObjectSemantic SegmentationUnsupervised Video Object SegmentationVideo Object SegmentationVideo Semantic Segmentation

Methods 이 논문이 사용한 방법론

VOS VOS is a type of video object segmentation model consisting of two network components. The target appearance model consists of a light-weight module, which is learned during…

Similar Papers 제목 키워드 기반

CUPID in the Model Zoo: Online Matchmaking for Selecting Your Dream LLM

2026-05-30 · Son Nguyen, Xinyuan Liu, Ransalu Senanayake arxiv

Users increasingly face the challenge of selecting an appropriate LLM for a given task from a rapidly growing pool of LLMs, each with distinct but often opaque latent properties. Compounding this challenge, users may lac…

Active Learning

A General Framework for Information Extraction using Dynamic Span Graphs

2019-04-05 · NAACL 2019 6 · Yi Luan, Dave Wadden, Luheng He, Amy Shah 외

We introduce a general framework for several information extraction tasks that share span representations using dynamically constructed span graphs. The graphs are constructed by selecting the most confident entity spans…

Joint Entity and Relation ExtractionNamed Entity Recognition (NER)RelationRelation Extraction

Hot RAD: A Tool for Analysis of Next-Gen RAD Tag Data

2015-11-20

Restriction site Associated DNA (RAD) tagging (also known as RAD-seq, etc.) is an emerging method for analyzing an organism's genome without completely sequencing it. This can be applied to a non-model organism without a…

TAG

A Hybrid GA LLM Framework for Structured Task Optimization

2025-06-09 · Berry Feng, Jonas Lin, Patrick Lau

GA LLM is a hybrid framework that combines Genetic Algorithms with Large Language Models to handle structured generation tasks under strict constraints. Each output, such as a plan or report, is treated as a gene, and ev…

global-optimizationLanguage ModelingLanguage Modelling

Moving Window Regression: A Novel Approach to Ordinal Regression

2022-03-24 · CVPR 2022 1 · Nyeong-Ho Shin, Seon-Ho Lee, Chang-Su Kim

A novel ordinal regression algorithm, called moving window regression (MWR), is proposed in this paper. First, we propose the notion of relative rank ($\rho$-rank), which is a new order representation scheme for input an…

Age And Gender ClassificationAge Estimationimage-classificationImage Classification+1