返回
Towards automatic bounding box annotations from weakly labeled images
DOI:10.1007/s11042-014-2434-z.png)
摘要
En 中文
In this work we discuss the problem of automatically determining bounding box annotations for objects in images whereas we only assume weak labeling in the form of global image labels. We therefore are only given a set of positive images all containing at least one instance of a desired object and a negative set of images which represent background. Our goal is then to determine the locations of the object instances within the positive images by bounding boxes. We also describe and analyze a method for automatic bounding box annotation which consists of two major steps. First, we apply a statistical model for determining visual features which are likely to be indicative for the respective object class. Based on these feature models we infer preliminary estimations for bounding boxes. Second, we use a CCCP training algorithm for latent structured SVM in order to improve the initial estimations by using them as initializations for latent variables modeling the optimal bounding box positions. We evaluate our approach on three publicly available datasets.
Keyword:
Automatic annotation
Weakly labeled data
Statistical feature model
Visual features
Image analysis
AI总结
对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3
论文数:
2.0W
被引数:
3.2W
机构
引用论文
E-cadherin, Snail, ZEB-1, DNMT1, DNMT3A and DNMT3B expression in normal and breast cancer tissues*E-cadherin、Snail、ZEB-1、DNMT1、DNMT3A和DNMT3B在正常和乳腺癌组织中的表达*
miR-550a-5p promotes the proliferation and migration of hepatocellular carcinoma by targeting GNE via the Wnt/β-catenin signaling pathwaymiR-550a-5p通过靶向GNE,经由Wnt/β-catenin信号通路促进肝细胞癌的增殖和迁移。
Neoplasma
IF0
Crystalline‐State Reaction with Allosteric Effect in Spin‐Crossover, Interpenetrated Networks with Magnetic and Optical Bistability具有磁和光学双稳态的自旋交叉,互穿网络中具有变构效应的晶态反应
Analysis of Clinicopathological Features and Prognostic Factors in 39 Cases of Bladder Neuroendocrine Carcinoma39例膀胱神经内分泌癌的临床病理特征及预后因素分析

