Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

Detection of visually salient image regions is useful for applications like object segmentation, adaptive compression, and object recognition. In this paper, we introduce a method for salient region detection that outputs full resolution saliency maps with well-defined boundaries of salient objects. These boundaries are preserved by retaining substantially more frequency content from the original image than other existing techniques. Our method exploits features of color and luminance, is simple to implement, and is computationally efficient. We compare our algorithm to five state-of-the-art salient region detection methods with a frequency domain analysis, ground truth, and a salient object segmentation application. Our method outperforms the five algorithms both on the ground-truth evaluation and on the segmentation task by achieving both higher precision and better recall.

/pdf/frequency-tuned-salient-region-detection-4po18ylvds.pdf

Frequency-tuned salient region detection

Automatic estimation of salient object regions across images, without any prior assumption or knowledge of the contents of the corresponding scenes, enhances many computer vision and computer graphics applications. We introduce a regional contrast based salient object detection algorithm, which simultaneously evaluates global contrast differences and spatial weighted coherence scores. The proposed algorithm is simple, efficient, naturally multi-scale, and produces full-resolution, high-quality saliency maps. These saliency maps are further used to initialize a novel iterative version of GrabCut, namely SaliencyCut, for high quality unsupervised salient object segmentation. We extensively evaluated our algorithm using traditional salient object detection datasets, as well as a more challenging Internet image dataset. Our experimental results demonstrate that our algorithm consistently outperforms 15 existing salient object detection and segmentation methods, yielding higher precision and better recall rates. We also show that our algorithm can be used to efficiently extract salient object masks from Internet images, enabling effective sketch-based image retrieval (SBIR) via simple shape comparisons. Despite such noisy internet images, where the saliency regions are ambiguous, our saliency guided image retrieval achieves a superior retrieval rate compared with state-of-the-art SBIR methods, and additionally provides important target object region information.

https://mmcheng.net/mftp/SalObj/PosterSaliency.pdf

Global contrast based salient region detection

From the Publisher: 
The accessible presentation of this book gives both a general view of the entire computer vision enterprise and also offers sufficient detail to be able to build useful applications. Users learn techniques that have proven to be useful by first-hand experience and a wide range of mathematical methods. A CD-ROM with every copy of the text contains source code for programming practice, color images, and illustrative movies. Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance. Topics are discussed in substantial and increasing depth. Application surveys describe numerous important application areas such as image based rendering and digital libraries. Many important algorithms broken down and illustrated in pseudo code. Appropriate for use by engineers as a comprehensive reference to the computer vision enterprise.

Computer vision : a modern approach = 计算机视觉 : 一种现代的方法

The query-by-image video retrieval (QBIVR) is a difficult feature matching task across different modalities. More and more retrieval tasks require indexing the videos containing the activities in the image, which makes extracting meaningful spatio-temporal video features crucial. In this paper, we propose an approach based on adversarial learning, termed Adversarial Image-to-Video (AIV) approach. To capture the temporal pattern of videos, we utilize temporal regions likely to contain activities via fully-convolutional 3D ConvNet features, and then obtain the video bag features by 3D RoI Pooling. To solve mismatch issue with image vector features and identify the importances of information for videos, we add a Multiple Instance Learning (MIL) module to assign different weights to each temporal information in video bags. Moreover, we utilize the triplet loss to distinguish different semantic categorites and support intraclass variability of images and videos. Specially, our AIV proposes modality loss as an adversary to the triplet loss in the adversarial learning. The interplay between two losses jointly bridges the domain gap across different modalities. Extensive experiments on two widely used datasets verify the effectiveness of our proposed methods as compared with other methods.

Adversarial Query-by-Image Video Retrieval Based on Attention Mechanism

With the prevalence of image editing techniques, users can create fantastic synthetic images, but the image quality may be compromised by the color/illumination discrepancy between the manipulated region and background. Inharmonious region localization aims to localize the inharmonious region in a synthetic image. In this work, we attempt to leverage auxiliary style feature to facilitate this task. Specifically, we propose a novel color mapping module and a style feature loss to extract discriminative style features containing task-relevant color/illumination information. Based on the extracted style features, we also propose a novel style voting module to guide the localization of inharmonious region. Moreover, we introduce semantic information into the style voting module to achieve further improvement. Our method surpasses the existing methods by a large margin on the benchmark dataset.

Inharmonious Region Localization with Auxiliary Style Feature

For non‐small‐cell lung cancer (NSCLC) patients receiving neoadjuvant therapy, the major pathological response (MPR) is defined as the percentage of residual viable tumour cells (%RVT) in the tumour bed of no more than 10%. It has been proposed as a predictor of survival in neoadjuvant therapy‐treated cohorts. Nonetheless, the significance of %RVT in the pathological assessment of lung adenocarcinoma cohorts remains undetermined.

Major pathological response exhibited distinct prognostic significance for lung adenocarcinoma post different modalities of neoadjuvant therapy

The International Association for the Study of Lung Cancer proposed a novel grading system of invasive pulmonary adenocarcinoma (IPA), but the application of this grading system and its genotypic characterization in the real diagnostic scenario has never been reported.We prospectively collected and analyzed the clinicopathological and genotypic features of a cohort of 9353 consecutive patients with resected IPA, including 7134 patients with detection of common driver mutation.In the entire cohort, 3 (0.3%) of lepidic, 1207 (19.0%) of acinar, and 126 (23.6%) of papillary predominant IPAs were diagnosed as grade 3. In chronological order, an evident downtrend of the proportion of grade 2 was observed in chronological order. Conversely, the diagnostic ratio of grade 1 (8.0%-14.5%) and grade 3 (27.9%-32.3%) experienced a gradual rise. EGFR mutation was more frequently detected in grade 2 (77.5%) and grade 1 (69.7%) IPA than grade 3 (53.7%, p < 0.001), whereas the mutation rates of KRAS, BRAF, ALK, and ROS1 were higher in grade 3 IPA. More importantly, the rate of EGFR mutation gradually fell as the proportion of high-grade components increased, to 24.3% in IPA with more than 90% high-grade components.The grading system for IPA could be applied to stratify patients with different clinicopathological and genotypic features in a real diagnostic scenario. 

https://doi.org/10.1016/j.jtocrr.2023.100465

Application of the Novel Grading System of Invasive Pulmonary Adenocarcinoma in a Real Diagnostic Scenario: A Brief Report of 9353 Cases

This article tackles the problem of multi-person 3D human pose estimation based on monocular image sequence in a three-step framework: (1) we detect 2D human skeletons in each frame across the image sequence; (2) we track each person through the image sequence and identify the sequence of 2D skeletons for each person; (3) we reconstruct the 3D human skeleton for each person from the detected 2D human joints, by using prelearned base poses and considering the temporal smoothness. We evaluate our framework on the Human3.6M dataset and the multi-person image sequence captured by ourselves. The quantitative results on the Human3.6M dataset and the qualitative results on our constructed test data demonstrate the effectiveness of our proposed method.

Liqing Zhang

Papers

Adversarial Query-by-Image Video Retrieval Based on Attention Mechanism

Inharmonious Region Localization with Auxiliary Style Feature

Major pathological response exhibited distinct prognostic significance for lung adenocarcinoma post different modalities of neoadjuvant therapy

Application of the Novel Grading System of Invasive Pulmonary Adenocarcinoma in a Real Diagnostic Scenario: A Brief Report of 9353 Cases

Multi-person 3D Pose Estimation from Monocular Image Sequences