Learning event representations for temporal segmentation of image sequences by dynamic graph embedding
Institut de Robòtica i Informàtica Industrial, CSIC-UPC（工业机器人与信息研究所（CSIC-UPC））；Institut de Recherche en Informatique de Toulouse, CNRS, University of Toulouse（图卢兹计算机研究所，法国国家科学研究中心，图卢兹大学）
Mariella Dimiccoli, Herwig Wendt
备注：
Accepted in IEEE Transactions on Image Processing, 2020. To appear
Recently, self-supervised learning has proved to be effective to learn representations of events suitable for temporal segmentation in image sequences, where events are understood as sets of temporally adjacent images that are semantically perceived as a whole. However, although this approach does not require expensive manual annotations, it is data hungry and suffers from domain adaptation problems. As an alternative, in this work, we propose a novel approach for learning event representations named Dynamic Graph Embedding (DGE). The assumption underlying our model is that a sequence of images can be represented by a graph that encodes both semantic and temporal similarity. The key novelty of DGE is to learn jointly the graph and its graph embedding. At its core, DGE works by iterating over two steps: 1) updating the graph representing the semantic and temporal similarity of the data based on the current data representation, and 2) updating the data representation to take into account the current data graph structure. The main advantage of DGE over state-of-the-art self-supervised approaches is that it does not require any training set, but instead learns iteratively from the data itself a low-dimensional embedding that reflects their temporal and semantic similarity. Experimental results on two benchmark datasets of real image sequences captured at regular time intervals demonstrate that the proposed DGE leads to event representations effective for temporal segmentation. In particular, it achieves robust temporal segmentation on the EDUBSeg and EDUBSeg-Desc benchmark datasets, outperforming the state of the art. Additional experiments on two Human Motion Segmentation benchmark datasets demonstrate the generalization capabilities of the proposed DGE.
Embedding Generalized Semantic Knowledge into Few-Shot Remote Sensing Segmentation
School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University（西北工业大学人工智能与光学电子学院（iOPEN））；Data Science in Earth Observation, Technical University of Munich（慕尼黑工业大学地球观测数据科学系）
Hepatocellular Carcinoma Segmentation from Digital Subtraction Angiography Videos using Learnable Temporal Difference
The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Shenzhen Research Institute of Big Data（深圳大数据研究院）；The First Affiliated Hospital of Jinan University（暨南大学附属第一医院）
Embedding-based Instance Segmentation in Microscopy
Max Planck Institute of Molecular Cell Biology and Genetics（马克斯·普朗克分子细胞生物学与遗传学研究所）；Center for Systems Biology Dresden (CSBD)（德累斯顿系统生物学中心）；IT4Innovations, VŠB - Technical University of Ostrava（IT4Innovations，俄斯特拉发技术大学）；Fondatione Human Technopole（人类技术基金会）
Improving Chinese Segmentation-free Word Embedding With Unsupervised Association Measure
University of Chinese Academy of Sciences（中国科学院大学）；Chinese Academy of Sciences（中国科学院）；Shanghai Advanced Research Institute（上海高等研究院）；Shanghai Carbon Data Research Center（上海碳数据研究中心）；Centre for Excellence in Brain Science and Intelligence Technology（脑科学与智能技术卓越创新中心）
Fine-Grained Semantic Segmentation of Motion Capture Data using Dilated Temporal Fully-Convolutional Networks
German Research Center for Artificial Intelligence (DFKI) Saarbrücken（德国人工智能研究中心（DFKI）萨尔布吕肯）；Saarland University（萨尔大学）；Max-Planck Institute for Informatics（马克斯-普朗克计算机科学研究所）
