Jiyan Pan

TL;DR: An algorithm is proposed that progressively analyzes the occlusion situation by exploiting the spatiotemporal context information, which enables the proposed algorithm to make a clearer distinction between the target and occluders than existing approaches.

TL;DR: A content-adaptive progressive occlusion analysis (CAPOA) algorithm that makes a clear distinction between the target and outliers, and a drift-inhibitive masked Kalman appearance filter (DIMKAF) which accurately evaluates the influence of template drift when updating the masked template.

TL;DR: The hedged instance embedding (HIB) is introduced in which embeddings are modeled as random variables and the model is trained under the variational information bottleneck principle and results in improved performance for image matching and classification tasks, more structure in the learned embedding space, and an ability to compute a per-exemplar uncertainty measure that is correlated with downstream performance.

TL;DR: This work proposes a robust abandoned object detection algorithm for real-time video surveillance that performs region-level analysis in both background maintenance and static foreground object detection and is robust against illumination change, “ghosts” left by removed objects, distractions from partially static objects, and occlusions.

TL;DR: 48 time-lapse image sequences were generated with accompanying ground truths for C2C12 myoblast cells cultured under 4 different media conditions, including with fibroblast growth factor 2 (FGF2), bone morphogenetic protein 2 (BMP2), FGF2, BMP2, and control, providing an invaluable opportunity to deepen the understanding of individual and population-based cell dynamics for biomedical research.