J
Jiyan Pan
Researcher at Google
Publications - 17
Citations - 431
Jiyan Pan is an academic researcher from Google. The author has contributed to research in topics: Video tracking & Object detection. The author has an hindex of 11, co-authored 17 publications receiving 389 citations. Previous affiliations of Jiyan Pan include Fudan University & Carnegie Mellon University.
Papers
More filters
Proceedings ArticleDOI
Robust Occlusion Handling in Object Tracking
Jiyan Pan,Bo Hu +1 more
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.
Journal ArticleDOI
Robust and Accurate Object Tracking Under Various Types of Occlusions
Jiyan Pan,Bo Hu,Jian Qiu Zhang +2 more
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.
Proceedings Article
Modeling Uncertainty with Hedged Instance Embedding
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.
Proceedings ArticleDOI
Robust abandoned object detection using region-level analysis
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.
Journal ArticleDOI
Phase contrast time-lapse microscopy datasets with automated and manual cell tracking annotations.
Dai Fei Elmer Ker,Dai Fei Elmer Ker,Sungeun Eom,Sho Sanami,Ryoma Bise,Ryoma Bise,Corinne Pascale,Zhaozheng Yin,Zhaozheng Yin,Seungil Huh,Elvira Osuna-Highley,Silvina N. Junkers,Casey J. Helfrich,Peter Liang,Jiyan Pan,Soojin Jeong,Steven S. Kang,Jinyu Liu,Ritchie Nicholson,Michael F. Sandbothe,Phu T. Van,An-An Liu,An-An Liu,Mei Chen,Mei Chen,Mei Chen,Takeo Kanade,Lee E. Weiss,Phil G. Campbell +28 more
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.