Y
Yuting Su
Researcher at Tianjin University
Publications - Â 244
Citations - Â 4118
Yuting Su is an academic researcher from Tianjin University. The author has contributed to research in topics: Computer science & Feature extraction. The author has an hindex of 28, co-authored 220 publications receiving 3081 citations.
Papers
More filters
Journal ArticleDOI
Hierarchical Clustering Multi-Task Learning for Joint Human Action Grouping and Recognition
TL;DR: This paper forms the objective function into the group-wise least square loss regularized by low rank and sparsity with respect to two latent variables, model parameters and grouping information, for joint optimization and can attain both optimal action models and group discovery by alternating iteratively.
Proceedings ArticleDOI
Mnemonics Training: Multi-Class Incremental Learning without Forgetting
TL;DR: This paper proposes a novel and automatic framework, called mnemonics, where parameterize exemplars and make them optimizable in an end-to-end manner, and shows that using mnemonic exemplars can surpass the state-of-the-art by a large margin.
Proceedings ArticleDOI
Mnemonics Training: Multi-Class Incremental Learning Without Forgetting
TL;DR: In this paper, the authors propose a framework called mnemonics, where they parameterize exemplars and make them optimizable in an end-to-end manner, and train the framework through bilevel optimizations, i.e., model-level and exemplar-level.
Journal ArticleDOI
Multi-Modal Clique-Graph Matching for View-Based 3D Model Retrieval
TL;DR: The proposed MCG provides the following benefits: 1) preserves the local and global attributes of a graph with the designed structure; 2) eliminates redundant and noisy information by strengthening inliers while suppressing outliers; and 3) avoids the difficulty of defining high-order attributes and solving hyper-graph matching.
Journal ArticleDOI
Multipe/Single-View Human Action Recognition via Part-Induced Multitask Structural Learning
TL;DR: This paper is the first to demonstrate the applicability of MTSL with part-based regularization on multiple/single-view human action recognition in both RGB and depth modalities.