L
Li Xin
Researcher at Baidu
Publications - 40
Citations - 981
Li Xin is an academic researcher from Baidu. The author has contributed to research in topics: Feature (computer vision) & Normalization (image processing). The author has an hindex of 7, co-authored 40 publications receiving 345 citations.
Papers
More filters
Proceedings ArticleDOI
BMN: Boundary-Matching Network for Temporal Action Proposal Generation
TL;DR: This work proposes an effective, efficient and end-to-end proposal generation method, named Boundary-Matching Network (BMN), which generates proposals with precise temporal boundaries as well as reliable confidence scores simultaneously, and can achieve state-of-the-art temporal action detection performance.
Posted Content
BMN: Boundary-Matching Network for Temporal Action Proposal Generation
TL;DR: Zhang et al. as discussed by the authors proposed a boundary-matching network (BMN) to evaluate confidence scores of densely distributed proposals, which denote a proposal as a matching pair of starting and ending boundaries and combine all densely distributed BM pairs into the BM confidence map.
Journal ArticleDOI
Image Inpainting by End-to-End Cascaded Refinement with Mask Awareness
TL;DR: Wang et al. as mentioned in this paper proposed Mask-Aware Dynamic Filtering (MADF) module to effectively learn multi-scale features for missing regions in the encoding phase, where filters for each convolution window are generated from features of the corresponding region of the mask.
Proceedings Article
AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer
Songhua Liu,Tianwei Lin,Dongliang He,Fu Li,Meiling Wang,Li Xin,Zhengxing Sun,Qian Li,Errui Ding +8 more
TL;DR: Wang et al. as mentioned in this paper proposed a novel attention and normalization module, named Adaptive Attention Normalization (AdaAttN), to adaptively perform attentive normalization on per-point basis.
Proceedings ArticleDOI
Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfer
TL;DR: Wang et al. as discussed by the authors proposed LapStyle, a novel feed-forward method named Laplacian Pyramid Network (LapStyle), which first transfers global style patterns in low-resolution via a Drafting Network, and then revises the local details in high resolution via a Revision Network, which hallucinates a residual image according to the draft and the image textures extracted by LaPLacian filtering.