L
Li Su
Researcher at Chinese Academy of Sciences
Publications - 24
Citations - 1144
Li Su is an academic researcher from Chinese Academy of Sciences. The author has contributed to research in topics: Computer science & Medicine. The author has an hindex of 7, co-authored 16 publications receiving 508 citations. Previous affiliations of Li Su include Microsoft.
Papers
More filters
Proceedings ArticleDOI
Cascaded Partial Decoder for Fast and Accurate Salient Object Detection
Zhe Wu,Li Su,Qingming Huang +2 more
TL;DR: A novel Cascaded Partial Decoder (CPD) framework for fast and accurate salient object detection and applies the proposed framework to optimize existing multi-level feature aggregation models and significantly improve their efficiency and accuracy.
Proceedings ArticleDOI
Reverse Perspective Network for Perspective-Aware Object Counting
TL;DR: This work proposes a reverse perspective network to solve the scale variations of input images, instead of generating perspective maps to smooth final outputs, and explicitly evaluates the perspective distortions, and efficiently corrects the distortions by uniformly warping the input images.
Journal ArticleDOI
Complexity-Constrained H.264 Video Encoding
TL;DR: A joint complexity-distortion optimization approach is proposed for real-time H.264 video encoding under the power-constrained environment and the adaptive allocation of computational resources and the fine scalability of complexity control can be achieved.
Book ChapterDOI
Weakly-Supervised Crowd Counting Learns from Sorting Rather Than Locations
TL;DR: A weakly-supervised counting network is proposed, which directly regresses the crowd numbers without the location supervision, and a soft-label sorting network along with the counting network, which sorts the given images by their crowd numbers.
Posted Content
Cascaded Partial Decoder for Fast and Accurate Salient Object Detection
Zhe Wu,Li Su,Qingming Huang +2 more
TL;DR: Cascaded Partial Decoder (CPD) as mentioned in this paper proposes a cascaded partial decoder which discards larger resolution features of shallower layers for acceleration and observe that integrating features of deeper layers obtain relatively precise saliency map.