M
Mingfei Gao
Researcher at Salesforce.com
Publications - 34
Citations - 1675
Mingfei Gao is an academic researcher from Salesforce.com. The author has contributed to research in topics: Computer science & Object detection. The author has an hindex of 12, co-authored 29 publications receiving 969 citations. Previous affiliations of Mingfei Gao include University of Maryland, College Park & Indiana University.
Papers
More filters
Proceedings ArticleDOI
NISP: Pruning Networks Using Neuron Importance Score Propagation
Ruichi Yu,Ang Li,Chun-Fu Chen,Jui-Hsin Lai,Vlad I. Morariu,Xintong Han,Mingfei Gao,Ching-Yung Lin,Larry S. Davis +8 more
TL;DR: Zhang et al. as mentioned in this paper proposed the Neuron Importance Score Propagation (NISP) algorithm to propagate the importance scores of final responses to every neuron in the network.
Posted Content
NISP: Pruning Networks using Neuron Importance Score Propagation
Ruichi Yu,Ang Li,Chun-Fu Chen,Jui-Hsin Lai,Vlad I. Morariu,Xintong Han,Mingfei Gao,Ching-Yung Lin,Larry S. Davis +8 more
TL;DR: The Neuron Importance Score Propagation (NISP) algorithm is proposed to propagate the importance scores of final responses to every neuron in the network and is evaluated on several datasets with multiple CNN models and demonstrated to achieve significant acceleration and compression with negligible accuracy loss.
Proceedings ArticleDOI
Temporal Recurrent Networks for Online Action Detection
TL;DR: A novel framework, the Temporal Recurrent Network (TRN), to model greater temporal context of each frame by simultaneously performing online action detection and anticipation of the immediate future and integrates both of these into a unified end-to-end architecture.
Proceedings ArticleDOI
Dynamic Zoom-in Network for Fast Object Detection in Large Images
TL;DR: A generic framework that reduces the computational cost of object detection while retaining accuracy for scenarios where objects with varied sizes appear in high resolution images is introduced.
Book ChapterDOI
C-WSL: Count-Guided Weakly Supervised Localization
TL;DR: C-WSL as mentioned in this paper uses a simple count-based region selection algorithm to select high-quality regions, each of which covers a single object instance during training, and improves existing WSL methods by training with the selected regions.