Going deeper with convolutions
- Christian Szegedy, Wei Liu, Andrew Rabinovich
- Computer ScienceComputer Vision and Pattern Recognition
- 16 September 2014
We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition…
ParseNet: Looking Wider to See Better
- Wei Liu, Andrew Rabinovich, A. Berg
- Computer SciencearXiv.org
- 15 June 2015
This work presents a technique for adding global context to deep convolutional networks for semantic segmentation, and achieves state-of-the-art performance on SiftFlow and PASCAL-Context with small additional computational cost over baselines.
PointPWC-Net: Cost Volume on Point Clouds for (Self-)Supervised Scene Flow Estimation
- Wenxuan Wu, Zhiyuan Wang, Zhuwen Li, Wei Liu, Fuxin Li
- Computer ScienceEuropean Conference on Computer Vision
- 2020
A novel end-to-end deep scene flow model, called PointPWC-Net, that directly processes 3D point cloud scenes with large motions in a coarse- to-fine fashion, and shows great generalization ability on the KITTI Scene Flow 2015 dataset, outperforming all previous methods.
Predicting Entry-Level Categories
- Vicente Ordonez, Wei Liu, Jia Deng, Yejin Choi, A. Berg, Tamara L. Berg
- Computer ScienceInternational Journal of Computer Vision
- 1 October 2015
Results for category mapping and entry-level category prediction for images show promise for producing more natural human-like labels and the potential applicability of the results to the task of image description generation is demonstrated.
Learning to name objects
- Vicente Ordonez, Wei Liu, Jia Deng, Yejin Choi, A. Berg, Tamara L. Berg
- Computer ScienceCommunications of the ACM
- 25 February 2016
This paper looks at the problem of predicting category labels that mimic how human observers would name objects, related to the concept of entry-level categories first introduced by psychologists in the 1970s and 1980s.
Low-power image recognition challenge
- Kent W. Gauen, Rohit Rangan, A. Mohan, Yung-Hsiang Lu, Wei Liu, A. Berg
- Computer ScienceAsia and South Pacific Design Automation…
- 1 July 2018
Low-Power Image Recognition Challenge (LPIRC) is the only on-site competition that considers both energy consumption and recognition accuracy and was held as one-day workshops in the Design Automation Conference in 2015 and 2016.
Use of opaque sales channels in addition to traditional channels by service providers
- Bo Feng, Wei Liu, Zhaofang Mao
- BusinessInternational Journal of Production Research
- 27 March 2018
This study examines a game in which two collaborative service providers may use an opaque selling channel to satisfy demand from both leisure and business customers, and finds some interesting results driven by the strategic interaction between two service providers and by the heterogeneity of customers.
Opaque distribution channels for service providers with asymmetric capacities: Posted-price mechanisms
- Zhaofang Mao, Wei Liu, Bo Feng
- BusinessInternational Journal of Production Economics
- 2 February 2018
Rebooting Computing and Low-Power Image Recognition Challenge
- Yung-Hsiang Lu, A. Kadin, Jun Yao
- Computer ScienceIEEE/ACM International Conference on Computer…
- 2 November 2015
This paper introduces RC to the design automation community and solicits revolutionary ideas from the community for the directions of future computer research, and explains LPIRC and the solutions from the top two winners.
Refer-to-as Relations as Semantic Knowledge
- Song Feng, Sujith Ravi, Yejin Choi
- Computer ScienceAAAI Conference on Artificial Intelligence
- 25 January 2015
It is posited that Refer-to-as relations can be learned from data, and that both textual and visual information would be helpful in inferring the relations.
...
...