J
Jianqiang Huang
Researcher at Alibaba Group
Publications - 129
Citations - 3264
Jianqiang Huang is an academic researcher from Alibaba Group. The author has contributed to research in topics: Computer science & Feature (computer vision). The author has an hindex of 16, co-authored 102 publications receiving 1129 citations. Previous affiliations of Jianqiang Huang include Nanyang Technological University & Hong Kong Polytechnic University.
Papers
More filters
Proceedings ArticleDOI
Structure Aware Single-Stage 3D Object Detection From Point Cloud
TL;DR: An auxiliary network is designed which converts the convolutional features in the backbone network back to point-level representations and an efficient part-sensitive warping operation is developed to align the confidences to the predicted bounding boxes.
Posted Content
Unbiased Scene Graph Generation from Biased Training
TL;DR: A novel SGG framework based on causal inference but not the conventional likelihood is presented, which uses Total Direct Effect (TDE) as the proposed final predicate score for unbiased SGG and can be widely applied in the community who seeks unbiased predictions.
Proceedings ArticleDOI
Unbiased Scene Graph Generation From Biased Training
TL;DR: In this article, the authors propose to use the counterfactual causality from the trained graph to infer the effect from the bad bias, which should be removed, and use Total Direct Effect (TDE) as the proposed final predicate score for unbiased SGG.
Proceedings ArticleDOI
Quantization Networks
Jiwei Yang,Xu Shen,Jun Xing,Xinmei Tian,Houqiang Li,Bing Deng,Jianqiang Huang,Xian-Sheng Hua +7 more
TL;DR: This paper provides a simple and uniform way for weights and activations quantization by formulating it as a differentiable non-linear function that will shed new lights on the interpretation of neural network quantization.
Proceedings Article
Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect
TL;DR: In this paper, a causal inference framework is proposed to disentangle the paradoxical effects of SGD momentum by pursuing the direct causal effect caused by an input sample, which achieves new state-of-the-art performance on three long-tailed visual recognition benchmarks.