1 code implementation • 16 Sep 2024 • Meng Chen, Jiawei Tu, Chao Qi, Yonghao Dang, Feng Zhou, Wei Wei, Jianqin Yin
Experimental results show our adversarial patches reduce navigation success rates by about 40%, outperforming previous methods in practicality, effectiveness, and naturalness.
no code implementations • 12 Jun 2024 • Ren Zhang, Jianqin Yin, Chao Qi, Zehao Wang, Zhicheng Zhang, Yonghao Dang
Conversely, depth information can effectively represent motion information related to facial structure changes and is not affected by lighting.
no code implementations • 21 Feb 2023 • Chao Qi, Jianqin Yin, Jinghang Xu, Pengxiang Ding
This work introduces a new task of instance-incremental scene graph generation: Given a scene of the point cloud, representing it as a graph and automatically increasing novel instances.
no code implementations • 5 Dec 2021 • Chao Qi, Jianqin Yin
Specifically, the NSA-MC dropout samples the model many times through a space-dependent way, outputting point-wise distribution by aggregating stochastic inference results of neighbors.
no code implementations • 23 Nov 2021 • Chao Qi, Murilo Sandroni, Jesper Cairo Westergaard, Ea Høegh Riis Sundmark, Merethe Bagge, Erik Alexandersson, Junfeng Gao
Effective early detection of potato late blight (PLB) is an essential aspect of potato cultivation.
no code implementations • 4 Nov 2021 • Chao Qi, Junfeng Gao, Simon Pearson, Helen Harman, Kunjie Chen, Lei Shu
Tea chrysanthemum detection at its flowering stage is one of the key components for selective chrysanthemum harvesting robot development.
1 code implementation • 11 Jun 2019 • Wentao Ouyang, Xiuwu Zhang, Shukui Ren, Chao Qi, Zhaojie Liu, Yanlong Du
These subnets model the user-ad, ad-ad and feature-CTR relationship respectively.
Ranked #2 on
Click-Through Rate Prediction
on Avito
no code implementations • EMNLP 2017 • Zhen Xu, Bingquan Liu, Baoxun Wang, Chengjie Sun, Xiaolong Wang, Zhuoran Wang, Chao Qi
This paper presents a Generative Adversarial Network (GAN) to model single-turn short-text conversations, which trains a sequence-to-sequence (Seq2Seq) network for response generation simultaneously with a discriminative classifier that measures the differences between human-produced responses and machine-generated ones.