Bingbing Ni
Shanghai Jiao Tong University
288 Papers
1.2K Citations
Bingbing Ni is an academic researcher from Shanghai Jiao Tong University. The author has contributed to research in topics: Computer science & Feature extraction. The author has an hindex of 45, co-authored 238 publications. Previous affiliations of Bingbing Ni include Huawei & Google.
Chat about Author
Papers
HCP: A Flexible CNN Framework for Multi-Label Image Classification
TL;DR: Experimental results on Pascal VOC 2007 and VOC 2012 multi-label image datasets well demonstrate the superiority of the proposed HCP infrastructure over other state-of-the-arts, where an arbitrary number of object segment hypotheses are taken as the inputs.
Crowded Scene Analysis: A Survey
TL;DR: The background knowledge and the available features related to crowded scenes are provided and existing models, popular algorithms, evaluation protocols, and system performance are provided corresponding to different aspects of the crowded scene analysis.
546
Modeling Point Clouds With Self-Attention and Gumbel Subset Sampling
Jiancheng Yang,Qiang Zhang,Bingbing Ni,Linguo Li,Jinxian Liu,Mengdie Zhou,Qi Tian +6 more
- 01 Jun 2019
TL;DR: This work develops Point Attention Transformers (PATs), using a parameter-efficient Group Shuffle Attention (GSA) to replace the costly Multi-Head Attention, and proposes an end-to-end learnable and task-agnostic sampling operation, named Gumbel Subset Sampling (GSS), to select a representative subset of input points.
535
Adversarial Domain Adaptation with Domain Mixup
Minghao Xu,Jian Zhang,Bingbing Ni,Teng Li,Chengjie Wang,Qi Tian,Wenjun Zhang +6 more
- 03 Apr 2020
TL;DR: This paper presents adversarial domain adaptation with domain mixup (DM-ADA), which guarantees domain-invariance in a more continuous latent space and guides the domain discriminator in judging samples' difference relative to source and target domains.
Pose Transferrable Person Re-identification
Jinxian Liu,Bingbing Ni,Yichao Yan,Peng Zhou,Shuo Cheng,Jianguo Hu +5 more
- 18 Jun 2018
TL;DR: A pose-transferrable person ReID framework which utilizes posetransferred sample augmentations (i.e., with ID supervision) to enhance ReID model training, and achieves great performance improvement, and outperforms most state-of-the-art methods without elaborate designing the ReIDs.