Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Kaiqi Huang

Kaiqi Huang

Learning to Reweight Imaginary Transitions for Model-Based Reinforcement Learning


Apr 09, 2021
Wenzhen Huang, Qiyue Yin, Junge Zhang, Kaiqi Huang

Figure 1 for Learning to Reweight Imaginary Transitions for Model-Based Reinforcement Learning
Figure 2 for Learning to Reweight Imaginary Transitions for Model-Based Reinforcement Learning
Figure 3 for Learning to Reweight Imaginary Transitions for Model-Based Reinforcement Learning
Figure 4 for Learning to Reweight Imaginary Transitions for Model-Based Reinforcement Learning

  Access Paper or Ask Questions

OpenHoldem: An Open Toolkit for Large-Scale Imperfect-Information Game Research


Dec 19, 2020
Kai Li, Hang Xu, Meng Zhang, Enmin Zhao, Zhe Wu, Junliang Xing, Kaiqi Huang

Figure 1 for OpenHoldem: An Open Toolkit for Large-Scale Imperfect-Information Game Research
Figure 2 for OpenHoldem: An Open Toolkit for Large-Scale Imperfect-Information Game Research
Figure 3 for OpenHoldem: An Open Toolkit for Large-Scale Imperfect-Information Game Research
Figure 4 for OpenHoldem: An Open Toolkit for Large-Scale Imperfect-Information Game Research

  Access Paper or Ask Questions

Learning Category- and Instance-Aware Pixel Embedding for Fast Panoptic Segmentation


Sep 28, 2020
Naiyu Gao, Yanhu Shan, Xin Zhao, Kaiqi Huang

Figure 1 for Learning Category- and Instance-Aware Pixel Embedding for Fast Panoptic Segmentation
Figure 2 for Learning Category- and Instance-Aware Pixel Embedding for Fast Panoptic Segmentation
Figure 3 for Learning Category- and Instance-Aware Pixel Embedding for Fast Panoptic Segmentation
Figure 4 for Learning Category- and Instance-Aware Pixel Embedding for Fast Panoptic Segmentation

  Access Paper or Ask Questions

Rethinking of Pedestrian Attribute Recognition: Realistic Datasets with Efficient Method


May 26, 2020
Jian Jia, Houjing Huang, Wenjie Yang, Xiaotang Chen, Kaiqi Huang

Figure 1 for Rethinking of Pedestrian Attribute Recognition: Realistic Datasets with Efficient Method
Figure 2 for Rethinking of Pedestrian Attribute Recognition: Realistic Datasets with Efficient Method
Figure 3 for Rethinking of Pedestrian Attribute Recognition: Realistic Datasets with Efficient Method
Figure 4 for Rethinking of Pedestrian Attribute Recognition: Realistic Datasets with Efficient Method
* 12 pages, 4 figures. Code is availabel at https://github.com/valencebond/Strong_Baseline_of_Pedestrian_Attribute_Recognition 
  Access Paper or Ask Questions

GlobalTrack: A Simple and Strong Baseline for Long-term Tracking


Dec 18, 2019
Lianghua Huang, Xin Zhao, Kaiqi Huang

Figure 1 for GlobalTrack: A Simple and Strong Baseline for Long-term Tracking
Figure 2 for GlobalTrack: A Simple and Strong Baseline for Long-term Tracking
Figure 3 for GlobalTrack: A Simple and Strong Baseline for Long-term Tracking
Figure 4 for GlobalTrack: A Simple and Strong Baseline for Long-term Tracking
* Accepted in AAAI2020 
  Access Paper or Ask Questions

MVP-Net: Multi-view FPN with Position-aware Attention for Deep Universal Lesion Detection


Sep 16, 2019
Zihao Li, Shu Zhang, Junge Zhang, Kaiqi Huang, Yizhou Wang, Yizhou Yu

Figure 1 for MVP-Net: Multi-view FPN with Position-aware Attention for Deep Universal Lesion Detection
Figure 2 for MVP-Net: Multi-view FPN with Position-aware Attention for Deep Universal Lesion Detection
Figure 3 for MVP-Net: Multi-view FPN with Position-aware Attention for Deep Universal Lesion Detection
Figure 4 for MVP-Net: Multi-view FPN with Position-aware Attention for Deep Universal Lesion Detection
* Accepted by MICCAI 2019 (Medical Image Computing and Computer Assisted Intervention) 
  Access Paper or Ask Questions

SSAP: Single-Shot Instance Segmentation With Affinity Pyramid


Sep 04, 2019
Naiyu Gao, Yanhu Shan, Yupei Wang, Xin Zhao, Yinan Yu, Ming Yang, Kaiqi Huang

Figure 1 for SSAP: Single-Shot Instance Segmentation With Affinity Pyramid
Figure 2 for SSAP: Single-Shot Instance Segmentation With Affinity Pyramid
Figure 3 for SSAP: Single-Shot Instance Segmentation With Affinity Pyramid
Figure 4 for SSAP: Single-Shot Instance Segmentation With Affinity Pyramid
* ICCV 2019 
  Access Paper or Ask Questions

SparseMask: Differentiable Connectivity Learning for Dense Image Prediction


Apr 16, 2019
Huikai Wu, Junge Zhang, Kaiqi Huang

Figure 1 for SparseMask: Differentiable Connectivity Learning for Dense Image Prediction
Figure 2 for SparseMask: Differentiable Connectivity Learning for Dense Image Prediction
Figure 3 for SparseMask: Differentiable Connectivity Learning for Dense Image Prediction
Figure 4 for SparseMask: Differentiable Connectivity Learning for Dense Image Prediction
* Code is available at https://github.com/wuhuikai/SparseMask 
  Access Paper or Ask Questions

FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation


Mar 28, 2019
Huikai Wu, Junge Zhang, Kaiqi Huang, Kongming Liang, Yizhou Yu

Figure 1 for FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation
Figure 2 for FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation
Figure 3 for FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation
Figure 4 for FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation
* Code is available in https://github.com/wuhuikai/FastFCN 
  Access Paper or Ask Questions

3D Object Detection Using Scale Invariant and Feature Reweighting Networks


Jan 08, 2019
Xin Zhao, Zhe Liu, Ruolan Hu, Kaiqi Huang

Figure 1 for 3D Object Detection Using Scale Invariant and Feature Reweighting Networks
Figure 2 for 3D Object Detection Using Scale Invariant and Feature Reweighting Networks
Figure 3 for 3D Object Detection Using Scale Invariant and Feature Reweighting Networks
Figure 4 for 3D Object Detection Using Scale Invariant and Feature Reweighting Networks
* The Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19) 
  Access Paper or Ask Questions

EANet: Enhancing Alignment for Cross-Domain Person Re-identification


Dec 29, 2018
Houjing Huang, Wenjie Yang, Xiaotang Chen, Xin Zhao, Kaiqi Huang, Jinbin Lin, Guan Huang, Dalong Du

Figure 1 for EANet: Enhancing Alignment for Cross-Domain Person Re-identification
Figure 2 for EANet: Enhancing Alignment for Cross-Domain Person Re-identification
Figure 3 for EANet: Enhancing Alignment for Cross-Domain Person Re-identification
Figure 4 for EANet: Enhancing Alignment for Cross-Domain Person Re-identification

  Access Paper or Ask Questions

GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild


Oct 29, 2018
Lianghua Huang, Xin Zhao, Kaiqi Huang

Figure 1 for GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild
Figure 2 for GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild
Figure 3 for GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild
Figure 4 for GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild
* 14 pages, 10 figures 
  Access Paper or Ask Questions

Deep Crisp Boundaries: From Boundaries to Higher-level Tasks


Oct 09, 2018
Yupei Wang, Xin Zhao, Yin Li, Kaiqi Huang

Figure 1 for Deep Crisp Boundaries: From Boundaries to Higher-level Tasks
Figure 2 for Deep Crisp Boundaries: From Boundaries to Higher-level Tasks
Figure 3 for Deep Crisp Boundaries: From Boundaries to Higher-level Tasks
Figure 4 for Deep Crisp Boundaries: From Boundaries to Higher-level Tasks
* Accepted by IEEE Trans. on Image Processing 
  Access Paper or Ask Questions

Discriminative Learning of Latent Features for Zero-Shot Recognition


Mar 18, 2018
Yan Li, Junge Zhang, Jianguo Zhang, Kaiqi Huang

Figure 1 for Discriminative Learning of Latent Features for Zero-Shot Recognition
Figure 2 for Discriminative Learning of Latent Features for Zero-Shot Recognition
Figure 3 for Discriminative Learning of Latent Features for Zero-Shot Recognition
Figure 4 for Discriminative Learning of Latent Features for Zero-Shot Recognition
* CVPR 2018 (Oral) 
  Access Paper or Ask Questions

Fast End-to-End Trainable Guided Filter


Mar 15, 2018
Huikai Wu, Shuai Zheng, Junge Zhang, Kaiqi Huang

Figure 1 for Fast End-to-End Trainable Guided Filter
Figure 2 for Fast End-to-End Trainable Guided Filter
Figure 3 for Fast End-to-End Trainable Guided Filter
Figure 4 for Fast End-to-End Trainable Guided Filter
* Accepted by CVPR 2018. Project Website: http://wuhuikai.me/DeepGuidedFilterProject 
  Access Paper or Ask Questions

Mixed Supervised Object Detection with Robust Objectness Transfer


Mar 13, 2018
Yan Li, Junge Zhang, Kaiqi Huang, Jianguo Zhang

Figure 1 for Mixed Supervised Object Detection with Robust Objectness Transfer
Figure 2 for Mixed Supervised Object Detection with Robust Objectness Transfer
Figure 3 for Mixed Supervised Object Detection with Robust Objectness Transfer
Figure 4 for Mixed Supervised Object Detection with Robust Objectness Transfer
* IEEE Transactions on Pattern Analysis and Machine Intelligence (2018). Together with Supplementary Materials 
  Access Paper or Ask Questions

A2-RL: Aesthetics Aware Reinforcement Learning for Image Cropping


Mar 12, 2018
Debang Li, Huikai Wu, Junge Zhang, Kaiqi Huang

Figure 1 for A2-RL: Aesthetics Aware Reinforcement Learning for Image Cropping
Figure 2 for A2-RL: Aesthetics Aware Reinforcement Learning for Image Cropping
Figure 3 for A2-RL: Aesthetics Aware Reinforcement Learning for Image Cropping
Figure 4 for A2-RL: Aesthetics Aware Reinforcement Learning for Image Cropping
* Accepted by CVPR 2018 
  Access Paper or Ask Questions

Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification


Oct 18, 2017
Dangwei Li, Xiaotang Chen, Zhang Zhang, Kaiqi Huang

Figure 1 for Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification
Figure 2 for Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification
Figure 3 for Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification
Figure 4 for Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification
* Accepted by CVPR 2017 
  Access Paper or Ask Questions

MSC: A Dataset for Macro-Management in StarCraft II


Oct 09, 2017
Huikai Wu, Junge Zhang, Kaiqi Huang

Figure 1 for MSC: A Dataset for Macro-Management in StarCraft II
Figure 2 for MSC: A Dataset for Macro-Management in StarCraft II
Figure 3 for MSC: A Dataset for Macro-Management in StarCraft II
Figure 4 for MSC: A Dataset for Macro-Management in StarCraft II
* Homepage: https://github.com/wuhuikai/MSC 
  Access Paper or Ask Questions

Beyond triplet loss: a deep quadruplet network for person re-identification


Apr 06, 2017
Weihua Chen, Xiaotang Chen, Jianguo Zhang, Kaiqi Huang

Figure 1 for Beyond triplet loss: a deep quadruplet network for person re-identification
Figure 2 for Beyond triplet loss: a deep quadruplet network for person re-identification
Figure 3 for Beyond triplet loss: a deep quadruplet network for person re-identification
Figure 4 for Beyond triplet loss: a deep quadruplet network for person re-identification
* accepted to CVPR2017 
  Access Paper or Ask Questions

GP-GAN: Towards Realistic High-Resolution Image Blending


Mar 25, 2017
Huikai Wu, Shuai Zheng, Junge Zhang, Kaiqi Huang

Figure 1 for GP-GAN: Towards Realistic High-Resolution Image Blending
Figure 2 for GP-GAN: Towards Realistic High-Resolution Image Blending
Figure 3 for GP-GAN: Towards Realistic High-Resolution Image Blending
Figure 4 for GP-GAN: Towards Realistic High-Resolution Image Blending
* See more information in the project website: https://wuhuikai.github.io/GP-GAN-Project/ 
  Access Paper or Ask Questions

A Large-scale Distributed Video Parsing and Evaluation Platform


Nov 29, 2016
Kai Yu, Yang Zhou, Da Li, Zhang Zhang, Kaiqi Huang

Figure 1 for A Large-scale Distributed Video Parsing and Evaluation Platform
Figure 2 for A Large-scale Distributed Video Parsing and Evaluation Platform
* Accepted by Chinese Conference on Intelligent Visual Surveillance 2016 
  Access Paper or Ask Questions

A Multi-task Deep Network for Person Re-identification


Nov 25, 2016
Weihua Chen, Xiaotang Chen, Jianguo Zhang, Kaiqi Huang

Figure 1 for A Multi-task Deep Network for Person Re-identification
Figure 2 for A Multi-task Deep Network for Person Re-identification
Figure 3 for A Multi-task Deep Network for Person Re-identification
* Accepted by AAAI2017 
  Access Paper or Ask Questions

Weakly-supervised Learning of Mid-level Features for Pedestrian Attribute Recognition and Localization


Nov 17, 2016
Kai Yu, Biao Leng, Zhang Zhang, Dangwei Li, Kaiqi Huang

Figure 1 for Weakly-supervised Learning of Mid-level Features for Pedestrian Attribute Recognition and Localization
Figure 2 for Weakly-supervised Learning of Mid-level Features for Pedestrian Attribute Recognition and Localization
Figure 3 for Weakly-supervised Learning of Mid-level Features for Pedestrian Attribute Recognition and Localization
Figure 4 for Weakly-supervised Learning of Mid-level Features for Pedestrian Attribute Recognition and Localization
* Containing 9 pages and 5 figures. Codes open-sourced on https://github.com/kyu-sz/WPAL-network 
  Access Paper or Ask Questions

Deep Aesthetic Quality Assessment with Semantic Information


Oct 21, 2016
Yueying Kao, Ran He, Kaiqi Huang

Figure 1 for Deep Aesthetic Quality Assessment with Semantic Information
Figure 2 for Deep Aesthetic Quality Assessment with Semantic Information
Figure 3 for Deep Aesthetic Quality Assessment with Semantic Information
Figure 4 for Deep Aesthetic Quality Assessment with Semantic Information
* 13 pages, 10 figures 
  Access Paper or Ask Questions

An equalised global graphical model-based approach for multi-camera object tracking


Jul 19, 2016
Weihua Chen, Lijun Cao, Xiaotang Chen, Kaiqi Huang

Figure 1 for An equalised global graphical model-based approach for multi-camera object tracking
Figure 2 for An equalised global graphical model-based approach for multi-camera object tracking
Figure 3 for An equalised global graphical model-based approach for multi-camera object tracking
Figure 4 for An equalised global graphical model-based approach for multi-camera object tracking
* 13 pages, 17 figures 
  Access Paper or Ask Questions

A Richly Annotated Dataset for Pedestrian Attribute Recognition


Apr 27, 2016
Dangwei Li, Zhang Zhang, Xiaotang Chen, Haibin Ling, Kaiqi Huang

Figure 1 for A Richly Annotated Dataset for Pedestrian Attribute Recognition
Figure 2 for A Richly Annotated Dataset for Pedestrian Attribute Recognition
Figure 3 for A Richly Annotated Dataset for Pedestrian Attribute Recognition
Figure 4 for A Richly Annotated Dataset for Pedestrian Attribute Recognition
* 16 pages, 8 figures 
  Access Paper or Ask Questions

Translation-Invariant Representation for Cumulative Foot Pressure Images


Oct 26, 2010
Shuai Zheng, Kaiqi Huang, Tieniu Tan

Figure 1 for Translation-Invariant Representation for Cumulative Foot Pressure Images
Figure 2 for Translation-Invariant Representation for Cumulative Foot Pressure Images
Figure 3 for Translation-Invariant Representation for Cumulative Foot Pressure Images
Figure 4 for Translation-Invariant Representation for Cumulative Foot Pressure Images
* Shuai Zheng, Kaiqi Huang and Tieniu Tan. Translation Invariant Representation for Cumulative foot pressure Image, The second CJK Joint Workshop on Pattern Recognition(CJKPR), 2010 
 * 6 pages 
  Access Paper or Ask Questions