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 Kan Chen

Kan Chen

Edge of chaos as a guiding principle for modern neural network training


Jul 20, 2021
Lin Zhang, Ling Feng, Kan Chen, Choy Heng Lai

Figure 1 for Edge of chaos as a guiding principle for modern neural network training
Figure 2 for Edge of chaos as a guiding principle for modern neural network training
Figure 3 for Edge of chaos as a guiding principle for modern neural network training
Figure 4 for Edge of chaos as a guiding principle for modern neural network training

  Access Paper or Ask Questions

Differentially Private Bayesian Neural Networks on Accuracy, Privacy and Reliability


Jul 18, 2021
Qiyiwen Zhang, Zhiqi Bu, Kan Chen, Qi Long

Figure 1 for Differentially Private Bayesian Neural Networks on Accuracy, Privacy and Reliability
Figure 2 for Differentially Private Bayesian Neural Networks on Accuracy, Privacy and Reliability
Figure 3 for Differentially Private Bayesian Neural Networks on Accuracy, Privacy and Reliability
Figure 4 for Differentially Private Bayesian Neural Networks on Accuracy, Privacy and Reliability

  Access Paper or Ask Questions

Video Question Answering with Phrases via Semantic Roles


Apr 08, 2021
Arka Sadhu, Kan Chen, Ram Nevatia

Figure 1 for Video Question Answering with Phrases via Semantic Roles
Figure 2 for Video Question Answering with Phrases via Semantic Roles
Figure 3 for Video Question Answering with Phrases via Semantic Roles
Figure 4 for Video Question Answering with Phrases via Semantic Roles
* NAACL21 Camera Ready including appendix 
  Access Paper or Ask Questions

Unbiased Teacher for Semi-Supervised Object Detection


Feb 18, 2021
Yen-Cheng Liu, Chih-Yao Ma, Zijian He, Chia-Wen Kuo, Kan Chen, Peizhao Zhang, Bichen Wu, Zsolt Kira, Peter Vajda

Figure 1 for Unbiased Teacher for Semi-Supervised Object Detection
Figure 2 for Unbiased Teacher for Semi-Supervised Object Detection
Figure 3 for Unbiased Teacher for Semi-Supervised Object Detection
Figure 4 for Unbiased Teacher for Semi-Supervised Object Detection
* Accepted to ICLR 2021; Code is available at https://github.com/facebookresearch/unbiased-teacher 
  Access Paper or Ask Questions

A Dynamical View on Optimization Algorithms of Overparameterized Neural Networks


Oct 25, 2020
Zhiqi Bu, Shiyun Xu, Kan Chen

Figure 1 for A Dynamical View on Optimization Algorithms of Overparameterized Neural Networks
Figure 2 for A Dynamical View on Optimization Algorithms of Overparameterized Neural Networks
Figure 3 for A Dynamical View on Optimization Algorithms of Overparameterized Neural Networks
Figure 4 for A Dynamical View on Optimization Algorithms of Overparameterized Neural Networks

  Access Paper or Ask Questions

FBNetV3: Joint Architecture-Recipe Search using Neural Acquisition Function


Jun 07, 2020
Xiaoliang Dai, Alvin Wan, Peizhao Zhang, Bichen Wu, Zijian He, Zhen Wei, Kan Chen, Yuandong Tian, Matthew Yu, Peter Vajda, Joseph E. Gonzalez

Figure 1 for FBNetV3: Joint Architecture-Recipe Search using Neural Acquisition Function
Figure 2 for FBNetV3: Joint Architecture-Recipe Search using Neural Acquisition Function
Figure 3 for FBNetV3: Joint Architecture-Recipe Search using Neural Acquisition Function
Figure 4 for FBNetV3: Joint Architecture-Recipe Search using Neural Acquisition Function

  Access Paper or Ask Questions

CPARR: Category-based Proposal Analysis for Referring Relationships


Apr 17, 2020
Chuanzi He, Haidong Zhu, Jiyang Gao, Kan Chen, Ram Nevatia

Figure 1 for CPARR: Category-based Proposal Analysis for Referring Relationships
Figure 2 for CPARR: Category-based Proposal Analysis for Referring Relationships
Figure 3 for CPARR: Category-based Proposal Analysis for Referring Relationships
Figure 4 for CPARR: Category-based Proposal Analysis for Referring Relationships
* CVPR 2020 Workshop on Multimodal Learning 
  Access Paper or Ask Questions

FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions


Apr 12, 2020
Alvin Wan, Xiaoliang Dai, Peizhao Zhang, Zijian He, Yuandong Tian, Saining Xie, Bichen Wu, Matthew Yu, Tao Xu, Kan Chen, Peter Vajda, Joseph E. Gonzalez

Figure 1 for FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions
Figure 2 for FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions
Figure 3 for FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions
Figure 4 for FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions
* 8 pages, 10 figures, accepted to CVPR 2020 
  Access Paper or Ask Questions

Video Object Grounding using Semantic Roles in Language Description


Mar 24, 2020
Arka Sadhu, Kan Chen, Ram Nevatia

Figure 1 for Video Object Grounding using Semantic Roles in Language Description
Figure 2 for Video Object Grounding using Semantic Roles in Language Description
Figure 3 for Video Object Grounding using Semantic Roles in Language Description
Figure 4 for Video Object Grounding using Semantic Roles in Language Description
* CVPR20 camera-ready including appendix 
  Access Paper or Ask Questions

Zero-Shot Grounding of Objects from Natural Language Queries


Aug 20, 2019
Arka Sadhu, Kan Chen, Ram Nevatia

Figure 1 for Zero-Shot Grounding of Objects from Natural Language Queries
Figure 2 for Zero-Shot Grounding of Objects from Natural Language Queries
Figure 3 for Zero-Shot Grounding of Objects from Natural Language Queries
Figure 4 for Zero-Shot Grounding of Objects from Natural Language Queries
* ICCV19 oral, camera-ready version 
  Access Paper or Ask Questions

Cascaded Parallel Filtering for Memory-Efficient Image-Based Localization


Aug 16, 2019
Wentao Cheng, Weisi Lin, Kan Chen, Xinfeng Zhang

Figure 1 for Cascaded Parallel Filtering for Memory-Efficient Image-Based Localization
Figure 2 for Cascaded Parallel Filtering for Memory-Efficient Image-Based Localization
Figure 3 for Cascaded Parallel Filtering for Memory-Efficient Image-Based Localization
Figure 4 for Cascaded Parallel Filtering for Memory-Efficient Image-Based Localization
* Accepted at ICCV 2019 
  Access Paper or Ask Questions

Billion-scale semi-supervised learning for image classification


May 02, 2019
I. Zeki Yalniz, Hervé Jégou, Kan Chen, Manohar Paluri, Dhruv Mahajan

Figure 1 for Billion-scale semi-supervised learning for image classification
Figure 2 for Billion-scale semi-supervised learning for image classification
Figure 3 for Billion-scale semi-supervised learning for image classification
Figure 4 for Billion-scale semi-supervised learning for image classification

  Access Paper or Ask Questions

MAC: Mining Activity Concepts for Language-based Temporal Localization


Nov 21, 2018
Runzhou Ge, Jiyang Gao, Kan Chen, Ram Nevatia

Figure 1 for MAC: Mining Activity Concepts for Language-based Temporal Localization
Figure 2 for MAC: Mining Activity Concepts for Language-based Temporal Localization
Figure 3 for MAC: Mining Activity Concepts for Language-based Temporal Localization
Figure 4 for MAC: Mining Activity Concepts for Language-based Temporal Localization
* WACV 2019 
  Access Paper or Ask Questions

CTAP: Complementary Temporal Action Proposal Generation


Jul 18, 2018
Jiyang Gao, Kan Chen, Ram Nevatia

Figure 1 for CTAP: Complementary Temporal Action Proposal Generation
Figure 2 for CTAP: Complementary Temporal Action Proposal Generation
Figure 3 for CTAP: Complementary Temporal Action Proposal Generation
Figure 4 for CTAP: Complementary Temporal Action Proposal Generation
* ECCV 2018 main conference paper (camera ready version). Code is available in http://www.github.com/jiyanggao/CTAP 
  Access Paper or Ask Questions

Motion-Appearance Co-Memory Networks for Video Question Answering


Mar 29, 2018
Jiyang Gao, Runzhou Ge, Kan Chen, Ram Nevatia

Figure 1 for Motion-Appearance Co-Memory Networks for Video Question Answering
Figure 2 for Motion-Appearance Co-Memory Networks for Video Question Answering
Figure 3 for Motion-Appearance Co-Memory Networks for Video Question Answering
Figure 4 for Motion-Appearance Co-Memory Networks for Video Question Answering
* CVPR 2018 
  Access Paper or Ask Questions

Knowledge Aided Consistency for Weakly Supervised Phrase Grounding


Mar 11, 2018
Kan Chen, Jiyang Gao, Ram Nevatia

Figure 1 for Knowledge Aided Consistency for Weakly Supervised Phrase Grounding
Figure 2 for Knowledge Aided Consistency for Weakly Supervised Phrase Grounding
Figure 3 for Knowledge Aided Consistency for Weakly Supervised Phrase Grounding
Figure 4 for Knowledge Aided Consistency for Weakly Supervised Phrase Grounding
* CVPR 2018 conference paper 
  Access Paper or Ask Questions

Query-guided Regression Network with Context Policy for Phrase Grounding


Aug 04, 2017
Kan Chen, Rama Kovvuri, Ram Nevatia

Figure 1 for Query-guided Regression Network with Context Policy for Phrase Grounding
Figure 2 for Query-guided Regression Network with Context Policy for Phrase Grounding
Figure 3 for Query-guided Regression Network with Context Policy for Phrase Grounding
Figure 4 for Query-guided Regression Network with Context Policy for Phrase Grounding
* Spotlight in ICCV 2017 
  Access Paper or Ask Questions

TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals


Aug 04, 2017
Jiyang Gao, Zhenheng Yang, Chen Sun, Kan Chen, Ram Nevatia

Figure 1 for TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals
Figure 2 for TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals
Figure 3 for TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals
Figure 4 for TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals
* ICCV 2017 camera ready 
  Access Paper or Ask Questions

AMC: Attention guided Multi-modal Correlation Learning for Image Search


Apr 03, 2017
Kan Chen, Trung Bui, Fang Chen, Zhaowen Wang, Ram Nevatia

Figure 1 for AMC: Attention guided Multi-modal Correlation Learning for Image Search
Figure 2 for AMC: Attention guided Multi-modal Correlation Learning for Image Search
Figure 3 for AMC: Attention guided Multi-modal Correlation Learning for Image Search
Figure 4 for AMC: Attention guided Multi-modal Correlation Learning for Image Search
* CVPR 2017 
  Access Paper or Ask Questions

Knowledge Graph Representation with Jointly Structural and Textual Encoding


Dec 13, 2016
Jiacheng Xu, Kan Chen, Xipeng Qiu, Xuanjing Huang

Figure 1 for Knowledge Graph Representation with Jointly Structural and Textual Encoding
Figure 2 for Knowledge Graph Representation with Jointly Structural and Textual Encoding
Figure 3 for Knowledge Graph Representation with Jointly Structural and Textual Encoding
Figure 4 for Knowledge Graph Representation with Jointly Structural and Textual Encoding

  Access Paper or Ask Questions

Learning Word Embeddings from Intrinsic and Extrinsic Views


Aug 20, 2016
Jifan Chen, Kan Chen, Xipeng Qiu, Qi Zhang, Xuanjing Huang, Zheng Zhang


  Access Paper or Ask Questions

ABC-CNN: An Attention Based Convolutional Neural Network for Visual Question Answering


Apr 03, 2016
Kan Chen, Jiang Wang, Liang-Chieh Chen, Haoyuan Gao, Wei Xu, Ram Nevatia

Figure 1 for ABC-CNN: An Attention Based Convolutional Neural Network for Visual Question Answering
Figure 2 for ABC-CNN: An Attention Based Convolutional Neural Network for Visual Question Answering
Figure 3 for ABC-CNN: An Attention Based Convolutional Neural Network for Visual Question Answering
Figure 4 for ABC-CNN: An Attention Based Convolutional Neural Network for Visual Question Answering

  Access Paper or Ask Questions