General

蒋树强 男 博导
电子邮件:sqjiang@ict.ac.cn
联系电话:
通信地址:
邮政编码:

Introduction

He is a professor with the Institute of Computing Technology, Chinese Academy of Sciences(CAS), and a professor in University of CAS. He is also with the Key Laboratory of Intelligent Information Processing, CAS. His research interests include multimedia content analysis and retrieval, image/video understanding, and multimodal intelligence. He has authored or coauthored more than 200 papers. He was supported by National Science Fund for Distinguished Young Scholars in 2021, NSFC Excellent Young Scientists Fund in 2013, Young top-notch talent of Ten Thousand Talent Program in 2014. He is the senior member of IEEE and CCF, member of ACM, Associate Editor of IEEE Multimedia, Multimedia Tools and Applications. He is the vice chair of IEEE CASS Beijing Chapter and vice chair of ACM SIGMM China chapter.


News

  • The paper “GridMM: Grid Memory Map for Vision-and-Language Navigation”have been accepted by ICCV2023(2023-07-14)

  • ​The paper“MemBridge: Video-Language Pre-training with Memory-Augmented Inter-Modality Bridge”has been accepted by IEEE Transactions on Image Processing(2023-05-23)
  • The paper“Vision-Based Fruit Recognition via Multi-Scale Attention CNN”has been accepted by Computers and Electronics in Agriculture(2023-05-05)
  • The paper“TransWeaver: Weave Image Pairs for Class Agnostic Common Object Detection”has been accepted by IEEE Transactions on Image Processing(2023-04-28)
  • The paper“Multi-Object Navigation using Potential Target Position Policy Function” has been accepted by IEEE Transactions on Image Processing(2023-02-28)
  • Four papers “Layout-based Causal Inference for Object Navigation”,“KERM: Knowledge Enhanced Reasoning for Vision-and-Language Navigation”,“Bi-level Meta-learning for Few-shot Domain Generalization”,“Data-Free Knowledge Distillation via Feature Exchange and Activation Region Constraint”have been accepted by CVPR2023(2023-02-28)
  • The paper “Large Scale Visual Food Recognition”has been accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence (2023-01-14)
  • The paper “Focus and Align: Learning Tube Tokens for Video-Language Pre-training”has been accepted by IEEE Transactions on Multimedia (2022-12-03)
  • The paper “Ingredient Prediction via Context Learning Network with Class-Adaptive Asymmetric Loss”has been accepted by IEEE Transactions on Image Processing (2022-07-10)
  • The paper “Generative Meta-Adversarial Network for Unseen Object Navigation” has been accepted by ECCV2022(2022-07-09)
  • Shuqiang Jiang was invited  to join Editorial Board of Journal of Computer Researach and Development《计算机研究与发展》 for the four-year term from  July 2022 to June 2026.(2022-06-30)
  • Shuqiang Jiang was invited  to join Editorial Board of Journal of Computer Science and Technology for the four-year term from  July 2022 to June 2026.(2022-06-27)
  • The paper "Applications of Knowledge Graphs for the Food Science and Industry" has been accepted by Patterns (Cell Press). (2022-03-08)
  • The paper "Dataset Bias in Few-shot Image Recognition" has been accepted by IEEE TPAMI. (2022-02-16)
  • The paper "Evaluation of Deep Learning-Based Automated Detection of Primary Spine Tumors on MRI Using the Turing Test" has been accepted by Frontiers in Oncology (IF: 6.244). (2022-02-16)
  • The paper "A Review on Vision-based Analysis for Automatic Dietary Assessment" has been accepted by Trends in Food Science & Technology (IF: 12.563). (2022-02-12)
  • The paper "Rethinking the Optimization of Average Precision: Only Penalizing Negative Instances before Positive Ones is Enough" has been accepted by AAAI 2022. (2021-12-01)
  • The workshop “LargeFineFoodAI: Large-Scale Fine-Grained Food AnalysIs“ has been held in conjunction with ICCV 2021. (2021-10-16)
  • The paper "See More for Scene: Pairwise Consistency Learning for Scene Classification" has been accepted by NeurIPS 2021.(2021-09-29)
  • The paper "Hierarchical Object-to-Zone Graph for Object Navigation" has been accepted by ICCV 2021.(2021-07-23)
  • The paper "ION: Instance-level Object Navigation" has been accepted by ACM Multimedia 2021.(2021-07-04)
  • The paper "FoodLogoDet-1500: A Dataset for Large-Scale Food Logo Detection via Multi-Scale Feature Decoupling Network" has been accepted by ACM Multimedia 2021.(2021-07-04)
  • The team won the championship of CVPR 2021 Embodied AI Workshop AI2-THOR ObjectNav Challenge.  (2021-06-21)
  • The paper "What If We Could Not See? Counterfactual Analysis for Egocentric Action Anticipation" has been accepted by IJCAI 2021.(2021-04-29)
  • The paper "Plant Disease Recognition: A Large-Scale Benchmark Dataset and a Visual Region and Loss Reweighting Approach" has been accepted by IEEE Trans. on Image Processing(2020-12-29)
  • The project "Image and Video Multi-scale representation and semantic mapping" (participated) won the first prize of the CAAI Wu Wenjun Artificial Intelligence Science and Technology Award. (2020-12-10)
  • The paper "Amorphous Region Context Modeling for Scene Recognition" has been accepted by IEEE Trans. on Multimedia(2020-12-07)
  • The project "Local associated analysis and expression of visual media" completed by Prof. Shuqiang Jiang's Group won the second prize of natural science. (2020-12-03)
  • Keynote Speech "Contextual Correlation Visual Media Understanding and Search" on the 16th International Conference on Advanced Data Mining and Applications (ADMA 2020).(2020-11-13)
  • 2019 FrontRunner 5000 Top Articles in Outstanding S&T Journals of China——the paper " Survey and Prospect of Intelligent Interaction-Oriented Image Recognition Techniques" (published on the Journal of Computer Research and Development, 2016)(2020-09-28)
  • The paper “Hybrid-Attention Enhanced Two-Stream Fusion Network for Video Venue Prediction”has been accepted by IEEE Trans. on Multimedia.(2020-08-11)
  • Four papers “ISIA Food-500: A dataset for Large-Scale Food Recognition via Stacked Global-Local Attention Network”, “Generalized Zero-shot Learning with Multi-source Semantic Embeddings for Scene Recognition”, “Expressional Region Retrieval” and “An Egocentric Action Anticipation Framework via Fusing Intuition and Analysis” have been accepted by ACM Multimedia 2020(2020-07-26)
  • The paper “Attribute-Guided Feature Learning for Few-Shot Image Recognition”has been accepted by IEEE Trans. on Multimedia.(2020-04-29)
  • The paper “Multi-attention Meta Learning for Few-shot Fine-grained Image Recognition”has been accepted by IJCAI.(2020-04-21)
  • The paper “Few-Shot Food Recognition via Multi-View Representation Learning”has been accepted by ACM Transactions on Multimedia Computing, Communications and Applications.(2020-03-28)
  • The paper “Scene Recognition with Prototype-agnostic Scene Layout”has been accepted by IEEE Transactions on Image Processing.(2020-03-28
  • The paper “A Two-Stage Triplet Network Training Framework for Image Retrieval”has been accepted by IEEE Trans. on Multimedia.(2020-02-11)
  • The paper “Food Recommendation: Framework, Existing Solutions and Challenges”has been accepted by IEEE Transactions on Multimedia.(2019-11-18)
  • The paper “Logo-2K+: A Large-Scale Logo Dataset for Scalable Logo Classification”has been accepted by AAAI 2020.(2019-11-11)
  • The paper “Learning Scene Attribute for Scene Recognition”has been accepted by IEEE Transactions on Multimedia.(2019-09-17)
  • The paper “Multi-Task Deep Relative Attribute Learning for Visual Urban Perception”has been accepted by IEEE Transactions on Image Processing.(2019-07-28)
  • The paper “Image Representations with Spatial Object-to-Object Relations for RGB-D Scene Recognition”has been accepted by IEEE Transactions on Image Processing.(2019-07-24)
  • The paper “Multi-Scale Multi-View Deep Feature Aggregation for Food Recognition”has been accepted by IEEE Transactions on Image Processing.(2019-07-11)
  • Four papers “Ingredient-Guided Cascaded Multi-Attention Network for Food Recognition”, “Aberrance-aware gradient-sensitive attentions for scene recognition with RGB-D videos”, “MUCH: MUtual Coupling enHancement of scene recognition and dense captioning” and “Attention-based Densely Connected LSTM for Video Captioning” have been accepted by ACM Multimedia 2019.(2019-07-03)
  • The paper “A Survey on Food Computing”has been accepted by ACM Computing Surveys.(2019-04-30)
  • The paper “Multifaceted Analysis of Fine-Tuning in Deep Model for Visual Recognition”has been accepted by ACM Transactions on Data Science.(2019-03-05)
  • The paper “Know More Say Less: Image Captioning Based on Scene Graphs”has been accepted by IEEE Transactions on Multimedia.(2019-01-02)
  • Shuqiang Jiang was invited to join Editorial Board of ACM TOMM journal as associate editor for the three-year term starting January 1st,2019 and ending December 31st,2021.(2019-01-01)
  • The paper “Class Agnostic Image Common Object Detection”has been accepted by IEEE Transactions on Image Processing.(2018-12-24)
  • The paper “Learning Object Context for Dense Captioning”has been accepted by AAAI2019.(2018-11-01)
  • The paper “Hierarchy-Dependent Cross-Platform Multi-View Feature Learning for Venue Category Prediction”has been accepted by IEEE Transactions on Multimedia.(2018-10-03)
  • The paper “Learning Effective RGB-D Representations for Scene Recognition”has been accepted by IEEE Transactions on Image Processing(TIP).(2018-09-24)
  • The paper “Attentive Recurrent Neural Network for Weak-supervised Multi-label Image Classification”has been accepted by ACM Multimedia2018.(2018-07-03)
  • The paper “Deep Patch Representations with Shared Codebook for Scene Classification”has been accepted by ACM Transactions on Multimedia Computing, Communications and Applications.(2018-06-10)
  • The paper “Bundled Object Context for Referring Expressions”has been accepted by IEEE Transactions on Multimedia.(2018-02-09)
  • The paper“Deep Structured Learning for Visual Relationship Detection”has been accepted by AAAI2018.(2017-11-09)
  • The paper “You Are What You Eat: Exploring Rich Recipe Information for Cross-Region Food Analysis”has been accepted by IEEE Transactions on Multimedia.(2017-09-04)
  • Two Papers“RGB-D Scene Recognition with Object-to-Object Relation”and “A Delicious Recipe Analysis Framework for Exploring Multi-Modal Recipes”have been accepted by ACM Multimedia Conference2017.(2017-07-03)
  • Two Papers“Dual Track Multimodal Automatic Learning through Human-Robot Interaction”and“Combining Models from Multiple Sources for RGB-D Scene Recognition”have been accepted by IJCAI2017.(2017-04-14)