jizhong@tju.edu.cn
信息与通信系统
天津大学“北洋****-青年骨干教师”
副教授
面向网络的多视频摘要核心技术研究

---

基于移动平台的手势识别技术

---

鲁棒的人体检测和手指技术

---

深度视觉零样本学习关键技术研究

---

基于排序信息和排序学习的维数约简

---

面向无人驾驶汽车的恶劣天气环境下视觉计算技术

---

面向网络多视频摘要的关联学习关键技术研究

---

面向多媒体排序学习的维数约简
一种用于图像或视频搜索重排序的方法

---

一种用于零样本分类的多改进的典型相关分析模态典型相关分析的方法

---

基于逆向k近邻的图像搜索中高质量相关样本自动选取法

---

基于Fisher准则的嵌入流形回归模型

---

一种基于内容的图像伪相关重排序方法

---

基于相关保持映射和一分类器的图像视频搜索排序系统

---

加入皮尔逊相关系数的局部保持投影方法

---

一种基于超图的视频镜头边界检测方法

---

一种视频关键帧选取方法

---

基于多组间因子分析的零样本图像分类方法

---

一种用于零样本分类的多模态典型相关分析的方法

---

基于局部保持典型相关分析的零样本视频分类技术

---

一种新的域自适应学习方法

---

一种基于多模态字典学习的零样本分类方法

---

基于噪点先验约束的全变分图像去噪

---

一种基于自编码器词袋的视觉特征表示方法
一种用于图像或视频搜索重排序的方法

---

1

---

基于逆向k近邻的图像搜索中高质量相关样本自动选取法

---

基于Fisher准则的嵌入流形回归模型

---

一种基于内容的图像伪相关重排序方法

---

基于相关保持映射和一分类器的图像视频搜索排序系统

---

加入皮尔逊相关系数的局部保持投影方法

---

一种基于超图的视频镜头边界检测方法

---

一种视频关键帧选取方法

---

基于多组间因子分析的零样本图像分类方法20**

---

一种用于零样本分类的多模态典型相关分析的方法

---

1

---

1

---

20**

---

1

---

一种基于自编码器词袋的视觉特征表示方法
Deep pedestrian attribute recognition based on LSTM

---

Dual-Path in Dual-Path Network for Single Image Dehazing

---

Small and Dense Commodity Object Detection with Multi-Receptive Field Attention

---

Stacked Semantics-Guided Attention Model for Fine-Grained Zero-Shot Learning

---

Saliency-Guided Attention Network for Image-Sentence Matching

---

, Multi-Video Summarization with Query-Dependent Weighted Archetypal Analysis

---

Query-Aware Sparse Coding for Multi-Video Summarization

---

Image-Attribute Reciprocally Guided Attention Network for Pedestrian Attribute Recognition

---

Manifold Embedding for Zero-Shot Recognition

---

零样本图像分类综述:十年进展

---

Query-Aware Sparse Coding for Multi-Video Summarization, Information Sciences

---

Class-Specific Synthesized Dictionary Model for Zero-Shot Learning

---

Transductive Zero-Shot Learning with Adaptive Structural Embedding

---

Transductive Zero-Shot Learning with a Self-Training Dictionary Approach

---

Semantic softmax loss for zero-shot learning

---

Hypergraph Dominant Set Based Multi-Video Summarization

---

Zero-Shot Learning via Latent Space Encoding

---

Fusion-Attention Network for Person Search with Free-Form Natural Language

---

Zero-Shot Learning with Multi-Battery Factor Analysis

---

一种基于直推判别字典学习的零样本分类方法

---

Manifold regularized cross-modal embedding for zero-shot learning

---

基于超图排序算法的视频摘要

---

Relevance and Irrelevance Graphs Based Marginal Fisher Analysis for Image Search Reranking

---

Relevance Preserving Projection and Ranking for Web Image Search Reranking

---

基于抗噪声局部二值模式的纹理图像分类

---

Zero-Shot Learning with Regularized Cross-Modality Ranking

---

Image Search Reranking with Semi-supervised LPP and RankingSVM

---

Semi-supervised LPP Algorithms for Learning-to-Rank-Based Visual Search Reranking

---

Ranking Graph Embedding for Learning to Rerank

---

Ranking Fisher Discriminant Analysis

---

Balance between Object and Background: Object Enhanced Features for Scene Image Classification

---

Manifold regularized cross-modal embedding for zero-shot learning

---

Rank canonical correlation analysis and its application in visual search reranking