Deep Cross-Modal Hashing

Slides:



Advertisements
Similar presentations
Aggregating local image descriptors into compact codes
Advertisements

Computer Science and Engineering Inverted Linear Quadtree: Efficient Top K Spatial Keyword Search Chengyuan Zhang 1,Ying Zhang 1,Wenjie Zhang 1, Xuemin.
Query Specific Fusion for Image Retrieval
Presented by Relja Arandjelović Iterative Quantization: A Procrustean Approach to Learning Binary Codes University of Oxford 21 st September 2011 Yunchao.
Complex Networks for Representation and Characterization of Object For CS790g Project Bingdong Li 11/9/2009.
Li-Jia Li Yongwhan Lim Li Fei-Fei Chong Wang David M. Blei B UILDING AND U SING A S EMANTIVISUAL I MAGE H IERARCHY CVPR, 2010.
1 Statistical correlation analysis in image retrieval Reporter : Erica Li 2004/9/30.
1 Jun Wang, 2 Sanjiv Kumar, and 1 Shih-Fu Chang 1 Columbia University, New York, USA 2 Google Research, New York, USA Sequential Projection Learning for.
A novel log-based relevance feedback technique in content- based image retrieval Reporter: Francis 2005/6/2.
Botanical treesBlood/Lungs systemsRiver basins Valleys on MarsSnowflakesNeurons.
An Investigation into the Relationship between Semantic and Content Based Similarity Using LIDC Grace Dasovich Robert Kim Midterm Presentation August 21.
J Cheng et al,. CVPR14 Hyunchul Yang( 양현철 )
Efficient Image Search and Retrieval using Compact Binary Codes
Fast vector quantization image coding by mean value predictive algorithm Authors: Yung-Gi Wu, Kuo-Lun Fan Source: Journal of Electronic Imaging 13(2),
Utilising software to enhance your research Eamonn Hynes 5 th November, 2012.
School of Information Technology & Electrical Engineering Multiple Feature Hashing for Real-time Large Scale Near-duplicate Video Retrieval Jingkuan Song*,
An Example of Course Project Face Identification.
Xiaoying Gao Computer Science Victoria University of Wellington Intelligent Agents COMP 423.
Thanks to Bill Arms, Marti Hearst Documents. Last time Size of information –Continues to grow IR an old field, goes back to the ‘40s IR iterative process.
Minimal Loss Hashing for Compact Binary Codes
Deep Learning Powered In- Session Contextual Ranking using Clickthrough Data Xiujun Li 1, Chenlei Guo 2, Wei Chu 2, Ye-Yi Wang 2, Jude Shavlik 1 1 University.
Clustering More than Two Million Biomedical Publications Comparing the Accuracies of Nine Text-Based Similarity Approaches Boyack et al. (2011). PLoS ONE.
Unsupervised Auxiliary Visual Words Discovery for Large-Scale Image Object Retrieval Yin-Hsi Kuo1,2, Hsuan-Tien Lin 1, Wen-Huang Cheng 2, Yi-Hsuan Yang.
Detecting Remote Evolutionary Relationships among Proteins by Large-Scale Semantic Embedding Xu Linhe 14S
Cross-modal Hashing Through Ranking Subspace Learning
Image Retrieval and Ranking using L.S.I and Cross View Learning Sumit Kumar Vivek Gupta
Naifan Zhuang, Jun Ye, Kien A. Hua
Big data classification using neural network
Unsupervised Learning of Video Representations using LSTMs
CNN-RNN: A Unified Framework for Multi-label Image Classification
Learning to Compare Image Patches via Convolutional Neural Networks
Linguistic Graph Similarity for News Sentence Searching
Applying Deep Neural Network to Enhance EMPI Searching
Multiple Feature Hashing for Real-time Large Scale
An Image Database Retrieval Scheme Based Upon Multivariate Analysis and Data Mining Presented by C.C. Chang Dept. of Computer Science and Information.
Deep learning David Kauchak CS158 – Fall 2016.
DeepFont: Identify Your Font from An Image
Deep Compositional Cross-modal Learning to Rank via Local-Global Alignment Xinyang Jiang, Fei Wu, Xi Li, Zhou Zhao, Weiming Lu, Siliang Tang, Yueting.
Saliency-guided Video Classification via Adaptively weighted learning
Regularizing Face Verification Nets To Discrete-Valued Pain Regression
Data Mining 101 with Scikit-Learn
Personalized Social Image Recommendation
Multimodal Learning with Deep Boltzmann Machines
Presenter: Chu-Song Chen
ECE533 – Image Processing Project Face Recognition Techniques
Unsupervised Learning and Autoencoders
State-of-the-art face recognition systems
Zan Gao, Deyu Wang, Xiangnan He, Hua Zhang
Thanks to Bill Arms, Marti Hearst
Ganapathy Mani, Bharat Bhargava, Jason Kobes*
Lei Sha, Jing Liu, Chin-Yew Lin, Sujian Li, Baobao Chang, Zhifang Sui
Progressive Cross-media Correlation Learning
Design of Hierarchical Classifiers for Efficient and Accurate Pattern Classification M N S S K Pavan Kumar Advisor : Dr. C. V. Jawahar.
Deep Visual-Semantic Alignments for Generating Image Descriptions
MEgo2Vec: Embedding Matched Ego Networks for User Alignment Across Social Networks Jing Zhang+, Bo Chen+, Xianming Wang+, Fengmei Jin+, Hong Chen+, Cuiping.
Papers 15/08.
Deep Cross-media Knowledge Transfer
Deep Robust Unsupervised Multi-Modal Network
Using Multilingual Neural Re-ranking Models for Low Resource Target Languages in Cross-lingual Document Detection Using Multilingual Neural Re-ranking.
Heterogeneous convolutional neural networks for visual recognition
Topological Signatures For Fast Mobility Analysis
Philosophy What is it? What is it not?.
Wellington Cabrera Advisor: Carlos Ordonez
Domingo Mery Department of Computer Science
Deep Object Co-Segmentation
FashionBrain Research and Technology
Topic: Semantic Text Mining
Multi-Modal Multi-Scale Deep Learning for Large-Scale Image Annotation
Weekly Learning Alex Omar Ruiz Irene.
Week 7 Presentation Ngoc Ta Aidean Sharghi
Presentation transcript:

Deep Cross-Modal Hashing Qing-Yuan Jiang Wu-Jun Li Presented by Zi-Fan Shi

Multi-Modal Data In reality, data can have multi-modalities – Images, Textual tags…

Cross-Modal Similarity Search – Query: from one modality – Database: from another modality

Cross-Modal Hashing Learn compact representations that preserve cross-modal similarity Existing methods (hand-crafted based methods): – Cross view hashing (CVH) – Semantic correlation maximization (SCM) – Collective matrix factorization hashing (CMFH) – Semantics-preserving hashing (SePH)

Cross-Modal Hashing X Image 𝑥 𝑖 -1 -1 -1 1 Y 𝑦 1 Husky British Shorthair -1 -1 -1 1 1 1 -1 -1 𝑦 2 Text … … … 𝑦 𝑛−1 Pomeranian American Shorthair -1 -1 1 -1 1 1 1 -1 𝑦 𝑛

Cross-Modal Hashing Distance - Hamming Distance - Euclidean Distance …… Ranking 𝑏 𝑖 (𝑥) → 𝑏 𝑗1 (𝑦) , ……, 𝑏 𝑗𝑛 (𝑦) Two Functions ℎ 𝑥 𝑥 𝑖 → {+1,−1} 𝑐 ℎ 𝑦 𝑦 𝑖 → {+1,−1} 𝑐

Deep Learning for Hashing Deep hashing – An end-to-end way Existing methods – Deep hashing network(DHN) – Deep pairwise-supervised hashing (DPSH) We propose deep cross-modal hashing

Deep Cross-Modal Hashing

Feature learning part Two neural networks for image and text modality Image modality – First seven layers: VGG-F structure – Eight layer: Hash code layer Text modality – First layer: Full connected layer – Second layer: Hash code layer

Deep Cross-Modal Hashing

Hash code learning part

Hash code learning part

Hash code learning part

Hash code learning part

Hash code learning part

Learning

Algorithm

Generate hash codes 𝒃 𝑝 (𝑥) = ℎ 𝑥 𝒙 𝑝 =𝑠𝑖𝑔𝑛(𝑓( 𝒙 𝑝 ; 𝜃 𝑥 )) 𝒃 𝑝 (𝑥) = ℎ 𝑥 𝒙 𝑝 =𝑠𝑖𝑔𝑛(𝑓( 𝒙 𝑝 ; 𝜃 𝑥 )) 𝒃 𝑞 (𝑦) = ℎ 𝑦 𝒙 𝑞 =𝑠𝑖𝑔𝑛(𝑓( 𝒙 𝑞 ; 𝜃 𝑦 ))

Datasets and evaluation protocols

Hamming ranking

Hamming ranking

Hash lookup

Hash lookup

Effectiveness of feature learning

THANK YOU ~.~