Filters








4,770 Hits in 5.3 sec

Incorporating Vision Bias into Click Models for Image-oriented Search Engine [article]

Ningxin Xu, Cheng Yang, Yixin Zhu, Xiaowei Hu, Changhu Wang
2021 arXiv   pre-print
In this paper, we assume that vision bias exists in an image-oriented search engine as another crucial factor affecting the examination probability aside from position.  ...  Empirically, we evaluate our model on a dataset developed from a real-world online image-oriented search engine, and demonstrate that our proposed model can achieve significant improvements over its baseline  ...  Click models which adopt the vision bias can estimate more unbiased relevance in image-oriented search engines.  ... 
arXiv:2101.02459v1 fatcat:hjqgwgzxvfcjdhdzwyoe6bdvte

Predicting Search User Examination with Visual Saliency

Yiqun Liu, Zeyang Liu, Ke Zhou, Meng Wang, Huanbo Luan, Chao Wang, Min Zhang, Shaoping Ma
2016 Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval - SIGIR '16  
With more and more heterogeneous components federated into search engine result pages (SERPs), it becomes difficult for traditional position-based models to accurately predict users' actual examination  ...  With an experimental search engine, we carefully design a user study in which users' examination behavior (eye movement) is recorded.  ...  They incorporated mouse hover and scroll information as additional signals into click models to improve click prediction performance and gain promising results [20] . Guo et al.  ... 
doi:10.1145/2911451.2911517 dblp:conf/sigir/LiuLZWLWZM16 fatcat:6t6zqhf6sbd3tcmsrcq4kayxcq

VisualRank: Applying PageRank to Large-Scale Image Search

Yushi Jing, S. Baluja
2008 IEEE Transactions on Pattern Analysis and Machine Intelligence  
search engines.  ...  Because of the relative ease in understanding and processing text, commercial image-search systems often rely on techniques that are largely indistinguishable from text search.  ...  Rehg, Henry Rowley, Michele Covell, and Dennis Strelow for the fruitful discussions on local features and graph analysis algorithms and Mithun Gupta for his help in implementing LSH.  ... 
doi:10.1109/tpami.2008.121 pmid:18787237 fatcat:5keoiqxihzambmtos7spj2y47u

When relevance is not Enough: Promoting Visual Attractiveness for Fashion E-commerce [article]

Wei Di, Anurag Bhardwaj, Vignesh Jagadeesh, Robinson Piramuthu, Elizabeth Churchill
2014 arXiv   pre-print
We show quantitative improvement by promoting visual attractiveness into search on top of relevance.  ...  A visual attractiveness based re-ranking model that incorporates both presentation efficacy and user preference is proposed.  ...  We show quantitatively that by incorporating attractiveness element into search engine, in the form of re-ranking, we can promoting better user engagement on top of relevance.  ... 
arXiv:1406.3561v1 fatcat:4tc6qy2gvbd73gbfjo5ecaqi7a

Measuring and Improving User Experience Through Artificial Intelligence-Aided Design

Bin Yang, Long Wei, Zihan Pu
2020 Frontiers in Psychology  
These projected pages consist of the click information of all users in the process of completing a certain task.  ...  The goal of the proposed methodology is to make the deep neural network model simulate the user's experience in the process of operating a mobile application as much as possible.  ...  This model is a general personalization framework, which can be incorporated into the click model.  ... 
doi:10.3389/fpsyg.2020.595374 pmid:33329260 pmcid:PMC7710987 fatcat:2ycxnlieovfv7bav2vf7fguziy

The impact of images on user clicks in product search

Sung H. Chung, Anjan Goswami, Honglak Lee, Junling Hu
2012 Proceedings of the Twelfth International Workshop on Multimedia Data Mining - MDMKDD '12  
In this paper, we propose adding information extracted from the thumbnail image of the item as additional features for click prediction.  ...  Product search engine faces unique challenges that differ from web page search. The goal of a product search engine is to rank relevant items that the user may be interested in purchasing.  ...  This paper tries to introduce image factors into click prediction model for product search.  ... 
doi:10.1145/2343862.2343866 fatcat:uertnscg6fhjhmlwo577fcnwi4

Multi-Modal Generative Adversarial Network for Short Product Title Generation in Mobile E-Commerce [article]

Jian-Guo Zhang, Pengcheng Zou, Zhao Li, Yao Wan, Xiuming Pan, Yu Gong, Philip S. Yu
2019 arXiv   pre-print
Moreover, we deploy our model into a real-world online E-Commerce environment and effectively boost the performance of click through rate and click conversion rate by 1.66% and 1.87%, respectively.  ...  In this paper, we propose a Multi-Modal Generative Adversarial Network (MM-GAN) for short product title generation in E-Commerce, which innovatively incorporates image information and attribute tags from  ...  As we mentioned be- fore, our model tries to incorporate multiple modalities of a product (i.e., product image, attribute tags and long title).  ... 
arXiv:1904.01735v1 fatcat:cncharlchjaozcosktftf2d7aa

Multi-Modal Generative Adversarial Network for Short Product Title Generation in Mobile E-Commerce

Jianguo Zhang, Pengcheng Zou, Zhao Li, Yao Wan, Xiuming Pan, Yu Gong, Philip S. Yu
2019 Proceedings of the 2019 Conference of the North  
Moreover, we deploy our model into a real-world online E-Commerce environment and effectively boost the performance of click through rate and click conversion rate by 1.66% and 1.87%, respectively.  ...  In this paper, we propose a Multi-Modal Generative Adversarial Network (MM-GAN) for short product title generation in E-Commerce, which innovatively incorporates image information and attribute tags from  ...  As we mentioned be- fore, our model tries to incorporate multiple modalities of a product (i.e., product image, attribute tags and long title).  ... 
doi:10.18653/v1/n19-2009 dblp:conf/naacl/ZhangZLWPGY19 fatcat:ecjx3ohbkjfrlfxtipuagk6c7q

Cross-Media Similarity Evaluation for Web Image Retrieval in the Wild [article]

Jianfeng Dong, Xirong Li, Duanqing Xu
2018 arXiv   pre-print
Such a connection reveals that the success of the state-of-the-art is mainly attributed to their good performance on visual-oriented queries, while these queries account for only a small part of real-user  ...  Given baseline methods that compute cross-media similarity using relatively simple text/image matching, how much progress have advanced models made is also unclear.  ...  Yuxiao Hu) for evaluating our results on IRC-MM15-test. The authors also thank the anonymous reviewers for their insightful comments.  ... 
arXiv:1709.01305v2 fatcat:adfiz723k5d7vopelt2l7vriri

Personalized online document, image and video recommendation via commodity eye-tracking

Songhua Xu, Hao Jiang, Francis C.M. Lau
2008 Proceedings of the 2008 ACM conference on Recommender systems - RecSys '08  
The recommendation results produced by our algorithm are evaluated by comparing with those manually labeled by users as well as by commercial search engines including Google (Web) Search, Google Image  ...  We propose a new recommendation algorithm for online documents, images and videos, which is personalized.  ...  Acknowledgements We thank Tao Jin for helping us in some of the experiments.  ... 
doi:10.1145/1454008.1454023 dblp:conf/recsys/XuJL08 fatcat:weqz6xqvgfhpnghbahk6pmanri

Software design for an autonomous ground vehicle for the 13thAnnual Intelligent Ground Vehicle Competition

Tim Roberts, Daniel Barber, Brian C. Becker, Fernando Gonzalez, David P. Casasent, Ernest L. Hall, Juha Röning
2005 Intelligent Robots and Computer Vision XXIII: Algorithms, Techniques, and Active Vision  
A combination of various image enhancing filters and the color classifier allow for the isolation of possible obstacles within the image.  ...  After filtering the image for areas of high brightness and contrast, the line finder performs a Hough Transform to find lines in the image.  ...  Discover Vision Figure 2: Discover Vision GUI The Discover Vision Engine is modeled after existing tools such as MatLab, except aiming to present an interface capable of easily manipulating images instead  ... 
doi:10.1117/12.630962 fatcat:uyheylzl3ffb3j5ga4fq5ldwte

What do saliency models predict?

K. Koehler, F. Guo, S. Zhang, M. P. Eckstein
2014 Journal of Vision  
All 800 images were processed by each of three saliency model toolboxes for MatLab. A saliency map  ...  The variability of observers' eye movements was modulated by the task (lowest for the object search task and greatest for the free viewing and saliency search tasks) as well as the clutter content of the  ...  Portions of this work were previously presented at the Vision Sciences Society Annual Meeting (Koehler et al., 2011) . Commercial relationships: none.  ... 
doi:10.1167/14.3.14 pmid:24618107 pmcid:PMC3954044 fatcat:fyuctfvmqzcfznd3tp2eaboyqu

Personalized News Recommendation: Methods and Challenges [article]

Chuhan Wu, Fangzhao Wu, Yongfeng Huang, Xing Xie
2022 arXiv   pre-print
Next, we introduce the public datasets and evaluation methods for personalized news recommendation.  ...  We first review the techniques for tackling each core problem in a personalized news recommender system and the challenges they face.  ...  Moreover, several methods incorporate user behaviors on other platforms, such as social media, search engines and e-commerce platforms.  ... 
arXiv:2106.08934v3 fatcat:iagqsw73hrehxaxpvpydvtr26m

Bottom-up Attention, Models of [article]

Ali Borji, Hamed R. Tavakoli, Zoya Bylinskii
2019 arXiv   pre-print
In spite of tremendous efforts and huge progress, there is still room for improvement in terms finer-grained analysis of deep saliency models, evaluation measures, datasets, annotation methods, cognitive  ...  In this review, we examine the recent progress in saliency prediction and proposed several avenues for future research.  ...  Images in this dataset come from search engines and computer vision datasets. The training set contains 100 images per category and has fixation annotations from 18 different observers.  ... 
arXiv:1810.05680v3 fatcat:yurrgypswnbt5kyxnxugivdwiq

Inferring Searcher Attention by Jointly Modeling User Interactions and Content Salience

Dmitry Lagun, Eugene Agichtein
2015 Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval - SIGIR '15  
Modeling and predicting user attention is crucial for interpreting search behavior.  ...  Grounding the observed interactions to the underlying page content provides a general and robust approach to user attention modeling, which could enable more powerful tools for search behavior interpretation  ...  Furthermore, as search engines increasingly incorporate images and other visually attractive elements into the search result, models of searcher attention have to be revisited accordingly.  ... 
doi:10.1145/2766462.2767745 dblp:conf/sigir/LagunA15 fatcat:d5qqtmfssnb5jitsw6h4dkxkya
« Previous Showing results 1 — 15 out of 4,770 results