Dhiraj Joshi, Ph.D.

Senior Research Scientist

Dhiraj Joshi

Dhiraj’s research interests include social media mining, crowd-sourced data mining and multimedia analysis. Before joining FXPAL, Dhiraj was a Scientist at Kodak Research Labs. Dhiraj received an Integrated M.Sc. (5 yr) in Mathematics and Scientific Computing from Indian Institute of Technology (IIT) Kanpur in 2002. He completed his Ph.D. in Computer Science and Engineering from Penn. State University in 2007.  At Penn State, he was a member of Intelligent Information Systems Research Lab and worked with Prof. James Z. Wang. He has been a research intern at the I.B.M. T.J. Watson Research Labs and the IDIAP Research Institute (Switzerland). In 2006, he was selected as an Emerging Leader in Multimedia Research to present at the Watson Emerging Leaders in Multimedia Workshop. He actively participates as a technical program committee member/reviewer of leading international conferences and journals and served as the Chair/Vice-Chair of IEEE Signal Processing Society Rochester Chapter from 2009 to 2012.

See Dhiraj’s personal homepage for more details and a full list of publications.

Co-Authors

Publications

2016
Publication Details
  • ICME 2016
  • Jul 11, 2016

Abstract

Close
Captions are a central component in image posts that communicate the background story behind photos. Captions can enhance the engagement with audiences and are therefore critical to campaigns or advertisement. Previous studies in image captioning either rely solely on image content or summarize multiple web documents related to image's location; both neglect users' activities. We propose business-aware latent topics as a new contextual cue for image captioning that represent user activities. The idea is to learn the typical activities of people who posted images from business venues with similar categories (e.g., fast food restaurants) to provide appropriate context for similar topics (e.g., burger) in new posts. User activities are modeled via a latent topic representation. In turn, the image captioning model can generate sentences that better reflect user activities at business venues. In our experiments, the business-aware latent topics are effective for adapting to captions to images captured in various businesses than the existing baselines. Moreover, they complement other contextual cues (image, time) in a multi-modal framework.

Social Media-Based Profiling of Business Locations

Publication Details
  • Fuji Xerox Technical Report
  • Mar 17, 2016

Abstract

Close
We present a method for profiling businesses at specific locations that is based on mining information from social media. The method matches geo-tagged tweets from Twitter against venues from Foursquare to identify the specific business mentioned in a tweet. By linking geo-coordinates to places, the tweets associated with a business, such as a store, can then be used to profile that business. From these venue-located tweets, we create sentiment profiles for each of the stores in a chain. We present the results as heat maps showing how sentiment differs across stores in the same chain and how some chains have more positive sentiment than other chains. We also estimate social group size from photos and create profiles of social group size for businesses. Sample heat maps of these results illustrate how the average social group size can vary across businesses.
Publication Details
  • AAAI
  • Feb 12, 2016

Abstract

Close
Image localization is important for marketing and recommendation of local business; however, the level of granularity is still a critical issue. Given a consumer photo and its rough GPS information, we are interested in extracting the fine-grained location information (i.e. business venues) of the image. To this end, we propose a novel framework for business venue recognition. The framework mainly contains three parts. First, business aware visual concept discovery: we mine a set of concepts that are useful for business venue recognition based on three guidelines including business-awareness, visually detectable, and discriminative power. Second, business-aware concept detection by convolutional neural networks (BA-CNN): we pro- pose a new network architecture that can extract semantic concept features from input image. Third, multimodal business venue recognition: we extend visually detected concepts to multimodal feature representations that allow a test image to be associated with business reviews and images from social media for business venue recognition. The experiments results show the visual concepts detected by BA-CNN can achieve up to 22.5% relative improvement for business venue recognition compared to the state-of-the-art convolutional neural network features. Experiments also show that by leveraging multimodal information from social media we can further boost the performance, especially in the case when the database images belonging to each business venue are scarce.
2015
Publication Details
  • MM Commons Workshop co-located with ACM Multimedia 2015.
  • Oct 30, 2015

Abstract

Close
In this paper, we analyze the association between a social media user's photo content and their interests. Visual content of photos is analyzed using state-of-the-art deep learning based automatic concept recognition. An aggregate visual concept signature is thereby computed for each user. User tags manually applied to their photos are also used to construct a tf-idf based signature per user. We also obtain social groups that users join to represent their social interests. In an effort to compare the visual-based versus tag-based user profiles with social interests, we compare corresponding similarity matrices with a reference similarity matrix based on users' group memberships. A random baseline is also included that groups users by random sampling while preserving the actual group sizes. A difference metric is proposed and it is shown that the combination of visual and text features better approximates the group-based similarity matrix than either modality individually. We also validate the visual analysis against the reference inter-user similarity using the Spearman rank correlation coefficient. Finally we cluster users by their visual signatures and rank clusters using a cluster uniqueness criteria.

Inferring Crowd-Sourced Venues for Tweets

Publication Details
  • IEEE BigData 2015
  • Oct 29, 2015

Abstract

Close
Knowing the geo-located venue of a tweet can facilitate better understanding of a user's geographic context, allowing apps to more precisely present information, recommend services, and target advertisements. However, due to privacy concerns, few users choose to enable geotagging of their tweets resulting in a small percentage of tweets being geotagged; furthermore, even if the geo-coordinates are available, the closest venue to the geo-location may be incorrect. In this paper, we present a method for providing a ranked list of geo-located venues for a non-geotagged tweet, which simultaneously indicates the venue name and the geo-location at a very fine-grained granularity. In our proposed method for Venue Inference for Tweets ({\VIT}), we construct a heterogeneous social network in order to analyze the embedded social relations, and leverage available but limited geographic data to estimate the geo-located venue of tweets. A single classifier is trained to predict the probability of a tweet and a geo-located venue being linked, rather than training a separate model for each venue. We examine the performance of four types of social relation features and three types of geographic features embedded in a social network when predicting whether a tweet and a venue are linked, with a best accuracy of over 88%. We use the classifier probability estimates to rank the predicted geo-located venues of a non-geotagged tweet from over 19k possibilities, and observed an average top-5 accuracy of 29%.
2014

Multi-modal Language Models for Lecture Video Retrieval

Publication Details
  • ACM Multimedia 2014
  • Nov 2, 2014

Abstract

Close
We propose Multi-modal Language Models (MLMs), which adapt latent variable models for text document analysis to modeling co-occurrence relationships in multi-modal data. In this paper, we focus on the application of MLMs to indexing slide and spoken text associated with lecture videos, and subsequently employ a multi-modal probabilistic ranking function for lecture video retrieval. The MLM achieves highly competitive results against well established retrieval methods such as the Vector Space Model and Probabilistic Latent Semantic Analysis. Retrieval performance with MLMs is also shown to improve with the quality of the available extracted spoken text.

Social Media-based Profiling of Store Locations

Publication Details
  • ACM Multimedia Workshop on Geotagging and Its Applications in Multimedia
  • Nov 2, 2014

Abstract

Close
We present a method for profiling businesses at specific locations that is based on mining information from social media. The method matches geo-tagged tweets from Twitter against venues from Foursquare to identify the specific business mentioned in a tweet. By linking geo-coordinates to places, the tweets associated with a business, such as a store, can then be used to profile that business. We used a sentiment estimator developed for tweets to create sentiment profiles of the stores in a chain, computing the average sentiment of tweets associated with each store. We present the results as heatmaps which show how sentiment differs across stores in the same chain and how some chains have more positive sentiment than other chains. We also created profiles of social group size for businesses and show sample heatmaps illustrating how the size of a social group can vary.

On Aesthetics and Emotions in Scene Images: A Computational Perspective.

Publication Details
  • Book: Scene Vision, MIT Press, (Editors Kestas Kveraga and Moshe Bar).
  • Nov 1, 2014

Abstract

Close
In this chapter, we discuss the problem of computational inference of aesthetics and emotions from images. We draw inspiration from diverse disciplines such as philosophy, photography, art, and psychology to define and understand the key concepts of aesthetics and emotions. We introduce the primary computational problems that the research community has been striving to solve and the computational framework required for solving them. We also describe datasets available for performing assessment and outline several real-world applications where research in this domain can be employed. This chapter discusses the contributions of a significant number of research articles that have attempted to solve problems in aesthetics and emotion inference in the last several years. We conclude the chapter with directions for future research. Here’s a link to the book.
http://mitpress.mit.edu/books/scene-vision
Publication Details
  • ACM SIGIR International Workshop on Social Media Retrieval and Analysis
  • Jul 11, 2014

Abstract

Close
We examine the use of clustering to identify selfies in a social media user's photos for use in estimating demographic information such as age, gender, and race. Faces are first detected within a user's photos followed by clustering using visual similarity. We define a cluster scoring scheme that uses a combination of within-cluster visual similarity and average face size in a cluster to rank potential selfie-clusters. Finally, we evaluate this ranking approach over a collection of Twitter users and discuss methods that can be used for improving performance in the future.
Publication Details
  • ACM ICMR 2014
  • Apr 1, 2014

Abstract

Close
Motivated by scalable partial-duplicate visual search, there has been growing interest on a wealth of compact and efficient binary feature descriptors (e.g. ORB, FREAK, BRISK). Typically, binary descriptors are clustered into codewords and quantized with Hamming distance, which follows conventional bag-of-words strategy. However, such codewords formulated in Hamming space did not present obvious indexing and search performance improvement as compared to the Euclidean ones. In this paper, without explicit codeword construction, we explore to utilize binary descriptors as direct codebook indices (addresses). We propose a novel approach to build multiple index tables which parallelly check the collision of same hash values. The evaluation is performed on two public image datasets: DupImage and Holidays. The experimental results demonstrate the index efficiency and retrieval accuracy of our approach.