Department of Computer Science & Engineering

&ldquo;IIT Jodhpur is committed to impart quality education to facilitate the creation of qualified, competent and responsible human resources to meet the emerging technological challenges of the world. It is working towards creating an equitable learning platform that is positive, accessible and effective in the face of the modern societal and scientific advancements.

Flexibility in curriculum, in all its academic programs, encompassing elements of teaching, research, creativity, innovation and entrepreneurship is the most unique feature of IIT Jodhpur. The Department of Science and Technology (DST), under the National Mission on Cyber Physical Systems, has identified IIT Jodhpur as a Technology &amp; Innovation Hub in the area of Augmented Reality and Virtual Reality. The institute has also been nominated as the coordinator for the Jodhpur City and Knowledge Cluster by the Office of Principal Scientific Adviser, Government of India.

The sprawling 852-acre IIT Jodhpur campus is a majestic tribute to the deep-rooted diverse cultural heritage of the region. The campus is an architectural masterpiece, which is slated to become an international exemplar of sustainability with net-zero energy, and advanced water and waste management strategies.&rdquo;

IIT Jodhpur

Signed network analysis being one of the greatest disruptive innovations within the last decade has assembled a vast amount of attention of the citizenry. The positions of the users of the signed networks are used by several societies in the world to see the mentality of the users, the current movement of the grocery store and many more things. But even so, in that location is a latent potential of social nets. Ace of the facial expressions that, we were able to determine was about seeing the relationship between the users (i.e., especially, the negative (i.e., −Ve) link in social networks) on the signed network using the stakes that the users work and the reaction of the other users towards it. The anticipation of a negative link (i.e., −Ve) can be applied in the information security field, to observe the aberrations in the largest social networks and further discover the malicious nodes in the larger social network; say, if two nodes are doing things together even though in that respect is no intercourse between them. It can likewise be utilized in improving the recommendation system in social networks as if there is some probability between the two the nodes of being an enemy or disliking each other then we can slay them from each other’s recommendation list or could assign a lesser weight to them in a recommended technique. To accomplish all this relationship between the nodes we first need to determine whether the user is posting posts with positive emotion (like happy, excited, etc.) or negative emotion (like angry, sad, and so on), and then that we can further examine the learning ability of the user and utilize it to recommend the people who we have previously separated with the similar personality. For that we have applied the sentiment analysis in social networks, which splits up the users into five simple categories: Highly Positive (i.e., Highly +Ve), Positive (i.e., +Ve), Neutral, Negative (i.e., −Ve) and Highly Negative (i.e., Highly −Ve). © 2018, Springer Science+Business Media, LLC, part of Springer Nature.

Wireless Personal Communications

Positive and Negative Link Prediction Algorithm Based on Sentiment Analysis in Large Social Networks

In this paper we study recently introduced conflict version of the classical Feedback Vertex Set (FVS) problem. For a family of graphs F, we consider the problem F-CF-Feedback Vertex Set (F-CF-FVS, for short). The F-CF-FVS problem takes as an input a graph G, a graph H ∈ F (where V (G) = V (H)), and an integer k, and the objective is to decide if there is a set S ⊆ V (G) of size at most k such that G − S is a forest and S is an independent set in H. Observe that if we instantiate F to be the family of edgeless graphs then we get the classical FVS problem. Jain, Kanesh, and Misra [CSR 2018] showed that in contrast to FVS, F-CF-FVS is W[1]-hard on general graphs and admits an FPT algorithm if F is the family of d-degenerate graphs. In this paper, we relate F-CF-FVS to the Independent Set problem on special classes of graphs, and obtain a complete dichotomy result on the Parameterized Complexity of the problem F-CF-FVS, when F is a hereditary graph family. In particular, we show that F-CF-FVS is FPT parameterized by the solution size if and only if F+Cluster IS is FPT parameterized by the solution size. Here, F+Cluster IS is the Independent Set problem in the (edge) union of a graph G ∈ F and a cluster graph H (G and H are explicitly given). Next, we exploit this characterization to obtain new FPT results as well as intractability results for F-CF-FVS. In particular, we give an FPT algorithm for F+Cluster IS when F is the family of Ki,j-free graphs. We show that for the family of bipartite graph B, B-CF-FVS is W[1]-hard, when parameterized by the solution size. Finally, we consider, for each 0 &lt; &lt; 1, the family of graphs F, which comprise of graphs G such that |E(G)| ≤ |V (G)|2−, and show that F-CF-FVS is W[1]-hard, when parameterized by the solution size, for every 0 &lt; &lt; 1. © Akanksha Agrawal, Pallavi Jain, Lawqueen Kanesh, Daniel Lokshtanov, and Saket Saurabh.

World University root node

Leibniz International Proceedings in Informatics, LIPIcs

Conflict free feedback vertex set: A parameterized dichotomy

As much as good representation and theory are needed to explain human actions, so are the action videos used for learning good segmentation techniques. To accurately model complex actions such as diving, figure skating, and yoga practices, videos depicting action by human experts are required. Lack of experts in any domain leads to reduced number of videos and hence an improper learning. In this work we attempt to utilize imperfect amateur performances to get more confident representations of human action sequences. We introduce a novel Community Detection based unsupervised framework that provides mechanisms to interpret video data and address its limitations to produce better action representation. Human actions are composed of distinguishable key poses which form dense communities in graph structures. Anomalous poses performed for a longer duration can also form such dense communities but can be identified based on their rare occurrence across action videos and be rejected. Further, we propose a technique to learn the temporal order of these key poses from these imperfect videos, where the inter community links help reduce the search space of many possible pose sequences. Our framework is seen to improve the segmentation performance of complex human actions with the help of some imperfect performances. The efficacy of our approach has been illustrated over two complex action datasets - Sun Salutation and Warm-up exercise, that have been developed using random executions from amateur performers. © 2018 ACM.

ACM International Conference Proceeding Series

Leveraging information from imperfect examples: Common action sequence mining from a mix of incorrect performances

In a multi-tenant cloud application, more than one heterogeneous tenants share the single instance of the application. It increases the degree of resource sharing among tenants and brings down the operational cost. In this work, we propose a methodological framework to manage the degree of tenancy for a microservice based multi-tenant cloud application. We also present a case study to show how microservices can be distributed among multiple tenants to increase the resource utilization and, at the same time meeting with the heterogeneous requirements of the tenants. © 2018 Association for Computing Machinery.

Towards dynamic tenant management for microservice based multi-tenant SaaS applications

Automatic image annotation is one of the fundamental problems in computer vision and machine learning. Given an image, here the goal is to predict a set of textual labels that describe the semantics of that image. During the last decade, a large number of image annotation techniques have been proposed that have been shown to achieve encouraging results on various annotation datasets. However, their scope has mostly remained restricted to quantitative results on the test data, thus ignoring various key aspects related to dataset properties and evaluation metrics that inherently affect the performance to a considerable extent. In this paper, first we evaluate ten state-of-the-art (both deep-learning based as well as non-deep-learning based) approaches for image annotation using the same baseline CNN features. Then we propose new quantitative measures to examine various issues/aspects in the image annotation domain, such as dataset specific biases, per-label versus per-image evaluation criteria, and the impact of changing the number and type of predicted labels. We believe the conclusions derived in this paper through thorough empirical analyzes would be helpful in making systematic advancements in this domain. © 2018, Springer Science+Business Media, LLC, part of Springer Nature.

Multimedia Tools and Applications

Automatic image annotation: the quirks and what works

We propose an improved random forest classifier that performs classification with a minimum number of trees. The proposed method iteratively removes some unimportant features. Based on the number of important and unimportant features, we formulate a novel theoretical upper limit on the number of trees to be added to the forest to ensure improvement in classification accuracy. Our algorithm converges with a reduced but important set of features. We prove that further addition of trees or further reduction of features does not improve classification performance. The efficacy of the proposed approach is demonstrated through experiments on benchmark data sets. We further use the proposed classifier to detect mitotic nuclei in the histopathological data sets of breast tissues. We also apply our method on the industrial data set of dual-phase steel microstructures to classify different phases. Results of our method on different data sets show significant reduction in an average classification error compared with a number of competing methods. © 1992-2012 IEEE.

IEEE Transactions on Image Processing

Improved Random Forest for Classification

The real-world is a medley of multisensory information and so are our experiences, memories, and responses. As embodied beings, we respond to the information endogenously and in ways derived from self-defining factors. Thus inspired, we attempt formalization of data-structures to facilitate generation of system-bespoke comprehension-granules of the real-world. The conceptualized structures encapsulate multisensory inputs (sourced from the real-world or memories), intrinsic and deliberate emotions, messages (bearing intermittent process-results, queries, multimodal data, etc.) across system modules and memory units, and sensorimotor responses to the inputs. The structural-schematics are anthropomorphic. These variable-length constructs are theoretically platform-independent, support genericity across data-modality and information-inclusion, and provide for representation of novel sensory-data. An epigenome-styled header node for the afferent data-units provides for the activation of intuitive 'fight-flight' behavior. The documentation includes a flow-graph, depicting the translation of information across the data-structures and the different ways of thinking while interpreting a real-world scene or a mind-generated event. Applicability of the structures has been analyzed in the context of comprehension in an embodied mind-machine framework and other similar architectures. Studies herein target contribution to the design of generally intelligent man-machine symbiotic systems. © 2016 IEEE.

IEEE Transactions on Cognitive and Developmental Systems

Data-Structures for Multisensory Information Processing in an Embodied Machine-Mind

Due to the massive growth of real estate industry, there is an increase in the number of online platforms designed for finding homes/furnished properties. Instead of descriptive words, query by example is always a preferred method for retrieval. Floor plans are the basic 2D representation giving an idea about the building structure at a particular level. The authors propose a framework for the retrieval of similar architectural floor plans under the query by example paradigm. They propose a novel algorithm to extract high-level semantic features from an architectural floor plan. Fine-grained retrieval using weighted sum of the features is proposed, where a feature can be given more preference over others, during retrieval. Experiments were performed on publicly available dataset containing 510 floor plans and compared with existing state-of-the-art techniques. Their proposed method outperforms others both in qualitative and quantitative terms. © The Institution of Engineering and Technology 2018.

IET Computer Vision

High-level feature aggregation for fine-grained architectural floor plan retrieval

Image inpainting is an extremely challenging and open problem for the computer vision community. Motivated by the recent advancement in deep learning algorithms for computer vision applications, we propose a new end-to-end deep learning based framework for image inpainting. Firstly, the images are down-sampled as it reduces the targeted area of inpainting therefore enabling better filling of the target region. A down-sampled image is inpainted using a trained deep convolutional auto-encoder (CAE). A coupled deep convolutional auto-encoder (CDCA) is also trained for natural image super resolution. The pre-trained weights from both of these networks serve as initial weights to an end-to-end framework during the fine tuning phase. Hence, the network is jointly optimized for both the aforementioned tasks while maintaining the local structure/information. We tested this proposed framework with various existing image inpainting datasets and it outperforms existing natural image blind inpainting algorithms. Our proposed framework also works well to get noise resilient super-resolution after fine-tuning on noise-free super-resolution dataset. It provides more visually plausible and better resultant image in comparison of other conventional and state-of-the-art noise-resilient super-resolution algorithms. © Springer Nature Singapore Pte Ltd. 2018.

Communications in Computer and Information Science

An end-to-end deep learning framework for super-resolution based inpainting

Convolutional neural network based architectures have achieved decent perceptual quality super resolution on natural images for small scaling factors (2X and 4X). However, image super-resolution for large magnication factors (8X) is an extremely challenging problem for the computer vision community. In this paper, we propose a novel Improved Residual based Gradual Up-Scaling Network (IRGUN) to improve the quality of the super-resolved image for a large magnification factor. IRGUN has a Gradual Upsampling and Residue-based Enhancment Network (GUREN) which comprises of series of Up-scaling and Enhancement blocks (UEB) connected end-to-end and fine-tuned together to give a gradual magnification and enhancement. Due to the perceptual importance of the luminance in super-resolution, the model is trained on luminance (Y) channel of the YCbCr image. Whereas, the chrominance components (Cb and Cr) channel are up-scaled using bicubic interpolation and combined with super-resolved Y channel of the image, which is then converted to RGB. A cascaded 3D-RED architecture trained on RGB images is utilized to incorporate its inter-channel correlation. In addition to this, the training methodology is also presented in the paper. In the training procedure, the weights of the previous UEB are used in the next immediate UEB for faster and better convergence. Each UEB is trained on its respective scale by taking the output image of the previous UEB as input and corresponding HR image of the same scale as ground truth to the successive UEB. All the UEBs are then connected end-to-end and fine tuned. The IRGUN recovers fine details effectively at large (8X) magnification factors. The efficiency of IRGUN is presented on various benchmark datasets and at different magnification scales. © 2018 IEEE.