A B C D E
1
2
Day 0: 18th Dec. Venue: Himalaya Building, IIIT Hyderabad
3
Complete details of Workshop programs and Tutorials are available on the corresponding pages
4
Time Tutorials Session Workshops (Run in parallel)
5
8:00 - 9:00 Registration, Breakfast
6
9:00 - 10:30 Tutorial 1
Session 1
Workshops: Session 1 MedImage, WCVA, WDAR, WDH
7
10:30 - 11:00
Tea Break
8
11:00 - 1:00 Tutorial 1
Session 2
Workshops: Session 2 MedImage, WCVA, WDAR, WDH
9
1:00 - 2:00 Lunch
10
2:00 - 3:30 Tutorial 1
Session 3
Workshops: Session 3 MedImage, WCVA, WDAR, WDH
11
3:30 - 4:00 Tea Break
12
4:00 - 6:00 Tutorial 1
Session 4
Workshops: Session 4 MedImage, WCVA, WDAR, WDH
13
14
Day 1: 19th Dec. Venue: ISB Hyderabad
15
Time Session
(Theme)
@Venue
Paper ID Speaker / Author Title
16
8:00 - 9:00 @ Corridor Registration, Breakfast
17
9:00 - 10:00
Plenary 1
@ Khemka
Peter Wonka
(Professor, KAUST)
18
10:00 - 10:30
@ Corridor Tea Break
19
10:30 - 10:50
Oral 1
(Geometry and Visualization)

@ Khemka
74 Vignesh Prasad, Dipanjan Das and Brojeshwar Bhowmick Epipolar Geometry based Learning of Multi-view Depth and Ego-Motion from Monocular Sequences
20
10:50 - 11:10
81 Nayan Joshi, Yogesh Sharma, Madhava Krishna, Brojeshwar Bhowmick, Rishabh Khawad and Parv Parkhiya Integrating Objects into Monocular SLAM: Line Based Category Specific Models
21
11:10 - 11:22
15 Neeladrishekhar Kanjilal and Parag Chaudhuri Real-time Simulation of Human Musculature
22
11:22 - 11:34
56 Mansi Sharma An Integrated Optimization Approach for Depth Map Enhancement on Special Riemannian Manifold
23
11:34 - 11:46
64 Udyan Khurana, Parikshit Sakurikar and P. J. Narayanan SLFT: A Physically Accurate Framework for Tracing Synthetic Light Fields
24
11:46 - 11:58
73 Sai Sagar and Avinash Sharma SplineNet: B-Spline Neural Network for efficient classification of 3D data
25
12:00 - 12:45 Poster Highlights 1
(Geometry and Visualization)

@ Khemka
25 Sumukh Bansal and Aditya Tatu Lie Bodies Based Deformation Transfer
26
31 Mohit Sharma and Vijay Natarajan On-Demand Augmentation of Contour Trees
27
36 Alphin Thottupattu, Shivin Yadav and Avinash Sharma Non-rigid Registration using Spectral Graph Wavelet features
28
54 Soumabha Bhowmick, Jayanta Mukherjee and Alok Kanti Deb An incremental tolpological map building algorithm using monocular vision
29
71 Debaditya Roy, Sanjay Bharath Gaddam Sreedatta, Mani Kumar T. and C. Krishna Mohan Tracking rapid body deformation using sparse representation of deep features
30
Poster Highlights 2
(Face, Body and Action)

@ Khemka
8 Muhammed Fasil C. and Subhasis Chaudhuri Moving Average Recurrent Neural Network Model for Video-based Person Re-Identification
31
9 Kamireddy Sai Suma, Gedela Aditya and Snehasis Mukherjee Activity Recognition in Egocentric Videos Using Bag of Key Action Units
32
13 Shobhanjana Kalita, Arindam Karmakar and Shyamanta Hazarika A Temporal Activity Graph Kernel for Human Activity Classification
33
23 Srijan Das, Kaustubh Sakhalkar, Michal Koperski and Francois Bremond Spatio-Temporal Grids for Daily Living Action Recognition
34
32 Aniket Dashpute, Rishubh Parihar and Prem Kalra Scene Adaptive Cosmetic Makeup Transfer
35
37 Ashish Goyal, Neha Bhargava, Subhasis Chaudhuri and Rajbabu Velmurugan Hierarchical Deep Network for Group Discovery and Multi-level Activity Recognition
36
41 Sudip Das, Partha Sarathi Mukherjee and Ujjwal Bhattacharya Seek and You Will Find: A New Optimized Framework for Efficient Detection of Pedestrian
37
43 Doney Alex, Zishan Sami, Sumandeep Banerjee and Subrat Panda Cluster Loss for Person Re-Identification
38
45 Kankana Roy and Rajiv Sahay Dynamic Gesture Recognition with Pose-based CNN Features derived from videos using LSTM
39
63 Hiteshi Jain and Gaurav Harit Leveraging information from imperfect examples: Common action sequence mining from a mix of incorrect performances
40
66 Vinay Kaushik, Prerana Mukherjee and Brejesh Lall Nrityantar: Pose oblivious Indian classical dance classification
41
68 Bindu Verma and Ayesha Choudhary Dynamic Hand Gesture Recognition using Convolutional Neural Networks with RGB-D Fusion
42
79 Narayan Vetrekar, Raghavendra Ramachandra, Kiran Raja, Rajendra Gad and Christoph Busch Disguise Face Recognition based on Spectral Imaging
43
12:45 - 2:00 @ Atrium Lunch
44
2:00 - 3:00
Plenary 2
@ Khemka
Bernt Schiele
(Professor, Max-Planck Institute)
45
3:00 - 3:20 Oral 2
(Face, Body and Action)

@ Khemka
10 Javed Imran and R Balasubramanian Multimodal Egocentric Activity Recognition Using Multi-Stream CNN
46
3:20 - 3:40 70 Avisek Lahiri, Abhinav Agarwalla and Prabir Biswas Unsupervised Domain Adaptation for Learning Eye Gaze from a Million Synthetic Images: An Adversarial Approach
47
3:40 - 3:52 21 Santosh Kumar Vipparthi, Monu Verma, Jaspreet Kaur and Girdhari Singh EXPERTNet: Exigent Features Preservative Network for Facial Expression Recognition
48
3:52 - 4:04 24 Avishek Bhattacharjee, Samik Banerjee and Sukhendu Das SpoofNET: Resolving Facial Makeup based Spoofs
49
4:05 - 5:30 @ Atrium Tea Break
50
Poster 1
(Geometry & Visualization; Face, Body and Action)
@ Atrium
Poster Session - 1
51
5:30 - 6:00
DDA 1
@Khemka
Presentation: IUPRAI Doctorial Dissertation Award Winner: 2017
52
6:00 - 6:45 Panel Discussion
@Khemka
Panel Discussion
53
54
Day 2: 20th Dec. Venue: ISB Hyderabad
55
Time Session
(Theme)
@Venue
Paper ID Speaker / Author Title
56
8:00 - 9:00 @ Corridor Breakfast
57
9:00 - 10:00
Plenary 3
@ Khemka
Tinne Tuytelaars
(Professor, KU Leuven)
58
10:00 - 10:30
@ Corridor Tea Break
59
10:30 - 10:50
Oral 3
(Deep Learning meets Signal/Image Processing)

@ Khemka
19 Spoorthi GE, Subrahmanyam Gorthi and Gorthi Rama Krishna Sai Subrahmanyam A Deep Learning-based Model for Phase Unwrapping
60
10:50 - 11:10
61 Srimanta Mandal, Kuldeep Purohit and Rajagopalan Ambasamudram Color Image Super Resolution in Real Noise
61
11:10 - 11:22
42 Kushal Borkar and Snehasis Mukherjee Video Dehazing using LMNN with respect to Augmented MRF
62
11:22 - 11:34
49 Abhinav Kumar, Shantanu Gupta, Vladimir Kozitsky and Sriganesh Madhvanath Transferable and Fast Licence Plate Re-identification using a Neural Embedding of Fisher Vectors
63
11:34 - 11:46
62 Arpan Gupta and Sakthi Muthiah Temporal Cricket Stroke Localization from Untrimmed Highlight Videos
64
11:46 - 11:58
67 Shruti Sharma, Santanu Chaudhary, Jayadeva and Snigdha Bhagat Sparse Signal Recovery for Multiple Measurement Vectors with Temporally Correlated Entries: A Bayesian Perspective
65
12:00 - 12:45 Poster Highlights 3
(Deep Learning meets Signal/Image Processing)

@ Khemka
7 Debanjan Sadhya, Akshay Agarwal and R Balasubramanian Perfectly Secure Shamir's Secret Sharing Scheme for Privacy Preserving Image Processing Over Cloud
66
18 Saurabh Kumar and Subhasis Chaudhuri A Fast Method for Very Low Bit-Rate Coding of Hyperspectral Images
67
22 Ranjan Mondal and Bhabotosh Chanda Anomaly Detection using Context Dependent Optical Flow
68
29 S. Bardhan and Shibu Jacob Regularized Random Walk Ranking for Co-Saliency Detection in images
69
39 Sasithradevi Anbalagan, Md Mansoor Roomi and M Mahisha Shot Boundary Detection in Videos Using Saliency based Statistical Model
70
40 Pavan Sandula and Manish Okade Compressed domain zoom motion detection and classification based on application of local ternary patterns on block motion vectors
71
48 Monika Mathur and Nidhi Taneja Dual domain approach for colour enhancement of underwater images
72
72 Shruti Sharma and Santanu Chaudhary and Jayadeva Temporal Modeling of EEG Signals using Block Sparse Variational Bayes Framework
73
75 Priya Mariam Raju, Deepak Mishra and Gorthi Rama Krishna Sai Subrahmanyam Bag of Visual Words based Correlation Filter Tracker(BoVW-CFT)
74
78 Sidharth Gautam, Tapan Gandhi and Bijaya Ketan Panigrahi Single image dehazing using image boundary constraint and nearest neighborhood optimization
75
80 Satendra Singh and Gaurav Bhatnagar A Chaos Based Robust and Secure Image Hashing Framework
76
Poster Highlights 4
(Applications, Medical)

@ Khemka
2 Annapurna Sharma and Dinesh Babu J. Handwritten Essay Grading on Mobiles using MDLSTM Model and Word Embeddings
77
4 Vijay John, Swarn Rathour and Seiichi Mita Vision-based Steering Angle Prediction by the Fusion of Depth and Intensity Deep Features
78
14 Srikrishna Varadarajan and Muktabh Mayank Srivastava Weakly Supervised Object Localization on grocery shelves using simple FCN and Synthetic Dataset
79
17 Anupama Arun, Thomas James Thomas, Sheeba Rani J. and Gorthi Rama Krishna Sai Subrahmanyam Variable Patch Dictionaries for efficient Compressed Sensing based MRI Reconstruction
80
35 Sukesh Adiga V. and Jayanthi Sivaswamy Shared Encoder based Denoising of Optical Coherence Tomography images
81
50 Saikat Sarkar, Amlan Chakrabarti and Dipti Prasad Mukherjee Estimation of Ball Possession Statistics in Soccer Video
82
52 Shashaank Aswatha, Vishnu Saini, Jayanta Mukherjee, Prabir Biswas, Subhas Aikat and Arundhati Misra Unsupervised Detection of Surface Mine Sites using Sentinel Multi-spectral Imagery and Dual-polarimetric SAR Data
83
59 Udit Shrivastava and Manjunath Joshi Automated Multiclass Diagnosis of Diabetic Retinopathy using Hierarchical Learning
84
76 RIki Kudo, Motoi Iwata, Masakazu Iwamura, and Koichi Kise Improvement of Trademark Retrieval Using Pseudo Relevance Feedback
85
77 Kunal Chelani, Sidhartha Chitturi and Venu Madhav Govindu Towards Automated Floorplan Generation
86
12:45 - 2:00 @ Atrium Lunch
87
2:00 - 3:00
Plenary 4
@ Khemka
P. Anandan
(CEO, Wadhwai AI)
88
3:00 - 3:20 Oral 4
(Applications, Medical)

@ Khemka
27 Snehal Shete, Srikant Srinivasan, Seyed Vahid Mirnezami, Baskar Ganapathysubramanian, Patrick Schnable and Timothy Gonsalves An automated tassel detection and trait extraction pipeline to support high-throughput field imaging of maize
89
3:20 - 3:40 58 Ajin Joy, and Joseph Suresh Paul A Rapid Non-Linear Diffusion Compressed Sensing parallel MR Image Reconstruction
90
3:40 - 3:52 44 Harsh Jain, Chandan Nataraj and Dinesh Babu J. Rash Driving Detection using a Frontal View Camera in Cars
91
3:52 - 4:04 55 Ekagra Ranjan, Soumava Paul, Siddharth Kapoor, Aupendu Kar, Ramanathan Sethuraman and Debdoot Sheet Jointly Learning Convolutional Representations to Compress Radiological Images and Classify Thoracic Diseases in the Compressed Domain
92
4:05 - 5:30 @ Atrium Tea Break
93
Poster 2
(DL + SIP; Applications, Medical)
@ Atrium
Poster Session - 2
94
5:30 - 6:00
DDA 2
@Khemka
Presentation: IUPRAI Doctorial Dissertation Award Winner: 2018
95
6:00 - 6:45 Meeting
@Khemka
IUPRAI General Body Meeting
96
6:45 onwards
Banquet
@ Khemka, Lawns
Banquet
97
98
Day 3: 21st Dec. Venue: ISB Hyderabad
99
Time Session
(Theme)
@Venue
Paper ID Speaker / Author Title
100
8:00 - 9:00 @ Corridor Breakfast
101
9:00 - 10:00
Plenary 5
@ Khemka
Ali Eslami
(Research Scientist, Google DeepMind)
102
10:00 - 10:30
@ Corridor Tea Break
103
10:30 - 10:50
Oral 5
(Learning and GANs)

@ Khemka
38 Sandeep Narayan Parameswaran and Sukhendu Das A Bottom-Up and Top-Down Approach for Image Captioning using Transformer
104
10:50 - 11:10
47 Vignesh Prasad, Karmesh Yadav, Saurabh Singh, Swapnil Daga, Nahas Pareekutty, Madhava Krishna, Balaraman Ravindran and Brojeshwar Bhowmick Learning to prevent Monocular SLAM failure using Reinforcement Learning
105
11:10 - 11:22
5 Omkar Gune, Meet Vora, Biplab Banerjee and Subhasis Chaudhuri Zero-shot Learning using Graph Regularized Latent Discriminative Cross-domain Triplets
106
11:22 - 11:34
28 Saptakatha Adak and Sukhendu Das VidSeg-GAN: Generative Adversarial Network for Video Object Segmentation Tasks
107
11:34 - 11:46
33 Ankush Gupta, Andrea Vedaldi and Andrew Zisserman Learning to Read by Spelling: Towards Unsupervised Text Recognition
108
11:46 - 11:58
51 Arka Ujjal Dey; Gaurav Harit and A. H. Abdul Hafez Greedy Gaussian Process Regression Applied to Object Categorization and Regression
109
12:00 - 12:45 Poster Highlights 5
(Learning and GANs)

@ Khemka
1 Adarsh Jamadandi, Sunidhi Kotturshettar and Uma Mudenagudi PredGAN - a deep multi-scale video prediction framework for anomaly detection in videos
110
3 T M Feroz Ali, Kalpesh Patel, Rajbabu Velmurugan and Subhasis Chaudhuri Multiple Kernel Fisher Discriminant Metric Learning for Person Re-identification
111
6 Akshay Dudhane; Subrahmanyam Murala and Abhinav Dhall LEDNet: Deep Network for Single Image Haze Removal
112
11 Ashish Mehta, Adithya Subramanian and Anbumani Subramanian Learning End-to-end Autonomous Driving using Guided Auxiliary Supervision
113
12 Amit More and Subhasis Chaudhuri A Neural Network Based Approach for Geo-Localizing Events in Crowd Sourced Videos
114
16 Fateme Bahri, Moein Shakeri and Nilanjan Ray Online Illumination Invariant Moving Object Detection by Generative Neural Network
115
20 Swetha V.C., Deepak Mishra and Gorthi Rama Krishna Sai Subrahmanyam Scale and Rotation Corrected CNNs ( SRC-CNNs ) for Scale and Rotation Invariant Character Recognition
116
26 Avishek Bhattacharjee, Samik Banerjee and Sukhendu Das DP-GAN: Dual Pathway Generative Adversarial Network for Face Recognition in degraded scenarios
117
30 Sai Ram Kasanagottu, Jayanta Mukherjee, Amit Patra and Partha Das HSD-CNN: Hierarchically self decomposing CNN architecture using class specific filter sensitivity analysis
118
34 Akshayvarun Subramanya, Konda Reddy Mopuri and Venkatesh Babu Radhakrishnan BatchOut: Batch-level feature augmentation to improve robustness to adversarial example
119
46 Rahul Roy, Susmita Ghosh and Ashish Ghosh Salient Object Detection based on Bayesian Surprise of Restricted Boltzmann Machine
120
53 Anisha Pal, Shourya Jaiswal, Swarnendu Ghosh, Nibaran Das and Mita Nasipuri SegFast: Using Depthwise Separable Convolutions and SqueezeNet to speed up Semantic Image Segmentation
121
57 Sayan Banerjee, Avik Hati, Subhasis Chaudhuri and Rajbabu Velmurugan Image Co-segmentation using Graph Convolution Neural Network
122
60 Shankar Setty, Sindhu Hegde, Supriya Satyappanavar, and Uma Mudenagudi Evaluation of Point Cloud Categorization for Rigid and Non-Rigid 3D Objects
123
69 Ankita Shukla, Shagun Uppal, Sarthak Bhagat, Saket Anand and Pavan Turaga Geometry of Deep Generative Models for Disentangled Representations
124
12:45 - 2:00 @ Atrium Lunch
125
2:00 - 4:00
Vision India
@ Khemka
Vision India
126
4:00 - 4:15 @ Atrium Tea Break
127
4:15 - 6:00 Poster 3
(Learning and GANs)
@ Atrium
Poster Session - 3
128
4:15 - 7:15
Tutorial 2
@Khemka
Carlos Castillo
(Research Scientist, University of Maryland)
Implementing DCNNs
129
4:15 - 6:00 DC
@LT
Doctoral Consortium
130
131
Day 4: 22nd Dec. Special Event: Hyderabad AI Symposium Venue: Infosys Campus Hyderabad