172 citations · 263 across the 34 of their papers we have counts for
37 papers
EpiSAM: Character Segmentation in Challenging Stone Inscriptions
Arnav Sharma, Pratyush Jena, Amal Joseph +1
Stone inscriptions are invaluable sources of historical and linguistic knowledge, yet their automated analysis remains a major challenge due to surface irregularities, erosion, and…
SeeThrough3D: Occlusion Aware 3D Control in Text-to-Image Generation
Vaibhav Agrawal, Rishubh Parihar, Pradhaan Bhat +2
We identify occlusion reasoning as a fundamental yet overlooked aspect for 3D layout-conditioned generation. It is essential for synthesizing partially occluded objects with depth-…
Unveiling Text in Challenging Stone Inscriptions: A Character-Context-Aware Patching Strategy for Binarization
Pratyush Jena, Amal Joseph, Arnav Sharma +1
Binarization is a popular first step towards text extraction in historical artifacts. Stone inscription images pose severe challenges for binarization due to poor contrast between…
IndicDLP: A Foundational Dataset for Multi-Lingual and Multi-Domain Document Layout Parsing
Oikantik Nath, Sahithi Kukkala, Mitesh Khapra +1
Document layout analysis is essential for downstream tasks such as information retrieval, extraction, OCR, and digitization. However, existing large-scale datasets like PubLayNet a…
TexTAR : Textual Attribute Recognition in Multi-domain and Multi-lingual Document Images
Rohan Kumar, Jyothi Swaroopa Jinka, Ravi Kiran Sarvadevabhatla
Recognizing textual attributes such as bold, italic, underline and strikeout is essential for understanding text semantics, structure, and visual presentation. These attributes hig…
DashCop: Automated E-ticket Generation for Two-Wheeler Traffic Violations Using Dashcam Videos
Deepti Rawat, Keshav Gupta, Aryamaan Basu Roy +1
Motorized two-wheelers are a prevalent and economical means of transportation, particularly in the Asia-Pacific region. However, hazardous driving practices such as triple riding a…
CrackUDA: Incremental Unsupervised Domain Adaptation for Improved Crack Segmentation in Civil Structures
Kushagra Srivastava, Damodar Datta Kancharla, Rizvi Tahereen +3
Crack segmentation plays a crucial role in ensuring the structural integrity and seismic safety of civil structures. However, existing crack segmentation algorithms encounter chall…
MoRAG -- Multi-Fusion Retrieval Augmented Generation for Human Motion
Sai Shashank Kalakonda, Shubh Maheshwari, Ravi Kiran Sarvadevabhatla
We introduce MoRAG, a novel multi-part fusion based retrieval-augmented generation strategy for text-based human motion generation. The method enhances motion diffusion models by l…
Automated Detection and Counting of Windows using UAV Imagery based Remote Sensing
Dhruv Patel, Shivani Chepuri, Sarvesh Thakur +3
Despite the technological advancements in the construction and surveying sector, the inspection of salient features like windows in an under-construction or existing building is pr…
Action-GPT: Leveraging Large-scale Language Models for Improved and Generalized Action Generation
Sai Shashank Kalakonda, Shubh Maheshwari, Ravi Kiran Sarvadevabhatla
We introduce Action-GPT, a plug-and-play framework for incorporating Large Language Models (LLMs) into text-based action generation models. Action phrases in current motion capture…
PSUMNet: Unified Modality Part Streams are All You Need for Efficient Pose-based Action Recognition
Neel Trivedi, Ravi Kiran Sarvadevabhatla
Pose-based action recognition is predominantly tackled by approaches which treat the input skeleton in a monolithic fashion, i.e. joints in the pose tree are processed as a whole.…
Counting in the 2020s: Binned Representations and Inclusive Performance Measures for Deep Crowd Counting Approaches
Sravya Vardhani Shivapuja, Ashwin Gopinath, Ayush Gupta +2
The data distribution in popular crowd counting datasets is typically heavy tailed and discontinuous. This skew affects all stages within the pipelines of deep crowd counting appro…
MUGL: Large Scale Multi Person Conditional Action Generation with Locomotion
Shubh Maheshwari, Debtanu Gupta, Ravi Kiran Sarvadevabhatla
We introduce MUGL, a novel deep neural model for large-scale, diverse generation of single and multi-person pose-based action sequences with locomotion. Our controllable approach e…
Palmira: A Deep Deformable Network for Instance Segmentation of Dense and Uneven Layouts in Handwritten Manuscripts
Prema Satish Sharan, Sowmya Aitha, Amandeep Kumar +3
Handwritten documents are often characterized by dense and uneven layout. Despite advances, standard deep network based approaches for semantic layout segmentation are not robust t…
BoundaryNet: An Attentive Deep Network with Fast Marching Distance Maps for Semi-automatic Layout Annotation
Abhishek Trivedi, Ravi Kiran Sarvadevabhatla
Precise boundary annotations of image regions can be crucial for downstream applications which rely on region-class semantics. Some document collections contain densely laid out, h…
Wisdom of (Binned) Crowds: A Bayesian Stratification Paradigm for Crowd Counting
Sravya Vardhani Shivapuja, Mansi Pradeep Khamkar, Divij Bajaj +2
Datasets for training crowd counting deep networks are typically heavy-tailed in count distribution and exhibit discontinuities across the count range. As a result, the de facto st…
Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action Localization
Anurag Bagchi, Jazib Mahmood, Dolton Fernandes +1
State of the art architectures for untrimmed video Temporal Action Localization (TAL) have only considered RGB and Flow modalities, leaving the information-rich audio modality tota…
Syntactically Guided Generative Embeddings for Zero-Shot Skeleton Action Recognition
Pranay Gupta, Divyanshu Sharma, Ravi Kiran Sarvadevabhatla
We introduce SynSE, a novel syntactically guided generative approach for Zero-Shot Learning (ZSL). Our end-to-end approach learns progressively refined generative embedding spaces…
NTU-X: An Enhanced Large-scale Dataset for Improving Pose-based Recognition of Subtle Human Actions
Neel Trivedi, Anirudh Thatipelli, Ravi Kiran Sarvadevabhatla
The lack of fine-grained joints (facial joints, hand fingers) is a fundamental performance bottleneck for state of the art skeleton action recognition models. Despite this bottlene…
Early Bird: Loop Closures from Opposing Viewpoints for Perceptually-Aliased Indoor Environments
Satyajit Tourani, Dhagash Desai, Udit Singh Parihar +4
Significant advances have been made recently in Visual Place Recognition (VPR), feature correspondence, and localization due to the proliferation of deep-learning-based methods. Ho…
Quo Vadis, Skeleton Action Recognition ?
Pranay Gupta, Anirudh Thatipelli, Aditya Aggarwal +4
In this paper, we study current and upcoming frontiers across the landscape of skeleton-based human action recognition. To study skeleton-action recognition in the wild, we introdu…
OPAL-Net: A Generative Model for Part-based Object Layout Generation
Rishabh Baghel, Ravi Kiran Sarvadevabhatla
We propose OPAL-Net, a novel hierarchical architecture for part-based layout generation of objects from multiple categories using a single unified model. We adopt a coarse-to-fine…
Topological Mapping for Manhattan-like Repetitive Environments
Sai Shubodh Puligilla, Satyajit Tourani, Tushar Vaidya +3
We showcase a topological mapping framework for a challenging indoor warehouse setting. At the most abstract level, the warehouse is represented as a Topological Graph where the no…
Indiscapes: Instance Segmentation Networks for Layout Parsing of Historical Indic Manuscripts
Abhishek Prusty, Sowmya Aitha, Abhishek Trivedi +1
Historical palm-leaf manuscript and early paper documents from Indian subcontinent form an important part of the world's literary and cultural heritage. Despite their importance, l…