S
Santanu Chaudhury
Researcher at Indian Institute of Technology, Jodhpur
Publications - 389
Citations - 4361
Santanu Chaudhury is an academic researcher from Indian Institute of Technology, Jodhpur. The author has contributed to research in topics: Ontology (information science) & Deep learning. The author has an hindex of 28, co-authored 380 publications receiving 3691 citations. Previous affiliations of Santanu Chaudhury include Central Electronics Engineering Research Institute & Indian Institute of Technology Delhi.
Papers
More filters
Proceedings ArticleDOI
Collaborative Human Machine Attention Module for Character Recognition
TL;DR: Wang et al. as mentioned in this paper proposed a collaborative human and machine attention module which considers both visual and network's attention, which can be integrated with any convolutional neural network (CNN) model.
Book ChapterDOI
Bone Age Assessment for Lower Age Groups Using Triplet Network in Small Dataset of Hand X-Rays
TL;DR: In this article, a bone-age assessment model using triplet loss for children in 0-3 years of age is proposed, which achieves an AUC of 0.92 for binary and 0.82 for multi-class classification with visible separation in embedding clusters.
Journal Article
Video Scene Interpretation Using Perceptual Prominence and Mise-en-scène Features
Gaurav Harit,Santanu Chaudhury +1 more
TL;DR: An empirical computational model is proposed for generating an interpretation of a video shot based on the proposed principle of perceptual prominence, which captures the key aspects of mise-en-scene required for interpreting a video scene.
Proceedings ArticleDOI
Eye Movement State Trajectory Estimator based on Ancestor Sampling
TL;DR: In this paper, a state trajectory estimator based on ancestor sampling (ST EAS) model was proposed for gaze data classification and video retrieval, which captures the features of the human temporal gaze pattern to identify the kind of visual stimuli.
Proceedings ArticleDOI
Content-aware seamless stereoscopic 3D compositing
TL;DR: A novel content-aware compositing technique that faithfully preserves the salient structures of cloned source and target content, and avoid major conflicting stereopsis cues to maintain a pleasant 3D illusion altogether is presented.