K
K. S. Venkatesh
Researcher at Indian Institute of Technology Kanpur
Publications - 123
Citations - 635
K. S. Venkatesh is an academic researcher from Indian Institute of Technology Kanpur. The author has contributed to research in topics: Depth map & Image segmentation. The author has an hindex of 12, co-authored 117 publications receiving 511 citations. Previous affiliations of K. S. Venkatesh include Kingston University & Indian Institutes of Technology.
Papers
More filters
Proceedings ArticleDOI
Collaborative Learning to Generate Audio-Video Jointly
TL;DR: In this paper, the authors proposed a method to generate naturalistic samples of video and audio data by the joint correlated generation of audio and video modalities, using multiple discriminators to ensure that the audio, video and the joint output are also indistinguishable from real-world samples.
Proceedings ArticleDOI
Acquisition of Aerial Light Fields
Indrajit Kurmi,K. S. Venkatesh +1 more
TL;DR: This paper proposes to use unmanned aerial vehicle for acquisition of larger unstructured aerial light fields and aims to capture light fields of larger objects and scenes which are not possible by traditional light field acquisition setup.
Book ChapterDOI
Visual Odometry Based Omni-directional Hyperlapse
TL;DR: This work addresses thehyperlapse problem for the very challenging category of intensive egomotion which makes the hyperlapse highly jerky, and proposes an economical approach for trajectory estimation based on Visual Odometry and implement cost functions to penalize pose and path deviations.
Proceedings ArticleDOI
SURF-based human tracking algorithm for a human-following mobile robot
TL;DR: This paper aims at developing a robust vision-based algorithm using point-based features, like SURF, which can track a human under challenging conditions including variation in illumination, pose change, full or partial occlusion and abrupt camera motion.
Proceedings ArticleDOI
An Energy Minimization Approach for Automatic Video Shot and Scene Boundary Detection
TL;DR: This paper formulate the extraction of Video shot as an energy minimization problem in which the desire to extract the shot with the common background is represented by an energy term and optimizes to minimize the discontinuity in the background edges and color.