Search Results for author:
Found 11 papers, 2 papers with code
Conditioning Covert Geo-Location (CGL) Detection on Semantic Class Information
Recently, with the aim to incorporate knowledge about non-object image regions (hideouts, turns, and other obscured regions), a task for identification of potential hideouts termed Covert Geo-Location (CGL) detection was proposed by Saha et al.
V3GAN: Decomposing Background, Foreground and Motion for Video Generation
Video generation is a challenging task that requires modeling plausible spatial and temporal dynamics in a video.
Catch Me if You Can: A Novel Task for Detection of Covert Geo-Locations (CGL)
Classification of any region of an image as a CGL (as boundary sub-segments of an occluding object that conceals the hideout) requires examining the 3D relation between boundaries of occluding objects and their neighborhoods & surroundings.
Future Frame Prediction of a Video Sequence
In this paper, we proposed a novel multi-scale architecture combining both approaches.
SD-GAN: Structural and Denoising GAN reveals facial parts under occlusion
Certain facial parts are salient (unique) in appearance, which substantially contribute to the holistic recognition of a subject.
What's There in the Dark
In this paper, we propose a noveldeep architecture, NiSeNet, that performs semantic segmen-tation of night scenes using a domain mapping approach ofsynthetic to real data.
Ranked #1 on
Semantic Segmentation
on BDD100K val
What's There in the Dark
In addition, we used an Adaptive channel reducing the domain gap between synthetic and real night images, which also complements the failures of Real channel output.
Moving Object Segmentation in Jittery Videos by Stabilizing Trajectories Modeled in Kendall's Shape Space
The 2nd stage performs a block-wise Procrustes analysis of the trajectories and estimates Frechet means (in Kendall's shape space) of the clusters.
Temporal Coherency based Criteria for Predicting Video Frames using Deep Multi-stage Generative Adversarial Networks
Although GANs have been used in the past for predicting the future, none of the works consider the relation between subsequent frames in the temporal dimension.
Domain Adaptation with Soft-margin multiple feature-kernel learning beats Deep Learning for surveillance face recognition
Face recognition (FR) is the most preferred mode for biometric-based surveillance, due to its passive nature of detecting subjects, amongst all different types of biometric traits.
Kernel Selection using Multiple Kernel Learning and Domain Adaptation in Reproducing Kernel Hilbert Space, for Face Recognition under Surveillance Scenario
The proposed technique in this paper tries to cope with the very low resolution and low contrast face images obtained from surveillance cameras, for FR under surveillance conditions.
