Search Results for author: Sukhendu Das

Found 11 papers, 2 papers with code

Conditioning Covert Geo-Location (CGL) Detection on Semantic Class Information

no code implementations27 Nov 2022 Binoy Saha, Sukhendu Das

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.

Semantic Segmentation

V3GAN: Decomposing Background, Foreground and Motion for Video Generation

no code implementations26 Mar 2022 Arti Keshari, Sonam Gupta, Sukhendu Das

Video generation is a challenging task that requires modeling plausible spatial and temporal dynamics in a video.

Video Generation

Catch Me if You Can: A Novel Task for Detection of Covert Geo-Locations (CGL)

no code implementations5 Feb 2022 Binoy Saha, Sukhendu Das

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.

object-detection Object Detection +1

Future Frame Prediction of a Video Sequence

no code implementations31 Aug 2020 Jasmeen Kaur, Sukhendu Das

In this paper, we proposed a novel multi-scale architecture combining both approaches.

Autonomous Driving Decision Making +1

SD-GAN: Structural and Denoising GAN reveals facial parts under occlusion

no code implementations19 Feb 2020 Samik Banerjee, Sukhendu Das

Certain facial parts are salient (unique) in appearance, which substantially contribute to the holistic recognition of a subject.

Denoising Face Recognition +1

What's There in the Dark

1 code implementation 26th IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan 2019 Sauradip Nag, Saptakatha Adak, Sukhendu Das

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.

Autonomous Driving Scene Parsing +1

What's There in the Dark

1 code implementation24 Sep 2019 Sauradip Nag, Saptakatha Adak, Sukhendu Das

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.

Scene Parsing Semantic Segmentation

Moving Object Segmentation in Jittery Videos by Stabilizing Trajectories Modeled in Kendall's Shape Space

no code implementations14 Aug 2018 Geethu Miriam Jacob, Sukhendu Das

The 2nd stage performs a block-wise Procrustes analysis of the trajectories and estimates Frechet means (in Kendall's shape space) of the clusters.

Clustering Segmentation +3

Temporal Coherency based Criteria for Predicting Video Frames using Deep Multi-stage Generative Adversarial Networks

no code implementations NeurIPS 2017 Prateep Bhattacharjee, Sukhendu Das

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

no code implementations5 Oct 2016 Samik Banerjee, Sukhendu Das

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.

Domain Adaptation Face Recognition

Kernel Selection using Multiple Kernel Learning and Domain Adaptation in Reproducing Kernel Hilbert Space, for Face Recognition under Surveillance Scenario

no code implementations3 Oct 2016 Samik Banerjee, Sukhendu Das

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.

Face Recognition Unsupervised Domain Adaptation

Cannot find the paper you are looking for? You can Submit a new open access paper.