activity
20172023
most citedAn Integrated Approach to Crowd Video Analysis: From Tracking to Multi-level Activity Recognition

2 citations · 9 across the 14 of their papers we have counts for

collaborators
Showing cs.CVShow all

19 papers · 1 filter

cs.CV20231 cited

Efficient Curriculum based Continual Learning with Informative Subset Selection for Remote Sensing Scene Classification

S Divakar Bhat, Biplab Banerjee, Subhasis Chaudhuri +1

We tackle the problem of class incremental learning (CIL) in the realm of landcover classification from optical remote sensing (RS) images in this paper. The paradigm of CIL has re…

cs.CV2023

Physically Plausible 3D Human-Scene Reconstruction from Monocular RGB Image using an Adversarial Learning Approach

Sandika Biswas, Kejie Li, Biplab Banerjee +2

Holistic 3D human-scene reconstruction is a crucial and emerging research area in robot perception. A key challenge in holistic 3D human-scene reconstruction is to generate a physi…

cs.CV2023

MultiScale Probability Map guided Index Pooling with Attention-based learning for Road and Building Segmentation

Shirsha Bose, Ritesh Sur Chowdhury, Debabrata Pal +3

Efficient road and building footprint extraction from satellite images are predominant in many remote sensing applications. However, precise segmentation map extraction is quite ch…

cs.CV2022

FRIDA -- Generative Feature Replay for Incremental Domain Adaptation

Sayan Rakshit, Anwesh Mohanty, Ruchika Chavhan +3

We tackle the novel problem of incremental unsupervised domain adaptation (IDA) in this paper. We assume that a labeled source domain and different unlabeled target domains are inc…

cs.CV20211 cited

Deep Learning based Novel View Synthesis

Amit More, Subhasis Chaudhuri

Predicting novel views of a scene from real-world images has always been a challenging task. In this work, we propose a deep convolutional neural network (CNN) which learns to pred…

cs.CV20202 cited

3D-NVS: A 3D Supervision Approach for Next View Selection

Kumar Ashutosh, Saurabh Kumar, Subhasis Chaudhuri

We present a classification based approach for the next best view selection and show how we can plausibly obtain a supervisory signal for this task. The proposed approach is end-to…