scispace - formally typeset
Search or ask a question
Institution

Indian Institute of Technology Kharagpur

EducationKharagpur, India
About: Indian Institute of Technology Kharagpur is a education organization based out in Kharagpur, India. It is known for research contribution in the topics: Natural rubber & Dielectric. The organization has 16887 authors who have published 38658 publications receiving 714526 citations.


Papers
More filters
Journal ArticleDOI
TL;DR: In this article, the authors reported calcined EMHS as an effective adsorbent for removal of PO43− from aqueous solutions and investigated the cumulative % removal rate in a batch adsorber with different initial adsorbate concentrations, adsorbant dose, pH of the solution and adsorption temperature.

122 citations

Journal ArticleDOI
TL;DR: In this paper, the drying characteristics of the coconut presscake were investigated under varying conditions of presscake thickness (2, 3 and 4mm) and vacuum chamber plate temperature (65, 70 and 75 °C) at 65 Âmm Hg absolute pressure.

122 citations

Journal ArticleDOI
25 Apr 2005-Polymer
TL;DR: In this article, the organic-inorganic hybrid nanocomposites comprising poly(iminohexamethyleneiminoadipoyl), better known as Polyamide-6,6 (abbreviated henceforth as PA66), and silica (SiO2) were synthesized through sol-gel technique at ambient temperature.

122 citations

Journal ArticleDOI
TL;DR: The present study investigated the feasibility of using Chlorella sorokiniana for CO2 sequestration from industrial flue gas and fatty acid composition in the total lipid was determined to evaluate its suitability for food, feed, and biofuel.

122 citations

Posted Content
TL;DR: This paper proposes DeepFix, a fully convolutional neural network, which models the bottom–up mechanism of visual attention via saliency prediction via Saliency prediction, and evaluates the model on multiple challenging saliency data sets and shows that it achieves the state-of-the-art results.
Abstract: Understanding and predicting the human visual attentional mechanism is an active area of research in the fields of neuroscience and computer vision. In this work, we propose DeepFix, a first-of-its-kind fully convolutional neural network for accurate saliency prediction. Unlike classical works which characterize the saliency map using various hand-crafted features, our model automatically learns features in a hierarchical fashion and predicts saliency map in an end-to-end manner. DeepFix is designed to capture semantics at multiple scales while taking global context into account using network layers with very large receptive fields. Generally, fully convolutional nets are spatially invariant which prevents them from modeling location dependent patterns (e.g. centre-bias). Our network overcomes this limitation by incorporating a novel Location Biased Convolutional layer. We evaluate our model on two challenging eye fixation datasets -- MIT300, CAT2000 and show that it outperforms other recent approaches by a significant margin.

122 citations


Authors

Showing all 17290 results

NameH-indexPapersCitations
Rajdeep Mohan Chatterjee11099051407
Vijay P. Singh106169955831
Arun Majumdar10245952464
Sanjay Gupta9990235039
Biswajeet Pradhan9873532900
Sandeep Kumar94156338652
Jürgen Eckert92136842119
Praveen Kumar88133935718
Tuan Vo-Dinh8669824690
Lawrence Carin8494931928
Anindya Dutta8224833619
Aniruddha B. Pandit8042722552
Krishnendu Chakrabarty7999627583
Ramesh Jain7855637037
Thomas Thundat7862222684
Network Information
Related Institutions (5)
Indian Institute of Science
62.4K papers, 1.2M citations

94% related

Royal Institute of Technology
68.4K papers, 1.9M citations

92% related

Nanyang Technological University
112.8K papers, 3.2M citations

92% related

Council of Scientific and Industrial Research
31.8K papers, 707.7K citations

92% related

National Technical University of Athens
31.2K papers, 723.5K citations

92% related

Performance
Metrics
No. of papers from the Institution in previous years
YearPapers
2023284
2022849
20213,142
20202,907
20192,779
20182,489