no code implementations • 25 Jun 2020 • Chiranjib Sur
Self-segregation strategy for attention contributes in better understanding and filtering the information that can be most helpful for answering the question and create diversity of visual-reasoning for attention.
no code implementations • 25 Jun 2020 • Chiranjib Sur
Video captioning works on the two fundamental concepts, feature detection and feature composition.
no code implementations • 14 Jun 2020 • Chiranjib Sur
In this work, we have introduced a generalized scheme for consistency for GAN architectures with two new concepts of Transformation Learning (TL) and Relative Learning (ReL) for enhanced learning image transformations.
no code implementations • 16 Feb 2020 • Chiranjib Sur
In this work, we have introduced Gaussian Smoothen Semantic Features (GSSF) for Better Semantic Selection for Indian regional language-based image captioning and introduced a procedure where we used the existing translation and English crowd-sourced sentences for training.
no code implementations • 15 Feb 2020 • Chiranjib Sur
While image captioning through machines requires structured learning and basis for interpretation, improvement requires multiple context understanding and processing in a meaningful way.
no code implementations • 27 Jan 2020 • Chiranjib Sur
Region visual features enhance the generative capability of the machines based on features, however they lack proper interaction attentional perceptions and thus ends up with biased or uncorrelated sentences or pieces of misinformation.
no code implementations • 22 Nov 2019 • Chiranjib Sur
Image captioning can be improved if the structure of the graphical representations can be formulated with conceptual positional binding.
no code implementations • 22 Nov 2019 • Chiranjib Sur
Bayesian prior definition of different embedding helps in better characterization of the sentences based on the natural language structure related to parts of speech and other semantic level categorization in a form which is machine interpret-able and inherits the characteristics of the Tensor Representation binding and unbinding based on the mutually orthogonality.
no code implementations • 17 Dec 2018 • Chiranjib Sur
Progress in image captioning is gradually getting complex as researchers try to generalized the model and define the representation between visual features and natural language processing.
no code implementations • 14 Oct 2013 • Chiranjib Sur, Anupam Shukla
The results clearly demarcates the GHOSA algorithm as an efficient algorithm specially considering that the number of algorithms for the discrete optimization is very low and robust and more explorative algorithm is required in this age of social networking and mostly graph based problem scenarios.