3 Hits in 1.2 sec


Dyut Kumar Sil, Srinivasan H. Sengamedu, Chiranjib Bhattacharyya
2011 Proceedings of the 20th international conference companion on World wide web - WWW '11  
We propose a new paradigm for displaying comments: showing comments alongside parts of the article they correspond to. We evaluate the effectiveness of various approaches for this task and show that a combination of bag of words and topic models performs the best.
doi:10.1145/1963192.1963256 dblp:conf/www/SilSB11 fatcat:zryvvh27zzcivbrjckeuvfytwu

An Adaptive Fuzzy Technique for Real-Time Detection of Multiple Faces against a Complex Background

Dyut Kumar Sil, Subhadip Basu, Mita Nasipuri
2010 International Journal of Computer Applications  
This paper describes a real-time face detection system which is capable of processing video frames extremely rapidly while achieving high detection rate. The primary contribution of this paper is development of a fast algorithm for partitioning each frame into sub-images, detection of potential facial sub-images and real-time clustering of such potential subimages into isolated objects/faces. A set of experiments in the domain of real-time face detection are presented. The performance of the
more » ... tem is comparable to some well known previous systems [5, 6, 8, 9] . Being implemented on a conventional desktop, face detection could be done at the rate of 13 frames per second.
doi:10.5120/543-707 fatcat:xtaqrprhvnaulpzu45pdpjzfwm

Training Language Models under Resource Constraints for Adversarial Advertisement Detection

Eshwar Shamanna Girishekar, Shiv Surya, Nishant Nikhil, Dyut Kumar Sil, Sumit Negi, Aruna Rajan
2021 Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Papers   unpublished
Advertising on e-commerce and social media sites deliver ad impressions at web scale on a daily basis driving value to both shoppers and advertisers. This scale necessitates programmatic ways of detecting unsuitable content in ads to safeguard customer experience and trust. This paper focusses on techniques for training text classification models under resource constraints, built as part of automated solutions for advertising content moderation. We show how weak supervision, curriculum learning
more » ... and multi-lingual training can be applied effectively to fine-tune BERT and its variants for text classification tasks in conjunction with different data augmentation strategies. Our extensive experiments on multiple languages show that these techniques detect adversarial ad categories with a substantial gain in precision at high recall threshold over the baseline.
doi:10.18653/v1/2021.naacl-industry.35 fatcat:b2x7l3yme5dctkzdwsxb7bhpcy