Anshul Mittal

Anshul Mittal

Auto-generated profile, based on publicly available information

Anshul Mittal

Microsoft, Noida, India

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 April 2019 in IEEE Sensors Journal
Verified
Journal Article
Closed access
AMAnshul Mittal
Anshul Mittal
PKPradeep Kumar
Pradeep Kumar
PRPartha Roy
Partha Roy
RBRaman Balasubramanian
Raman Balasubramanian
BCBidyut B. Chaudhuri
Bidyut B. Chaudhuri
Sign language facilitates communication between hearing impaired peoples and the rest of the society. A number of sign language recognition (SLR) systems have been developed by researchers, but they are limited to isolated sign gestures only. In this paper, we propose a modified long short-term memory (LSTM) model for continuous sequences of gestures or continuous SLR that recognizes a sequence of connected gestures. It is based on splitting of continuous signs into sub-units and modeling them with neural networks. Thus, the consideration of a different combination of sub-units is not required during training. The proposed system has been tested with 942 signed sentences of Indian Sign Language (ISL). These sign sentences are recognized using 35 different sign words. The average accuracy of 72.3% and 89.5% has been recorded on signed sentences and isolated sign words, respectively.

27 February 2023
Verified
Conference Paper
Open access
KDKunal Dahiya
Kunal Dahiya
NGNilesh Gupta
Nilesh Gupta
DSDeepak Saini
Deepak Saini
ASAkshay Soni
Akshay Soni
YWYajun Wang
Yajun Wang
MVManik Varma
Manik Varma
Extreme Classification (XC) seeks to tag data points with the most relevant subset of labels from an extremely large label set. Performing deep XC with dense, learnt representations for data points and labels has attracted much attention due to its superiority over earlier XC methods that used sparse, hand-crafted features. Negative mining techniques have emerged as a critical component of all deep XC methods, allowing them to scale to millions of labels. However, despite recent advances, training deep XC models with large encoder architectures such as transformers remains challenging. This paper notices that memory overheads of popular negative mining techniques often force mini-batch sizes to remain small and slow training down. In response, this paper introduces NGAME, a light-weight mini-batch creation technique that offers provably accurate in-batch negative samples. This allows training with larger mini-batches offering significantly faster convergence and higher accuracies than existing negative sampling techniques. NGAME was found to be up to 16% more accurate than state-of-the-art methods on a wide array of benchmark datasets for extreme classification, as well as 3% more accurate at retrieving search engine queries in response to a user webpage visit to show personalized ads. In live A/B tests on a popular search engine, NGAME yielded up to 23% gains in click-through-rates. Code for NGAME is available at https://github.com/Extreme-classification/ngame

22 June 2013
Verified
Conference Paper
Closed access
KSKidambi Sreenivas
Kidambi Sreenivas
CHChristopher B. Hilbert
Christopher B. Hilbert
AMAnshul Mittal
Anshul Mittal
LHLevi Hereth
Levi Hereth
LTLafayette Taylor
Lafayette Taylor

8 May 2025
Verified
Conference Paper
Open access
AMAnshul Mittal
Anshul Mittal
SMShikhar Mohan
Shikhar Mohan
DSDeepak Saini
Deepak Saini
SASiddarth Asokan
Siddarth Asokan
SPSuchith Chidananda Prabhu
Suchith Chidananda Prabhu
MVManik Varma
Manik Varma