Search Results for author:
Found 10 papers, 5 papers with code
PhraseOut: A Code Mixed Data Augmentation Method for MultilingualNeural Machine Tranlsation
Back-translation aug- ments parallel data by translating monolingual sentences in the target side to source language.
IndicSTR12: A Dataset for Indic Scene Text Recognition
Several benchmark datasets and substantial work on deep learning models are available for Latin languages to meet this need.
Compressing Video Calls using Synthetic Talking Heads
We use a state-of-the-art face reenactment network to detect key points in the non-pivot frames and transmit them to the receiver.
Audio-Visual Face Reenactment
The identity-aware generator takes the source image and the warped motion features as input to generate a high-quality output with fine-grained details.
Visual Understanding of Complex Table Structures from Document Images
Tables in unstructured business documents are tough to parse due to the high diversity of layouts, varying alignments of contents, and the presence of empty cells.
Personalized One-Shot Lipreading for an ALS Patient
Apart from evaluating our approach on the ALS patient, we also extend it to people with hearing impairment relying extensively on lip movements to communicate.
More Parameters? No Thanks!
We propose a novel adaptation strategy, where we iteratively prune and retrain the redundant parameters of an MNMT to improve bilingual representations while retaining the multilinguality.
Towards Automatic Speech to Sign Language Generation
Since the current datasets are inadequate for generating sign language directly from speech, we collect and release the first Indian sign language dataset comprising speech-level annotations, text transcripts, and the corresponding sign-language videos.
Canonical Saliency Maps: Decoding Deep Face Models
As Deep Neural Network models for face processing tasks approach human-like performance, their deployment in critical applications such as law enforcement and access control has seen an upswing, where any failure may have far-reaching consequences.
Exploring Pair-Wise NMT for Indian Languages
In this paper, we address the task of improving pair-wise machine translation for specific low resource Indian languages.
