no code implementations • NAACL 2022 • Himanshu Maheshwari, Nethraa Sivakumar, Shelly Jain, Tanvi Karandikar, Vinay Aggarwal, Navita Goyal, Sumit Shekhar
Linearly consuming (via scrolling or navigation through default table of content) these documents is time-consuming and challenging.
no code implementations • EMNLP 2020 • Hrituraj Singh, Sumit Shekhar
Chart Question Answering (CQA) is the task of answering natural language questions about visualisations in the chart image.
no code implementations • 1 Jun 2023 • Abisek Rajakumar Kalarani, Pushpak Bhattacharyya, Niyati Chhaya, Sumit Shekhar
We exploit context by pretraining our model with datasets of three tasks: news image captioning where the news article is the context, contextual visual entailment, and keyword extraction from the context.
no code implementations • 28 Feb 2023 • Prachi Singh, Srikrishna Karanam, Sumit Shekhar
We consider and propose a new problem of retrieving audio files relevant to multimodal design document inputs comprising both textual elements and visual imagery, e. g., birthday/greeting cards.
1 code implementation • 2 Jan 2023 • Sumit Shekhar, Max Reimann, Moritz Hilscher, Amir Semmo, Jürgen Döllner, Matthias Trapp
For stylization tasks, however, consistency control is an essential requirement as a certain amount of flickering adds to the artistic look and feel.
1 code implementation • 24 May 2022 • Divya Kothandaraman, Sumit Shekhar, Abhilasha Sancheti, Manoj Ghuhan, Tripti Shukla, Dinesh Manocha
SALAD has three key benefits: (i) it is task-agnostic, and can be applied across various visual tasks such as classification, segmentation and detection; (ii) it can handle shifts in output label space from the pre-trained source network to the target domain; (iii) it does not require access to source data for adaptation.
no code implementations • 9 Mar 2022 • Sumit Shekhar, Max Reimann, Amir Semmo, Sebastian Pasewaldt, Jürgen Döllner, Matthias Trapp
For videos captured in the wild, we perform a user study to demonstrate the preference for our method in comparison to state-of-the-art approaches.
1 code implementation • 30 Nov 2021 • Suraj Kothawade, Saikat Ghosh, Sumit Shekhar, Yu Xiang, Rishabh Iyer
We propose TALISMAN, a novel framework for Targeted Active Learning or object detectIon with rare slices using Submodular MutuAl iNformation.
no code implementations • 1 Oct 2021 • Sumit Shekhar, Bhanu Prakash Reddy Guda, Ashutosh Chaubey, Ishan Jindal, Avneet Jain
We propose novel rewards to account for class imbalance and user feedback in the annotation interface, to improve the active learning method.
no code implementations • 30 Jul 2019 • Ritwick Chaudhry, Sumit Shekhar, Utkarsh Gupta, Pranav Maneriker, Prann Bansal, Ajay Joshi
LEAF-QA being constructed from real-world sources, requires a novel architecture to enable question answering.
no code implementations • 17 Jul 2017 • Sumit Shekhar, Dhruv Singal, Harvineet Singh, Manav Kedia, Akhil Shetty
With the explosion of video content on the Internet, there is a need for research on methods for video analysis which take human cognition into account.
no code implementations • 10 Jul 2017 • Sumit Shekhar, Vishal M. Patel, Rama Chellappa
Recognition of low resolution face images is a challenging problem in many practical face recognition systems.
no code implementations • CVPR 2015 • Ashish Shrivastava, Mohammad Rastegari, Sumit Shekhar, Rama Chellappa, Larry S. Davis
Many existing recognition algorithms combine different modalities based on training accuracy but do not consider the possibility of noise at test time.
no code implementations • CVPR 2013 • Sumit Shekhar, Vishal M. Patel, Hien V. Nguyen, Rama Chellappa
Data-driven dictionaries have produced state-of-the-art results in various classification tasks.