no code implementations • 26 Jun 2023 • Prashant Kumar, Dhruv Makwana, Onkar Susladkar, Anurag Mittal, Prem Kumar Kalra
In the real world however, LiDAR scans consist of non-stationary dynamic structures - moving and movable objects.
1 code implementation • 27 Jan 2022 • Saikat Dutta, Arulkumar Subramaniam, Anurag Mittal
Video frame interpolation aims to synthesize one or multiple frames between two consecutive frames in a video.
1 code implementation • 14 Nov 2021 • Arulkumar Subramaniam, Jayesh Vaidya, Muhammed Abdul Majeed Ameen, Athira Nambiar, Anurag Mittal
In this work, we propose to utilize the common rationale that a sequence of video frames capture a set of common objects and interactions between them, thus a notion of co-segmentation between the video frame features may equip the model with the ability to automatically focus on task-specific salient regions and improve the underlying task's performance in an end-to-end manner.
no code implementations • NeurIPS Workshop Deep_Invers 2021 • Saikat Dutta, Anurag Mittal
Video Frame Interpolation is an important video enhancement problem which aims to generate one or multiple frames between consecutive frames in video.
no code implementations • 28 Aug 2021 • Gouthaman KV, Anurag Mittal
This paper shows that the sequence model architecture used in the question-encoder has a significant role in the generalizability of VQA models.
no code implementations • 14 Jun 2021 • Sinzith Tatikonda, Athira Nambiar, Anurag Mittal
In this paper, we propose a novel holistic model in this regard viz., ``Face Age progression With Attribute Manipulation (FAWAM)", i. e. generating face images at different ages while simultaneously varying attributes and other subject specific characteristics.
1 code implementation • 12 Apr 2021 • Saikat Dutta, Nisarg A. Shah, Anurag Mittal
Input LR frames are super-resolved using a state-of-the-art Video Super-Resolution method.
1 code implementation • 3 Nov 2020 • Divya Kothandaraman, Athira Nambiar, Anurag Mittal
Practical autonomous driving systems face two crucial challenges: memory constraints and domain gap issues.
no code implementations • 2 Nov 2020 • Rahul Chakwate, Arulkumar Subramaniam, Anurag Mittal
Representation learning from 3D point clouds is challenging due to their inherent nature of permutation invariance and irregular distribution in space.
no code implementations • 7 Oct 2020 • Vikram Singh, Anurag Mittal
In this work, we propose an approach to divide the problem of image super-resolution into multiple sub-problems and then solve/conquer them with the help of a neural network.
no code implementations • 18 Aug 2020 • Gouthaman KV, Athira Nambiar, Kancheti Sai Srinivas, Anurag Mittal
Humans perform such a correlation with a strong linguistic understanding of the visual world.
no code implementations • ECCV 2020 • Gouthaman KV, Anurag Mittal
We demonstrate the effect of VGQE on three recent VQA models and achieve state-of-the-art results on the bias-sensitive split of the VQAv2 dataset; VQA-CPv2.
no code implementations • 18 Jan 2020 • Anubha Pandey, Ashish Mishra, Vinay Kumar Verma, Anurag Mittal, Hema A. Murthy
Conventional approaches to Sketch-Based Image Retrieval (SBIR) assume that the data of all the classes are available during training.
1 code implementation • 27 Jul 2019 • Manoj Kumar Lenka, Anubha Pandey, Anurag Mittal
Modifications to the structures is done to improve the global perception of the model.
no code implementations • ECCV 2018 • Sasi Kiran Yelamarthi, Shiva Krishna Reddy, Ashish Mishra, Anurag Mittal
In this paper, we propose a new bench mark for zero-shot SBIR where the model is evaluated on novel classes that are not seen during training.
1 code implementation • 31 Jul 2018 • Sasi Kiran Yelamarthi, Shiva Krishna Reddy, Ashish Mishra, Anurag Mittal
In this paper, we propose a new benchmark for zero-shot SBIR where the model is evaluated in novel classes that are not seen during training.
no code implementations • 27 Jan 2018 • Ashish Mishra, Vinay Kumar Verma, M Shiva Krishna Reddy, Arulkumar S, Piyush Rai, Anurag Mittal
In particular, we assume that the distribution parameters for any action class in the visual space can be expressed as a linear combination of a set of basis vectors where the combination weights are given by the attributes of the action class.
no code implementations • 3 Sep 2017 • Ashish Mishra, M Shiva Krishna Reddy, Anurag Mittal, Hema A. Murthy
By extensive testing on four benchmark datasets, we show that our model outperforms the state of the art, particularly in the more realistic generalized setting, where the training classes can also appear at the test time along with the novel classes.
no code implementations • 7 Jun 2017 • Santhosh K. Ramakrishnan, Swarna Kamlam Ravindran, Anurag Mittal
Experiments show improvements over a simple re-detect-and-match framework as well as KLT in terms of speed/accuracy on different real-world applications, especially at the object boundaries.
no code implementations • CVPR 2017 • Santhosh K. Ramakrishnan, Ambar Pal, Gaurav Sharma, Anurag Mittal
We study the problem of answering questions about images in the harder setting, where the test questions and corresponding images contain novel objects, which were not queried about in the training data.
1 code implementation • NeurIPS 2016 • Arulkumar Subramaniam, Moitreya Chatterjee, Anurag Mittal
A novel inexact matching technique then matches pixels in the first representation with those of the second.
1 code implementation • 31 Oct 2016 • Arulkumar Subramaniam, Vismay Patel, Ashish Mishra, Prashanth Balasubramanian, Anurag Mittal
We propose a novel approach for First Impressions Recognition in terms of the Big Five personality-traits from short videos.
no code implementations • CVPR 2016 • Swarna K. Ravindran, Anurag Mittal
In this paper, we propose a new approach for feature detection, tracking and re-detection that gives significantly improved results at the object boundaries.
no code implementations • 31 Oct 2015 • Sarthak Parui, Anurag Mittal
The object boundaries are represented as chains of connected segments and the database images are pre-processed to obtain such chains that have a high chance of containing the object.
no code implementations • 25 Apr 2015 • Smit Marvaniya, Raj Gupta, Anurag Mittal
The problem is difficult due to many factors such as intra-class variations, local deformations, articulations, viewpoint changes and missed and extraneous contour portions due to errors in shape extraction.
no code implementations • 21 Dec 2014 • Anoop Katti, Anurag Mittal
Two of the most common and strong manifestations of such unhandled interactions are self-occlusion among the parts and the confusion in the localization of the non-adjacent symmetric parts.
no code implementations • 5 Dec 2014 • Swarna Kamlam Ravindran, Anurag Mittal
Feature or interest points typically use information aggregation in 2D patches which does not remain stable at object boundaries when there is object motion against a significantly varying background.