1 code implementation • 1 Feb 2024 • Simar Kareer, Vivek Vijaykumar, Harsh Maheshwari, Prithvijit Chattopadhyay, Judy Hoffman, Viraj Prabhu
While the vast majority of prior work has studied this as a frame-level Image-DAS problem, a few Video-DAS works have sought to additionally leverage the temporal signal present in adjacent frames.
1 code implementation • 21 Apr 2023 • Harsh Maheshwari, Yen-Cheng Liu, Zsolt Kira
We create the first benchmark for semi-supervised multi-modal semantic segmentation and also report the robustness to missing modalities.
Ranked #1 on Semantic Segmentation on SUN-RGBD (Mean IoU (test) metric, using extra training data)
RGBD Semantic Segmentation Robust Semi-Supervised RGBD Semantic Segmentation +3
1 code implementation • 17 Jul 2022 • Harsh Maheshwari
ImageNet trained PyTorch models are generally preferred as the off-the-shelf models for direct use or for initialisation in most computer vision tasks.
1 code implementation • 2 May 2022 • Debopriyo Banerjee, Harsh Maheshwari, Lucky Dhakad1, Arnab Bhattacharya1, Niloy Ganguly, Muthusamy Chelliah, Suyash Agarwal1
Fashion recommendation has witnessed a phenomenal growth of research, particularly in the domains of shop-the-look, contextaware outfit creation, personalizing outfit creation etc.
no code implementations • 30 Mar 2022 • Debopriyo Banerjee, Lucky Dhakad, Harsh Maheshwari, Muthusamy Chelliah, Niloy Ganguly, Arnab Bhattacharya
Recommendation in the fashion domain has seen a recent surge in research in various areas, for example, shop-the-look, context-aware outfit creation, personalizing outfit creation, etc.
1 code implementation • 19 Jun 2021 • Vidit Goel, Jiachen Li, Shubhika Garg, Harsh Maheshwari, Humphrey Shi
Our method improves the masks from segmentation and propagation branches in an online manner using the Mask Selection Network (MSN) hence limiting the noise accumulation during mask tracking.
Ranked #26 on Video Instance Segmentation on YouTube-VIS validation
no code implementations • 17 Nov 2020 • Shreyas S, Harsh Maheshwari, Avijit Saha, Samik Datta, Shashank Jain, Disha Makhija, Anuj Nagpal, Sneha Shukla, Suyash S
Consumable categories, such as grocery and fast-moving consumer goods, are quintessential to the growth of e-commerce marketplaces in developing countries.
1 code implementation • 6 Nov 2019 • Zhiqiang Shen, Harsh Maheshwari, Weichen Yao, Marios Savvides
Unsupervised domain adaptive object detection aims to learn a robust detector in the domain shift circumstance, where the training (source) domain is label-rich with bounding box annotations, while the testing (target) domain is label-agnostic and the feature distributions between training and testing domains are dissimilar or even totally different.