Zobrazeno 1 - 10
of 229
pro vyhledávání: '"Anbumani, P."'
CueCAn: Cue Driven Contextual Attention For Identifying Missing Traffic Signs on Unconstrained Roads
Unconstrained Asian roads often involve poor infrastructure, affecting overall road safety. Missing traffic signs are a regular part of such roads. Missing or non-existing object detection has been studied for locating missing curbs and estimating re
Externí odkaz:
http://arxiv.org/abs/2303.02641
Autor:
Dokania, Shubham, Hafez, A. H. Abdul, Subramanian, Anbumani, Chandraker, Manmohan, Jawahar, C. V.
Autonomous driving and assistance systems rely on annotated data from traffic and road scenarios to model and learn the various object relations in complex real-world scenarios. Preparation and training of deploy-able deep learning architectures requ
Externí odkaz:
http://arxiv.org/abs/2210.12878
High-quality structured data with rich annotations are critical components in intelligent vehicle systems dealing with road scenes. However, data curation and annotation require intensive investments and yield low-diversity scenarios. The recently gr
Externí odkaz:
http://arxiv.org/abs/2208.07943
Publikováno v:
Journal of Clinical and Diagnostic Research, Vol 18, Iss 03, Pp 08-11 (2024)
Adenomatoid Odontogenic Tumour (AOT) constitutes about 5% of all odontogenic tumours and is most commonly seen in young females, in association with impacted maxillary canines in a Dentigerous Cyst (DC) like relationship. Extrafollicular AOT is an un
Externí odkaz:
https://doaj.org/article/d950b915d4224e62810e7f5eb1cfd60e
Autor:
Goyal, Aman, Agarwal, Dev, Subramanian, Anbumani, Jawahar, C. V., Sarvadevabhatla, Ravi Kiran, Saluja, Rohit
In many Asian countries with unconstrained road traffic conditions, driving violations such as not wearing helmets and triple-riding are a significant source of fatalities involving motorcycles. Identifying and penalizing such riders is vital in curb
Externí odkaz:
http://arxiv.org/abs/2204.08364
Autor:
Bahety, Arpit, Saluja, Rohit, Sarvadevabhatla, Ravi Kiran, Subramanian, Anbumani, Jawahar, C. V.
Assessing the number of street trees is essential for evaluating urban greenery and can help municipalities employ solutions to identify tree-starved streets. It can also help identify roads with different levels of deforestation and afforestation ov
Externí odkaz:
http://arxiv.org/abs/2201.06569
Few-shot object detection (FSOD) localizes and classifies objects in an image given only a few data samples. Recent trends in FSOD research show the adoption of metric and meta-learning techniques, which are prone to catastrophic forgetting and class
Externí odkaz:
http://arxiv.org/abs/2111.06639
Localization and recognition of less-occurring road objects have been a challenge in autonomous driving applications due to the scarcity of data samples. Few-Shot Object Detection techniques extend the knowledge from existing base object classes to l
Externí odkaz:
http://arxiv.org/abs/2110.15074
Autor:
Garg, Prachi, Saluja, Rohit, Balasubramanian, Vineeth N, Arora, Chetan, Subramanian, Anbumani, Jawahar, C. V.
Recent efforts in multi-domain learning for semantic segmentation attempt to learn multiple geographical datasets in a universal, joint model. A simple fine-tuning experiment performed sequentially on three popular road scene segmentation datasets de
Externí odkaz:
http://arxiv.org/abs/2110.12205
Incremental few-shot learning has emerged as a new and challenging area in deep learning, whose objective is to train deep learning models using very few samples of new class data, and none of the old class data. In this work we tackle the problem of
Externí odkaz:
http://arxiv.org/abs/2108.08048