no code implementations • 15 Jun 2023 • Rahee Walambe, Pranav Nayak, Ashmit Bhardwaj, Ketan Kotecha
In this work, a multimodal AI-based framework is proposed to monitor a person's working behavior and stress levels.
1 code implementation • 12 May 2023 • Aboli Marathe, Deva Ramanan, Rahee Walambe, Ketan Kotecha
WEDGE consists of 3360 images in 16 extreme weather conditions manually annotated with 16513 bounding boxes, supporting research in the tasks of weather classification and 2D object detection.
no code implementations • 14 Mar 2023 • Rajanikant Ghate, Nayan Kalnad, Rahee Walambe, Ketan Kotecha
In this work, we present an approach based on transfer learning, from a model trained on a secondary dataset, for the real time deployment of the depression screening tool based on the actigraphy data of users.
no code implementations • 3 Apr 2022 • Aboli Marathe, Pushkar Jain, Rahee Walambe, Ketan Kotecha
Modern applications such as self-driving cars and drones rely heavily upon robust object detection techniques.
no code implementations • 3 Apr 2022 • Aboli Marathe, Rahee Walambe, Ketan Kotecha
Methods to mitigate such bias which allows the OD models to perform better and improve the robustness are also demonstrated.
no code implementations • 20 Mar 2022 • Gargi Joshi, Ananya Srivastava, Bhargav Yagnik, Mohammed Hasan, Zainuddin Saiyed, Lubna A Gabralla, Ajith Abraham, Rahee Walambe, Ketan Kotecha
In this work, the integration of two machine learning approaches, namely domain adaptation and explainable AI, is proposed to address these two issues of generalized detection and explainability.
no code implementations • 7 Feb 2022 • Nikita Bhandari, Rahee Walambe, Ketan Kotecha, Satyajeet Khare
We discuss the types of missing values, and the methods and approaches usually employed in their imputation.
1 code implementation • 4 Aug 2021 • Parag Narkhede, Rahee Walambe, Shashi Poddar, Ketan Kotecha
This paper presents a novel method for attitude estimation of an object in 3D space by incremental learning of the Long-Short Term Memory (LSTM) network.
no code implementations • 29 Jul 2021 • Anil Rahate, Rahee Walambe, Sheela Ramanna, Ketan Kotecha
We present the comprehensive taxonomy of multimodal co-learning based on the challenges addressed by co-learning and associated implementations.
no code implementations • 8 Jul 2021 • Parag Narkhede, Shashi Poddar, Rahee Walambe, George Ghinea, Ketan Kotecha
The orientation angles computed from these sensors are combined using the sensor fusion methodologies to obtain accurate estimates.
no code implementations • 11 Jun 2021 • Parag Narkhede, Rahee Walambe, Shruti Mandaokar, Pulkit Chandel, Ketan Kotecha, George Ghinea
With the rapid industrialization and technological advancements, innovative engineering technologies which are cost effective, faster and easier to implement are essential.
no code implementations • 21 May 2021 • Hema Karande, Rahee Walambe, Victor Benjamin, Ketan Kotecha, T. S. Raghu
Credibility is the believability of the piece of information at hand.
no code implementations • 17 May 2021 • Gargi Joshi, Rahee Walambe, Ketan Kotecha
Artificial Intelligence techniques powered by deep neural nets have achieved much success in several application domains, most significantly and notably in the Computer Vision applications and Natural Language Processing tasks.
no code implementations • 17 May 2021 • Nikita Bhandari, Satyajeet Khare, Rahee Walambe, Ketan Kotecha
In this work, we studied methods for vector encoding and promoter classification using genome sequences of three distinct higher eukaryotes viz.
no code implementations • 11 May 2021 • Ananya Srivastava, Mohammed Hasan, Bhargav Yagnik, Rahee Walambe, Ketan Kotecha
Hate speech detection algorithms deployed by most social networking platforms are unable to filter out offensive and abusive content posted in these code-mixed languages.
no code implementations • 22 May 2018 • Narendra Patwardhan, Madhura Ingalhalikar, Rahee Walambe
This work introduces a novel activation unit that can be efficiently employed in deep neural nets (DNNs) and performs significantly better than the traditional Rectified Linear Units (ReLU).