Zobrazeno 1 - 10
of 1 851
pro vyhledávání: '"Aarya"'
Autor:
Sreedasyam, Rachita1, Rao, Aishwarya1, Sachidanandan, Nidhi1, Sampath, Nalini1, Vasudevan, Shriram K.1 kv_shriram@cb.amrita.edu
Publikováno v:
Journal of Intelligent & Fuzzy Systems. 2017, Vol. 32 Issue 4, p2971-2976. 6p.
Recent advances in video question answering (VideoQA) offer promising applications, especially in traffic monitoring, where efficient video interpretation is critical. Within ITS, answering complex, real-time queries like "How many red cars passed in
Externí odkaz:
http://arxiv.org/abs/2412.01132
The curse of dimensionality poses a significant challenge to modern multilayer perceptron-based architectures, often causing performance stagnation and scalability issues. Addressing this limitation typically requires vast amounts of data. In contras
Externí odkaz:
http://arxiv.org/abs/2411.10622
Generative artificial intelligence poses new challenges around assessment, increasingly driving introductory programming educators to employ invigilated exams. But exams do not afford more authentic programming experiences that involve planning, impl
Externí odkaz:
http://arxiv.org/abs/2410.01010
Autor:
Ying, Lance, Liu, Jason Xinyu, Aarya, Shivam, Fang, Yizirui, Tellex, Stefanie, Tenenbaum, Joshua B., Shu, Tianmin
Spoken language instructions are ubiquitous in agent collaboration. However, in human-robot collaboration, recognition accuracy for human speech is often influenced by various speech and environmental factors, such as background noise, the speaker's
Externí odkaz:
http://arxiv.org/abs/2409.10849
Autor:
Kungurtsev, Vyacheslav, Apaar, Khandelwal, Aarya, Rastogi, Parth Sandeep, Chatterjee, Bapi, Mareček, Jakub
In this work, we demonstrate the Empirical Bayes approach to learning a Dynamic Bayesian Network. By starting with several point estimates of structure and weights, we can use a data-driven prior to subsequently obtain a model to quantify uncertainty
Externí odkaz:
http://arxiv.org/abs/2406.17831
Neural implicit representations have emerged as a powerful paradigm for 3D reconstruction. However, despite their success, existing methods fail to capture fine geometric details and thin structures, especially in scenarios where only sparse RGB view
Externí odkaz:
http://arxiv.org/abs/2406.04861
In Patil et. al 2024a, we developed a multitaper power spectrum estimation method, mtNUFFT, for analyzing time-series with quasi-regular spacing, and showed that it not only improves upon the statistical issues of the Lomb-Scargle periodogram, but al
Externí odkaz:
http://arxiv.org/abs/2405.18509
Autor:
Patil, Omkar, Shirbhate, Aarya
This report details the development of a networked distributed system named Group Communication System (GCS), implemented in Java to exemplify socket programming and communication protocols. GCS facilitates group-based client-server communication thr
Externí odkaz:
http://arxiv.org/abs/2404.10107
Autor:
Ying, Lance, Jha, Kunal, Aarya, Shivam, Tenenbaum, Joshua B., Torralba, Antonio, Shu, Tianmin
Verbal communication plays a crucial role in human cooperation, particularly when the partners only have incomplete information about the task, environment, and each other's mental state. In this paper, we propose a novel cooperative communication fr
Externí odkaz:
http://arxiv.org/abs/2403.11075