Zobrazeno 1 - 10
of 289
pro vyhledávání: '"Prasad, Dilip K"'
Autor:
Agarwal, Rohit, Naidu, Karaka Prasanth, Horsch, Alexander, Agarwal, Krishna, Prasad, Dilip K.
We study the online learning problem characterized by the varying input feature space of streaming data. Although LSTMs have been employed to effectively capture the temporal nature of streaming data, they cannot handle the dimension-varying streams
Externí odkaz:
http://arxiv.org/abs/2410.17394
Handling haphazard streaming data, such as data from edge devices, presents a challenging problem. Over time, the incoming data becomes inconsistent, with missing, faulty, or new inputs reappearing. Therefore, it requires models that are reliable. Re
Externí odkaz:
http://arxiv.org/abs/2409.10242
S\'ami, an indigenous language group comprising multiple languages, faces digital marginalization due to the limited availability of data and sophisticated language models designed for its linguistic intricacies. This work focuses on increasing techn
Externí odkaz:
http://arxiv.org/abs/2405.05777
The domain of online learning has experienced multifaceted expansion owing to its prevalence in real-life applications. Nonetheless, this progression operates under the assumption that the input feature space of the streaming data remains constant. I
Externí odkaz:
http://arxiv.org/abs/2404.04903
Untrimmed videos have interrelated events, dependencies, context, overlapping events, object-object interactions, domain specificity, and other semantics that are worth highlighting while describing a video in natural language. Owing to such a vast d
Externí odkaz:
http://arxiv.org/abs/2311.02538
Autor:
Agarwal, Rohit, Sinha, Aman, Vishwakarma, Ayan, Coubez, Xavier, Clausel, Marianne, Constant, Mathieu, Horsch, Alexander, Prasad, Dilip K.
Modeling irregularly-sampled time series (ISTS) is challenging because of missing values. Most existing methods focus on handling ISTS by converting irregularly sampled data into regularly sampled data via imputation. These models assume an underlyin
Externí odkaz:
http://arxiv.org/abs/2309.08698
Nearest neighbor (NN) sampling provides more semantic variations than pre-defined transformations for self-supervised learning (SSL) based image recognition problems. However, its performance is restricted by the quality of the support set, which hol
Externí odkaz:
http://arxiv.org/abs/2308.06983
Global contexts in images are quite valuable in image-to-image translation problems. Conventional attention-based and graph-based models capture the global context to a large extent, however, these are computationally expensive. Moreover, the existin
Externí odkaz:
http://arxiv.org/abs/2307.04149
Autor:
Arora, Gauri, Butola, Ankit, Rajput, Ruchi, Agarwal, Rohit, Agarwal, Krishna, Horsch, Alexander, Prasad, Dilip K, Senthilkumaran, Paramasivam
Structured beams carrying topological defects, namely phase and Stokes singularities, have gained extensive interest in numerous areas of optics. The non-separable spin and orbital angular momentum states of hybridly polarized Stokes singular beams p
Externí odkaz:
http://arxiv.org/abs/2306.05974
Publikováno v:
Transactions on Machine Learning Research, 2023
Many real-world applications based on online learning produce streaming data that is haphazard in nature, i.e., contains missing features, features becoming obsolete in time, the appearance of new features at later points in time and a lack of clarit
Externí odkaz:
http://arxiv.org/abs/2303.05155