Zobrazeno 1 - 10
of 6 593
pro vyhledávání: '"A. Rares"'
Most of the current vision-language models (VLMs) for videos struggle to understand videos longer than a few seconds. This is primarily due to the fact that they do not scale to utilizing a large number of frames. In order to address this limitation,
Externí odkaz:
http://arxiv.org/abs/2412.04729
Dimension Reduction via Sum-of-Squares and Improved Clustering Algorithms for Non-Spherical Mixtures
We develop a new approach for clustering non-spherical (i.e., arbitrary component covariances) Gaussian mixture models via a subroutine, based on the sum-of-squares method, that finds a low-dimensional separation-preserving projection of the input da
Externí odkaz:
http://arxiv.org/abs/2411.12438
Autor:
Xu, Yinshuang, Chen, Dian, Liu, Katherine, Zakharov, Sergey, Ambrus, Rares, Daniilidis, Kostas, Guizilini, Vitor
Incorporating inductive bias by embedding geometric entities (such as rays) as input has proven successful in multi-view learning. However, the methods adopting this technique typically lack equivariance, which is crucial for effective 3D learning. E
Externí odkaz:
http://arxiv.org/abs/2411.07326
Autor:
Irshad, Muhammad Zubair, Comi, Mauro, Lin, Yen-Chen, Heppert, Nick, Valada, Abhinav, Ambrus, Rares, Kira, Zsolt, Tremblay, Jonathan
Neural Fields have emerged as a transformative approach for 3D scene representation in computer vision and robotics, enabling accurate inference of geometry, 3D semantics, and dynamics from posed 2D data. Leveraging differentiable rendering, Neural F
Externí odkaz:
http://arxiv.org/abs/2410.20220
3D reconstruction from a single image is a long-standing problem in computer vision. Learning-based methods address its inherent scale ambiguity by leveraging increasingly large labeled and unlabeled datasets, to produce geometric priors capable of g
Externí odkaz:
http://arxiv.org/abs/2409.09896
Autor:
Franco, Nicola Rares
We develop a unified theoretical framework for low-rank approximation techniques in parametric settings, where traditional methods like Singular Value Decomposition (SVD), Proper Orthogonal Decomposition (POD), and Principal Component Analysis (PCA)
Externí odkaz:
http://arxiv.org/abs/2409.09102
Autor:
Chaudhury, Arkadeep Narayan, Vasiljevic, Igor, Zakharov, Sergey, Guizilini, Vitor, Ambrus, Rares, Narasimhan, Srinivasa, Atkeson, Christopher G.
Synthesizing accurate geometry and photo-realistic appearance of small scenes is an active area of research with compelling use cases in gaming, virtual reality, robotic-manipulation, autonomous driving, convenient product capture, and consumer-level
Externí odkaz:
http://arxiv.org/abs/2409.03061
Autor:
Cristian, Rares, Harsha, Pavithra, Ocejo, Clemente, Perakis, Georgia, Quanz, Brian, Spantidakis, Ioannis, Zerhouni, Hamza
Time series forecasting is an important task in many fields ranging from supply chain management to weather forecasting. Recently, Transformer neural network architectures have shown promising results in forecasting on common time series benchmark da
Externí odkaz:
http://arxiv.org/abs/2408.03872
Autor:
Dmitriev, Daniil, Buhai, Rares-Darius, Tiegel, Stefan, Wolters, Alexander, Novikov, Gleb, Sanyal, Amartya, Steurer, David, Yang, Fanny
We study the problem of estimating the means of well-separated mixtures when an adversary may add arbitrary outliers. While strong guarantees are available when the outlier fraction is significantly smaller than the minimum mixing weight, much less i
Externí odkaz:
http://arxiv.org/abs/2407.15792
Linear recurrent neural networks, such as State Space Models (SSMs) and Linear Recurrent Units (LRUs), have recently shown state-of-the-art performance on long sequence modelling benchmarks. Despite their success, their empirical performance is not w
Externí odkaz:
http://arxiv.org/abs/2407.07239