Zobrazeno 1 - 10
of 57
pro vyhledávání: '"Roy, Aniket"'
Autor:
Roy, Aniket Basu
We study the problem of Covering Orthogonal Polygons with Rectangles. For polynomial-time algorithms, the best-known approximation factor is $O(\sqrt{\log n})$ when the input polygon may have holes [Kumar and Ramesh, STOC '99, SICOMP '03], and there
Externí odkaz:
http://arxiv.org/abs/2406.16209
Visual illusions play a significant role in understanding visual perception. Current methods in understanding and evaluating visual illusions are mostly deterministic filtering based approach and they evaluate on a handful of visual illusions, and th
Externí odkaz:
http://arxiv.org/abs/2402.04541
Diffusion models have advanced generative AI significantly in terms of editing and creating naturalistic images. However, efficiently improving generated image quality is still of paramount interest. In this context, we propose a generic "naturalness
Externí odkaz:
http://arxiv.org/abs/2311.09753
To improve the robustness of deep classifiers against adversarial perturbations, many approaches have been proposed, such as designing new architectures with better robustness properties (e.g., Lipschitz-capped networks), or modifying the training pr
Externí odkaz:
http://arxiv.org/abs/2310.00116
We study the query version of the approximate heavy hitter and quantile problems. In the former problem, the input is a parameter $\varepsilon$ and a set $P$ of $n$ points in $\mathbb{R}^d$ where each point is assigned a color from a set $C$, and we
Externí odkaz:
http://arxiv.org/abs/2305.03180
Autor:
Shah, Anshul, Roy, Aniket, Shah, Ketul, Mishra, Shlok Kumar, Jacobs, David, Cherian, Anoop, Chellappa, Rama
Supervised learning of skeleton sequence encoders for action recognition has received significant attention in recent times. However, learning such encoders without labels continues to be a challenging problem. While prior works have shown promising
Externí odkaz:
http://arxiv.org/abs/2304.00387
Visual recognition in a low-data regime is challenging and often prone to overfitting. To mitigate this issue, several data augmentation strategies have been proposed. However, standard transformations, e.g., rotation, cropping, and flipping provide
Externí odkaz:
http://arxiv.org/abs/2212.05404
Autor:
Dhar, Prithviraj, Gleason, Joshua, Roy, Aniket, Castillo, Carlos D., Phillips, P. Jonathon, Chellappa, Rama
Face recognition networks generally demonstrate bias with respect to sensitive attributes like gender, skintone etc. For gender and skintone, we observe that the regions of the face that a network attends to vary by the category of an attribute. This
Externí odkaz:
http://arxiv.org/abs/2112.09786
Multimodal learning is an emerging yet challenging research area. In this paper, we deal with multimodal sarcasm and humor detection from conversational videos and image-text pairs. Being a fleeting action, which is reflected across the modalities, s
Externí odkaz:
http://arxiv.org/abs/2110.10949