Zobrazeno 1 - 10
of 220
pro vyhledávání: '"Kapadia, Mubbasir"'
Autor:
Qingze, Liu, Li, Danrui, Sohn, Samuel S., Yoon, Sejong, Kapadia, Mubbasir, Pavlovic, Vladimir
Accurate prediction of human or vehicle trajectories with good diversity that captures their stochastic nature is an essential task for many applications. However, many trajectory prediction models produce unreasonable trajectory samples that focus o
Externí odkaz:
http://arxiv.org/abs/2410.10804
Digital storytelling, essential in entertainment, education, and marketing, faces challenges in production scalability and flexibility. The StoryAgent framework, introduced in this paper, utilizes Large Language Models and generative tools to automat
Externí odkaz:
http://arxiv.org/abs/2406.10478
Vector fields are widely used to represent and model flows for many science and engineering applications. This paper introduces a novel neural network architecture for learning tangent vector fields that are intrinsically defined on manifold surfaces
Externí odkaz:
http://arxiv.org/abs/2406.09648
We study, from an empirical standpoint, the efficacy of synthetic data in real-world scenarios. Leveraging synthetic data for training perception models has become a key strategy embraced by the community due to its efficiency, scalability, perfect a
Externí odkaz:
http://arxiv.org/abs/2403.16244
Autor:
Li, Danrui, Schwartz, Mathew, Sohn, Samuel S., Yoon, Sejong, Pavlovic, Vladimir, Kapadia, Mubbasir
Publikováno v:
Transportation Research Part C: Emerging Technologies 162 (2024): 104583
For transportation hubs, leveraging pedestrian flows for commercial activities presents an effective strategy for funding maintenance and infrastructure improvements. However, this introduces new challenges, as consumer behaviors can disrupt pedestri
Externí odkaz:
http://arxiv.org/abs/2403.14892
Autor:
Chang, Che-Jui, Sohn, Samuel S., Zhang, Sen, Jayashankar, Rajath, Usman, Muhammad, Kapadia, Mubbasir
Previous studies regarding the perception of emotions for embodied virtual agents have shown the effectiveness of using virtual characters in conveying emotions through interactions with humans. However, creating an autonomous embodied conversational
Externí odkaz:
http://arxiv.org/abs/2309.15311
Autor:
Chang, Che-Jui, Li, Danrui, Patel, Deep, Goel, Parth, Zhou, Honglu, Moon, Seonghyeon, Sohn, Samuel S., Yoon, Sejong, Pavlovic, Vladimir, Kapadia, Mubbasir
The study of complex human interactions and group activities has become a focal point in human-centric computer vision. However, progress in related tasks is often hindered by the challenges of obtaining large-scale labeled datasets from real-world s
Externí odkaz:
http://arxiv.org/abs/2306.16772
Autor:
Zhou, Honglu, Martín-Martín, Roberto, Kapadia, Mubbasir, Savarese, Silvio, Niebles, Juan Carlos
Our goal is to learn a video representation that is useful for downstream procedure understanding tasks in instructional videos. Due to the small amount of available annotations, a key challenge in procedure understanding is to be able to extract fro
Externí odkaz:
http://arxiv.org/abs/2303.18230
Autor:
Moon, Seonghyeon, Sohn, Samuel S., Zhou, Honglu, Yoon, Sejong, Pavlovic, Vladimir, Khan, Muhammad Haris, Kapadia, Mubbasir
FSS(Few-shot segmentation) aims to segment a target class using a small number of labeled images(support set). To extract information relevant to the target class, a dominant approach in best-performing FSS methods removes background features using a
Externí odkaz:
http://arxiv.org/abs/2212.04673
Autor:
Qiao, Gang, Hu, Kaidong, Moon, Seonghyeon, Sohn, Samuel S., Yoon, Sejong, Kapadia, Mubbasir, Pavlovic, Vladimir
Learning-based approaches to modeling crowd motion have become increasingly successful but require training and evaluation on large datasets, coupled with complex model selection and parameter tuning. To circumvent this tremendously time-consuming pr
Externí odkaz:
http://arxiv.org/abs/2211.00817