Zobrazeno 1 - 10
of 304
pro vyhledávání: '"Xu, Yihong"'
In autonomous driving, motion prediction aims at forecasting the future trajectories of nearby agents, helping the ego vehicle to anticipate behaviors and drive safely. A key challenge is generating a diverse set of future predictions, commonly addre
Externí odkaz:
http://arxiv.org/abs/2409.11172
Multi-object tracking (MOT) endeavors to precisely estimate the positions and identities of multiple objects over time. The prevailing approach, tracking-by-detection (TbD), first detects objects and then links detections, resulting in a simple yet e
Externí odkaz:
http://arxiv.org/abs/2407.10151
Autor:
Xu, Yihong, Zablocki, Éloi, Boulch, Alexandre, Puy, Gilles, Chen, Mickael, Bartoccioni, Florent, Samet, Nermin, Siméoni, Oriane, Gidaris, Spyros, Vu, Tuan-Hung, Bursuc, Andrei, Valle, Eduardo, Marlet, Renaud, Cord, Matthieu
Motion forecasting is crucial in autonomous driving systems to anticipate the future trajectories of surrounding agents such as pedestrians, vehicles, and traffic signals. In end-to-end forecasting, the model must jointly detect and track from sensor
Externí odkaz:
http://arxiv.org/abs/2406.08113
Light field is a type of image data that captures the 3D scene information by recording light rays emitted from a scene at various orientations. It offers a more immersive perception than classic 2D images but at the cost of huge data volume. In this
Externí odkaz:
http://arxiv.org/abs/2307.06143
Towards Motion Forecasting with Real-World Perception Inputs: Are End-to-End Approaches Competitive?
Autor:
Xu, Yihong, Chambon, Loïck, Zablocki, Éloi, Chen, Mickaël, Alahi, Alexandre, Cord, Matthieu, Pérez, Patrick
Motion forecasting is crucial in enabling autonomous vehicles to anticipate the future trajectories of surrounding agents. To do so, it requires solving mapping, detection, tracking, and then forecasting problems, in a multi-step pipeline. In this co
Externí odkaz:
http://arxiv.org/abs/2306.09281
Light fields are a type of image data that capture both spatial and angular scene information by recording light rays emitted by a scene from different orientations. In this context, spatial information is defined as features that remain static regar
Externí odkaz:
http://arxiv.org/abs/2304.06322
A central goal of modern magnetic resonance imaging (MRI) is to reduce the time required to produce high-quality images. Efforts have included hardware and software innovations such as parallel imaging, compressed sensing, and deep learning-based rec
Externí odkaz:
http://arxiv.org/abs/2303.13700
Autor:
Zhao, Jian, Jiang, Lulu, Matlock, Alex, Xu, Yihong, Zhu, Jiabei, Zhu, Hongbo, Tian, Lei, Wolozin, Benjamin, Cheng, Ji-Xin
Amyloid proteins are associated with a broad spectrum of neurodegenerative diseases. However, it remains a grand challenge to extract molecular structure information from intracellular amyloid proteins in their native cellular environment. To address
Externí odkaz:
http://arxiv.org/abs/2302.11769
Autor:
Xuan, Hanyu, Xu, Yihong, Chen, Shuo, Wu, Zhiliang, Yang, Jian, Yan, Yan, Alameda-Pineda, Xavier
The recent success of audio-visual representation learning can be largely attributed to their pervasive property of audio-visual synchronization, which can be used as self-annotated supervision. As a state-of-the-art solution, Audio-Visual Instance D
Externí odkaz:
http://arxiv.org/abs/2204.12366
Autor:
Zhao, Jian, Matlock, Alex, Zhu, Hongbo, Song, Ziqi, Zhu, Jiabei, Wang, Biao, Chen, Fukai, Zhan, Yuewei, Chen, Zhicong, Xu, Yihong, Lin, Xingchen, Tian, Lei, Cheng, Ji-Xin
Recovering molecular information remains a grand challenge in the widely used holographic and computational imaging technologies. To address this challenge, we developed a computational mid-infrared photothermal microscope, termed Bond-selective Inte
Externí odkaz:
http://arxiv.org/abs/2203.13630