Zobrazeno 1 - 10
of 17
pro vyhledávání: '"Wu, Guanhang"'
Object detection is the key technique to a number of Computer Vision applications, but it often requires large amounts of annotated data to achieve decent results. Moreover, for pedestrian detection specifically, the collected data might contain some
Externí odkaz:
http://arxiv.org/abs/2307.11360
Recently, one-stage trackers that use a joint model to predict both detections and appearance embeddings in one forward pass received much attention and achieved state-of-the-art results on the Multi-Object Tracking (MOT) benchmarks. However, their s
Externí odkaz:
http://arxiv.org/abs/2205.05583
Autor:
Li, Kunpeng, Zhang, Zizhao, Wu, Guanhang, Xiong, Xuehan, Lee, Chen-Yu, Lu, Zhichao, Fu, Yun, Pfister, Tomas
Learning visual knowledge from massive weakly-labeled web videos has attracted growing research interests thanks to the large corpus of easily accessible video data on the Internet. However, for video action recognition, the action of interest might
Externí odkaz:
http://arxiv.org/abs/2101.03713
In static monitoring cameras, useful contextual information can stretch far beyond the few seconds typical video understanding models might see: subjects may exhibit similar behavior over multiple days, and background objects remain static. Due to po
Externí odkaz:
http://arxiv.org/abs/1912.03538
Spectral graph convolutional neural networks (CNNs) require approximation to the convolution to alleviate the computational complexity, resulting in performance loss. This paper proposes the topology adaptive graph convolutional network (TAGCN), a no
Externí odkaz:
http://arxiv.org/abs/1710.10370
In this paper, we develop deep spatio-temporal neural networks to sequentially count vehicles from low quality videos captured by city cameras (citycams). Citycam videos have low resolution, low frame rate, high occlusion and large perspective, makin
Externí odkaz:
http://arxiv.org/abs/1707.09476
Autor:
Zhao, Han, Zhang, Shanghang, Wu, Guanhang, Costeira, João P., Moura, José M. F., Gordon, Geoffrey J.
While domain adaptation has been actively researched in recent years, most theoretical results and algorithms focus on the single-source-single-target adaptation setting. Naive application of such algorithms on multiple source domain adaptation probl
Externí odkaz:
http://arxiv.org/abs/1705.09684
Understanding traffic density from large-scale web camera (webcam) videos is a challenging problem because such videos have low spatial and temporal resolution, high occlusion and large perspective. To deeply understand traffic density, we explore bo
Externí odkaz:
http://arxiv.org/abs/1703.05868
Autor:
Salem, Ghadi, Krynitsky, Jonathan, Kirkland, Brett, Lin, Eugene, Chan, Aaron, Anfinrud, Simeon, Anderson, Sarah, Garmendia-Cedillos, Marcial, Belayachi, Rhamy, Alonso-Cruz, Juan, Yu, Joshua, Iano-Fletcher, Anthony, Dold, George, Talbot, Tom, Kravitz, Alexxai V., Mitchell, James B., Wu, Guanhang, Dennis, John U., Hayes, Monson, Branson, Kristin
Publikováno v:
Advanced Concepts for Intelligent Vision Systems (9783319486796); 2016, p626-637, 12p
Publikováno v:
Journal of Materials Chemistry A; 3/28/2021, Vol. 9 Issue 12, p7261-7277, 17p