Zobrazeno 1 - 10
of 35
pro vyhledávání: '"Hou, Yunzhong"'
This study seeks to automate camera movement control for filming existing subjects into attractive videos, contrasting with the creation of non-existent content by directly generating the pixels. We select drone videos as our test case due to their r
Externí odkaz:
http://arxiv.org/abs/2412.09620
Jointly considering multiple camera views (multi-view) is very effective for pedestrian detection under occlusion. For such multi-view systems, it is critical to have well-designed camera configurations, including camera locations, directions, and fi
Externí odkaz:
http://arxiv.org/abs/2312.02144
Multiview camera setups have proven useful in many computer vision applications for reducing ambiguities, mitigating occlusions, and increasing field-of-view coverage. However, the high computational cost associated with multiple views poses a signif
Externí odkaz:
http://arxiv.org/abs/2303.06145
Color and structure are the two pillars that combine to give an image its meaning. Interested in critical structures for neural network recognition, we isolate the influence of colors by limiting the color space to just a few bits, and find structure
Externí odkaz:
http://arxiv.org/abs/2208.08438
Semi-supervised semantic segmentation needs rich and robust supervision on unlabeled data. Consistency learning enforces the same pixel to have similar features in different augmented views, which is a robust signal but neglects relationships with ot
Externí odkaz:
http://arxiv.org/abs/2208.08437
Data associations in multi-target multi-camera tracking (MTMCT) usually estimate affinity directly from re-identification (re-ID) feature distances. However, we argue that it might not be the best choice given the difference in matching scopes betwee
Externí odkaz:
http://arxiv.org/abs/2112.07664
Label-free model evaluation, or AutoEval, estimates model accuracy on unlabeled test sets, and is critical for understanding model behaviors in various unseen environments. In the absence of image labels, based on dataset representations, we estimate
Externí odkaz:
http://arxiv.org/abs/2112.00694
Regularization-based methods are beneficial to alleviate the catastrophic forgetting problem in class-incremental learning. With the absence of old task images, they often assume that old knowledge is well preserved if the classifier produces similar
Externí odkaz:
http://arxiv.org/abs/2109.00328
Consider a scenario where we are supplied with a number of ready-to-use models trained on a certain source domain and hope to directly apply the most appropriate ones to different target domains based on the models' relative performance. Ideally we s
Externí odkaz:
http://arxiv.org/abs/2108.10310
Autor:
Hou, Yunzhong, Zheng, Liang
Multiview detection incorporates multiple camera views to deal with occlusions, and its central problem is multiview aggregation. Given feature map projections from multiple views onto a common ground plane, the state-of-the-art method addresses this
Externí odkaz:
http://arxiv.org/abs/2108.05888