Zobrazeno 1 - 10
of 10 517
pro vyhledávání: '"Ma, Yue"'
Unsupervised anomaly detection is a challenging computer vision task, in which 2D-based anomaly detection methods have been extensively studied. However, multimodal anomaly detection based on RGB images and 3D point clouds requires further investigat
Externí odkaz:
http://arxiv.org/abs/2409.05378
Autor:
Chen, Qihua, Ma, Yue, Wang, Hongfa, Yuan, Junkun, Zhao, Wenzhe, Tian, Qi, Wang, Hongmei, Min, Shaobo, Chen, Qifeng, Liu, Wei
This paper explores higher-resolution video outpainting with extensive content generation. We point out common issues faced by existing methods when attempting to largely outpaint videos: the generation of low-quality content and limitations imposed
Externí odkaz:
http://arxiv.org/abs/2409.01055
Forward regression is a crucial methodology for automatically identifying important predictors from a large pool of potential covariates. In contexts with moderate predictor correlation, forward selection techniques can achieve screening consistency.
Externí odkaz:
http://arxiv.org/abs/2408.12272
Autor:
Pan, Paoqiang, Hu, Kewei, Huang, Xiao, Ying, Wei, Xie, Xiaoxuan, Ma, Yue, Zhang, Naizhong, Kang, Hanwen
Smart Micro Aerial Vehicles (MAVs) have transformed infrastructure inspection by enabling efficient, high-resolution monitoring at various stages of construction, including hard-to-reach areas. Traditional manual operation of drones in GPS-denied env
Externí odkaz:
http://arxiv.org/abs/2408.06030
Autor:
Liao, Zhichao, Huang, Di, Fang, Heming, Ma, Yue, Piao, Fengyuan, Li, Xinghui, Zeng, Long, Feng, Pingfa
Drawing freehand sketches of mechanical components on multimedia devices for AI-based engineering modeling has become a new trend. However, its development is being impeded because existing works cannot produce suitable sketches for data-driven resea
Externí odkaz:
http://arxiv.org/abs/2408.05966
Dual phase xenon time projection chambers (TPCs) detect both the scintillation photons and ionization electrons created by energy depositions within the liquid xenon (LXe) volume. The electrons are extracted from the interaction site through a gas ga
Externí odkaz:
http://arxiv.org/abs/2408.01646
Graph neural networks (GNNs) have achieved significant success in various applications. Most GNNs learn the node features with information aggregation of its neighbors and feature transformation in each layer. However, the node features become indist
Externí odkaz:
http://arxiv.org/abs/2407.19231
Video editing is an emerging task, in which most current methods adopt the pre-trained text-to-image (T2I) diffusion model to edit the source video in a zero-shot manner. Despite extensive efforts, maintaining the temporal consistency of edited video
Externí odkaz:
http://arxiv.org/abs/2406.08850
Autor:
Xue, Jingyun, Wang, Hongfa, Tian, Qi, Ma, Yue, Wang, Andong, Zhao, Zhiyuan, Min, Shaobo, Zhao, Wenzhe, Zhang, Kaihao, Shum, Heung-Yeung, Liu, Wei, Liu, Mengyang, Luo, Wenhan
Pose-controllable character video generation is in high demand with extensive applications for fields such as automatic advertising and content creation on social media platforms. While existing character image animation methods using pose sequences
Externí odkaz:
http://arxiv.org/abs/2406.03035
Autor:
Ma, Yue, Liu, Hongyu, Wang, Hongfa, Pan, Heng, He, Yingqing, Yuan, Junkun, Zeng, Ailing, Cai, Chengfei, Shum, Heung-Yeung, Liu, Wei, Chen, Qifeng
We present Follow-Your-Emoji, a diffusion-based framework for portrait animation, which animates a reference portrait with target landmark sequences. The main challenge of portrait animation is to preserve the identity of the reference portrait and t
Externí odkaz:
http://arxiv.org/abs/2406.01900