Zobrazeno 1 - 10
of 300
pro vyhledávání: '"Li Jinglun"'
Autor:
Guo, Pinxue, Li, Wanyun, Huang, Hao, Hong, Lingyi, Zhou, Xinyu, Chen, Zhaoyu, Li, Jinglun, Jiang, Kaixun, Zhang, Wei, Zhang, Wenqiang
Multi-modal Video Object Segmentation (VOS), including RGB-Thermal, RGB-Depth, and RGB-Event, has garnered attention due to its capability to address challenging scenarios where traditional VOS methods struggle, such as extreme illumination, rapid mo
Externí odkaz:
http://arxiv.org/abs/2409.19342
Autor:
Hong, Lingyi, Li, Jinglun, Zhou, Xinyu, Yan, Shilin, Guo, Pinxue, Jiang, Kaixun, Chen, Zhaoyu, Gao, Shuyong, Zhang, Wei, Lu, Hong, Zhang, Wenqiang
Transformer-based trackers have established a dominant role in the field of visual object tracking. While these trackers exhibit promising performance, their deployment on resource-constrained devices remains challenging due to inefficiencies. To imp
Externí odkaz:
http://arxiv.org/abs/2409.17564
Autor:
Li, Jinglun, Zhou, Xinyu, Guo, Pinxue, Sun, Yixuan, Huang, Yiwen, Ge, Weifeng, Zhang, Wenqiang
Detecting out-of-distribution inputs for visual recognition models has become critical in safe deep learning. This paper proposes a novel hierarchical visual category modeling scheme to separate out-of-distribution data from in-distribution data thro
Externí odkaz:
http://arxiv.org/abs/2408.15580
Autor:
Li, Jinglun, Zhou, Xinyu, Jiang, Kaixun, Hong, Lingyi, Guo, Pinxue, Chen, Zhaoyu, Ge, Weifeng, Zhang, Wenqiang
Multimodal fusion, leveraging data like vision and language, is rapidly gaining traction. This enriched data representation improves performance across various tasks. Existing methods for out-of-distribution (OOD) detection, a critical area where AI
Externí odkaz:
http://arxiv.org/abs/2408.15566
Autor:
Haze, Shinsuke, Li, Jinglun, Dorer, Dominik, D'Incao, José P., Julienne, Paul S., Tiemann, Eberhard, Deiß, Markus, Denschlag, Johannes Hecker
Gaining control over chemical reactions on the quantum level is a central goal of the modern field of cold and ultracold chemistry. Here, we demonstrate a novel method to coherently steer reaction flux of a three-body recombination process across dif
Externí odkaz:
http://arxiv.org/abs/2408.14922
Autor:
Guo, Haijing, Wang, Jiafeng, Chen, Zhaoyu, Jiang, Kaixun, Hong, Lingyi, Guo, Pinxue, Li, Jinglun, Zhang, Wenqiang
Deep neural networks (DNNs) are known to be susceptible to adversarial examples, leading to significant performance degradation. In black-box attack scenarios, a considerable attack performance gap between the surrogate model and the target model per
Externí odkaz:
http://arxiv.org/abs/2408.05745
Autor:
Hong, Lingyi, Liu, Zhongying, Chen, Wenchao, Tan, Chenzhi, Feng, Yuang, Zhou, Xinyu, Guo, Pinxue, Li, Jinglun, Chen, Zhaoyu, Gao, Shuyong, Zhang, Wei, Zhang, Wenqiang
Video object segmentation (VOS) aims to distinguish and track target objects in a video. Despite the excellent performance achieved by off-the-shell VOS models, existing VOS benchmarks mainly focus on short-term videos lasting about 5 seconds, where
Externí odkaz:
http://arxiv.org/abs/2404.19326
Autor:
Hong, Lingyi, Yan, Shilin, Zhang, Renrui, Li, Wanyun, Zhou, Xinyu, Guo, Pinxue, Jiang, Kaixun, Chen, Yiting, Li, Jinglun, Chen, Zhaoyu, Zhang, Wenqiang
Visual object tracking aims to localize the target object of each frame based on its initial appearance in the first frame. Depending on the input modility, tracking tasks can be divided into RGB tracking and RGB+X (e.g. RGB+N, and RGB+D) tracking. D
Externí odkaz:
http://arxiv.org/abs/2403.09634
Autor:
Guo, Pinxue, Hong, Lingyi, Zhou, Xinyu, Gao, Shuyong, Li, Wanyun, Li, Jinglun, Chen, Zhaoyu, Li, Xiaoqiang, Zhang, Wei, Zhang, Wenqiang
Video Object Segmentation (VOS) task aims to segment objects in videos. However, previous settings either require time-consuming manual masks of target objects at the first frame during inference or lack the flexibility to specify arbitrary objects o
Externí odkaz:
http://arxiv.org/abs/2403.06130
Autor:
Zhou, Xinyu, Guo, Pinxue, Hong, Lingyi, Li, Jinglun, Zhang, Wei, Ge, Weifeng, Zhang, Wenqiang
Reference features from a template or historical frames are crucial for visual object tracking. Prior works utilize all features from a fixed template or memory for visual object tracking. However, due to the dynamic nature of videos, the required re
Externí odkaz:
http://arxiv.org/abs/2402.14392