Zobrazeno 1 - 10
of 99
pro vyhledávání: '"Wen, Shilei"'
Autor:
Ma, Yuexiao, Li, Huixia, Zheng, Xiawu, Ling, Feng, Xiao, Xuefeng, Wang, Rui, Wen, Shilei, Chao, Fei, Ji, Rongrong
The significant resource requirements associated with Large-scale Language Models (LLMs) have generated considerable interest in the development of techniques aimed at compressing and accelerating neural networks. Among these techniques, Post-Trainin
Externí odkaz:
http://arxiv.org/abs/2403.12544
Autor:
Qin, Jie, Wu, Jie, Yan, Pengxiang, Li, Ming, Yuxi, Ren, Xiao, Xuefeng, Wang, Yitong, Wang, Rui, Wen, Shilei, Pan, Xin, Wang, Xingang
Recently, open-vocabulary learning has emerged to accomplish segmentation for arbitrary categories of text-based descriptions, which popularizes the segmentation system to more general-purpose application scenarios. However, existing methods devote t
Externí odkaz:
http://arxiv.org/abs/2303.17225
Existing methods proposed for hand reconstruction tasks usually parameterize a generic 3D hand model or predict hand mesh positions directly. The parametric representations consisting of hand shapes and rotational poses are more stable, while the non
Externí odkaz:
http://arxiv.org/abs/2303.15718
Autor:
Ma, Yuexiao, Li, Huixia, Zheng, Xiawu, Xiao, Xuefeng, Wang, Rui, Wen, Shilei, Pan, Xin, Chao, Fei, Ji, Rongrong
Post-training quantization (PTQ) is widely regarded as one of the most efficient compression methods practically, benefitting from its data privacy and low computation costs. We argue that an overlooked problem of oscillation is in the PTQ methods. I
Externí odkaz:
http://arxiv.org/abs/2303.11906
Autor:
Cui, Cheng, Guo, Ruoyu, Du, Yuning, He, Dongliang, Li, Fu, Wu, Zewu, Liu, Qiwen, Wen, Shilei, Huang, Jizhou, Hu, Xiaoguang, Yu, Dianhai, Ding, Errui, Ma, Yanjun
Recently, research efforts have been concentrated on revealing how pre-trained model makes a difference in neural network performance. Self-supervision and semi-supervised learning technologies have been extensively explored by the community and are
Externí odkaz:
http://arxiv.org/abs/2103.05959
Autor:
Chen, Peihao, Huang, Deng, He, Dongliang, Long, Xiang, Zeng, Runhao, Wen, Shilei, Tan, Mingkui, Gan, Chuang
We study unsupervised video representation learning that seeks to learn both motion and appearance features from unlabeled video only, which can be reused for downstream tasks such as action recognition. This task, however, is extremely challenging d
Externí odkaz:
http://arxiv.org/abs/2011.07949
Autor:
Qian, Mingyang, Fu, Yi, Tan, Xiao, Li, Yingying, Qi, Jinqing, Lu, Huchuan, Wen, Shilei, Ding, Errui
Video segmentation approaches are of great importance for numerous vision tasks especially in video manipulation for entertainment. Due to the challenges associated with acquiring high-quality per-frame segmentation annotations and large video datase
Externí odkaz:
http://arxiv.org/abs/2010.13085
Autor:
Hu, Di, Qian, Rui, Jiang, Minyue, Tan, Xiao, Wen, Shilei, Ding, Errui, Lin, Weiyao, Dou, Dejing
Discriminatively localizing sounding objects in cocktail-party, i.e., mixed sound scenes, is commonplace for humans, but still challenging for machines. In this paper, we propose a two-stage learning framework to perform self-supervised class-aware s
Externí odkaz:
http://arxiv.org/abs/2010.05466
Autor:
Long, Xiang, Deng, Kaipeng, Wang, Guanzhong, Zhang, Yang, Dang, Qingqing, Gao, Yuan, Shen, Hui, Ren, Jianguo, Han, Shumin, Ding, Errui, Wen, Shilei
Object detection is one of the most important areas in computer vision, which plays a key role in various practical scenarios. Due to limitation of hardware, it is often necessary to sacrifice accuracy to ensure the infer speed of the detector in pra
Externí odkaz:
http://arxiv.org/abs/2007.12099
Recently, most of the state-of-the-art human pose estimation methods are based on heatmap regression. The final coordinates of keypoints are obtained by decoding heatmap directly. In this paper, we aim to find a better approach to get more accurate l
Externí odkaz:
http://arxiv.org/abs/2007.10599