Zobrazeno 1 - 10
of 12 575
pro vyhledávání: '"Nong P"'
Autor:
Zhang, Huaxin, Xu, Xiaohao, Wang, Xiang, Zuo, Jialong, Huang, Xiaonan, Gao, Changxin, Zhang, Shanjun, Yu, Li, Sang, Nong
How can we enable models to comprehend video anomalies occurring over varying temporal scales and contexts? Traditional Video Anomaly Understanding (VAU) methods focus on frame-level anomaly prediction, often missing the interpretability of complex a
Externí odkaz:
http://arxiv.org/abs/2412.06171
Autor:
An, Yuda, Yi, Shushu, Mao, Bo, Li, Qiao, Zhang, Mingzhe, Zhou, Ke, Xiao, Nong, Sun, Guangyu, Wang, Xiaolin, Luo, Yingwei, Zhang, Jie
Compute Express Link (CXL) serves as a rising industry standard, delivering high-speed cache-coherent links to a variety of devices, including host CPUs, computational accelerators, and memory devices. It is designed to promote system scalability, en
Externí odkaz:
http://arxiv.org/abs/2411.08312
Autor:
Li, Dongxiao, Sun, Yuxuan, Li, Xingjian, Li, Xingxiang, Zhu, Zhengqing, Sun, Boxi, Nong, Shutong, Wu, Jiyang, Pan, Tingrui, Li, Weihua, Zhang, Shiwu, Li, Mujun
Liquid Crystal Elastomers with near-ambient temperature-responsiveness (NAT-LCEs) have been extensively studied for building bio-compatible, low-power consumption devices and robotics. However, conventional manufacturing methods face limitations in p
Externí odkaz:
http://arxiv.org/abs/2411.06931
Autor:
Wang, Yanjing, Wu, Lizhou, Hong, Wentao, Ou, Yang, Wang, Zicong, Gao, Sunfeng, Zhang, Jie, Ma, Sheng, Dong, Dezun, Qi, Xingyun, Lai, Mingche, Xiao, Nong
Compute eXpress Link (CXL) is a pivotal technology for memory disaggregation in future heterogeneous computing systems, enabling on-demand memory expansion and improved resource utilization. Despite its potential, CXL is in its early stages with limi
Externí odkaz:
http://arxiv.org/abs/2411.02282
We study the problem of fair allocation of a set of indivisible items among agents with additive valuations, under matroid constraints and two generalizations: $p$-extendible system and independence system constraints. The objective is to find fair a
Externí odkaz:
http://arxiv.org/abs/2411.01462
The pervasive use of the Internet and social media introduces significant challenges to automated sentiment analysis, particularly for sarcastic expressions in user-generated content. Sarcasm conveys negative emotions through ostensibly positive or e
Externí odkaz:
http://arxiv.org/abs/2411.01264
Autor:
Sun, Yanpeng, Zhang, Huaxin, Chen, Qiang, Zhang, Xinyu, Sang, Nong, Zhang, Gang, Wang, Jingdong, Li, Zechao
We focus on improving the visual understanding capability for boosting the vision-language models. We propose \textbf{Arcana}, a multiModal language model, which introduces two crucial techniques. First, we present Multimodal LoRA (MM-LoRA), a module
Externí odkaz:
http://arxiv.org/abs/2410.13733
Interactive portrait matting refers to extracting the soft portrait from a given image that best meets the user's intent through their inputs. Existing methods often underperform in complex scenarios, mainly due to three factors. (1) Most works apply
Externí odkaz:
http://arxiv.org/abs/2410.09788
Recent advancements in controllable human-centric video generation, particularly with the rise of diffusion models, have demonstrated considerable progress. However, achieving precise and localized control over human motion, e.g., replacing or insert
Externí odkaz:
http://arxiv.org/abs/2409.19911
Autor:
Zuo, Jialong, Nie, Ying, Zhou, Hanyu, Zhang, Huaxin, Wang, Haoyu, Guo, Tianyu, Sang, Nong, Gao, Changxin
Recent researches have proven that pre-training on large-scale person images extracted from internet videos is an effective way in learning better representations for person re-identification. However, these researches are mostly confined to pre-trai
Externí odkaz:
http://arxiv.org/abs/2409.18569