Zobrazeno 1 - 10
of 82
pro vyhledávání: '"Dong, Mingzhi"'
Autor:
Wang, Chenyu, Yan, Shuo, Chen, Yixuan, Wang, Yujiang, Dong, Mingzhi, Yang, Xiaochen, Li, Dongsheng, Dick, Robert P., Lv, Qin, Yang, Fan, Lu, Tun, Gu, Ning, Shang, Li
Video generation using diffusion-based models is constrained by high computational costs due to the frame-wise iterative diffusion process. This work presents a Diffusion Reuse MOtion (Dr. Mo) network to accelerate latent video generation. Our key di
Externí odkaz:
http://arxiv.org/abs/2409.12532
Autor:
Shi, Yubin, Chen, Yixuan, Dong, Mingzhi, Yang, Xiaochen, Li, Dongsheng, Wang, Yujiang, Dick, Robert P., Lv, Qin, Zhao, Yingying, Yang, Fan, Lu, Tun, Gu, Ning, Shang, Li
Despite their prevalence in deep-learning communities, over-parameterized models convey high demands of computational costs for proper training. This work studies the fine-grained, modular-level learning dynamics of over-parameterized models to attai
Externí odkaz:
http://arxiv.org/abs/2405.07527
Autor:
Wang, Yujiang, Thakur, Anshul, Dong, Mingzhi, Ma, Pingchuan, Petridis, Stavros, Shang, Li, Zhu, Tingting, Clifton, David A.
The prevalence of artificial intelligence (AI) has envisioned an era of healthcare democratisation that promises every stakeholder a new and better way of life. However, the advancement of clinical AI research is significantly hurdled by the dearth o
Externí odkaz:
http://arxiv.org/abs/2305.03711
Autor:
Wang, Yujiang, Dong, Mingzhi, Shen, Jie, Luo, Yiming, Lin, Yiming, Ma, Pingchuan, Petridis, Stavros, Pantic, Maja
This paper presents a novel method for face clustering in videos using a video-centralised transformer. Previous works often employed contrastive learning to learn frame-level representation and used average pooling to aggregate the features along th
Externí odkaz:
http://arxiv.org/abs/2203.13166
Autor:
Zhao, Yingying, Chang, Yuhu, Lu, Yutian, Wang, Yujiang, Dong, Mingzhi, Lv, Qin, Dick, Robert P., Yang, Fan, Lu, Tun, Gu, Ning, Shang, Li
Publikováno v:
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT), Volume 6, Issue 1, Article 38. March 2022
Emotion recognition in smart eyewear devices is highly valuable but challenging. One key limitation of previous works is that the expression-related information like facial or eye images is considered as the only emotional evidence. However, emotiona
Externí odkaz:
http://arxiv.org/abs/2201.09933
Autor:
Chang, Yuhu, Zhao, Yingying, Dong, Mingzhi, Wang, Yujiang, Lu, Yutian, Lv, Qin, Dick, Robert P., Lu, Tun, Gu, Ning, Shang, Li
Publikováno v:
Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., Volume 5 Issue 2, Article 56. June 2021
This work presents MemX: a biologically-inspired attention-aware eyewear system developed with the goal of pursuing the long-awaited vision of a personalized visual Memex. MemX captures human visual attention on the fly, analyzes the salient visual c
Externí odkaz:
http://arxiv.org/abs/2105.00916
Autor:
Zhao, Yingying, Dong, Mingzhi, Wang, Yujiang, Feng, Da, Lv, Qin, Dick, Robert P., Li, Dongsheng, Lu, Tun, Gu, Ning, Shang, Li
Deep-learning-based video processing has yielded transformative results in recent years. However, the video analytics pipeline is energy-intensive due to high data rates and reliance on complex inference algorithms, which limits its adoption in energ
Externí odkaz:
http://arxiv.org/abs/2104.04443
Metric learning aims to learn a distance metric such that semantically similar instances are pulled together while dissimilar instances are pushed away. Many existing methods consider maximizing or at least constraining a distance margin in the featu
Externí odkaz:
http://arxiv.org/abs/2006.05945
Dilated convolutions are widely used in deep semantic segmentation models as they can enlarge the filters' receptive field without adding additional weights nor sacrificing spatial resolution. However, as dilated convolutional filters do not possess
Externí odkaz:
http://arxiv.org/abs/2006.03708
For real-time semantic video segmentation, most recent works utilised a dynamic framework with a key scheduler to make online key/non-key decisions. Some works used a fixed key scheduling policy, while others proposed adaptive key scheduling methods
Externí odkaz:
http://arxiv.org/abs/1907.01296