Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Wang, Siqi"'
Autor:
Tang, Jingqun, Lin, Chunhui, Zhao, Zhen, Wei, Shu, Wu, Binghong, Liu, Qi, Feng, Hao, Li, Yang, Wang, Siqi, Liao, Lei, Shi, Wei, Liu, Yuliang, Liu, Hao, Xie, Yuan, Bai, Xiang, Huang, Can
Text-centric visual question answering (VQA) has made great strides with the development of Multimodal Large Language Models (MLLMs), yet open-source models still fall short of leading models like GPT4V and Gemini, partly due to a lack of extensive,
Externí odkaz:
http://arxiv.org/abs/2404.12803
Digital Image Correlation (DIC) is an optical technique that measures displacement and strain by tracking pattern movement in a sequence of captured images during testing. DIC has gained recognition in asphalt pavement engineering since the early 200
Externí odkaz:
http://arxiv.org/abs/2402.17074
Noisy labels can impair model performance, making the study of learning with noisy labels an important topic. Two conventional approaches are noise modeling and noise detection. However, these two methods are typically studied independently, and ther
Externí odkaz:
http://arxiv.org/abs/2312.00827
Autor:
Chen, Zitong, Pham, Chau, Wang, Siqi, Doron, Michael, Moshkov, Nikita, Plummer, Bryan A., Caicedo, Juan C.
Most neural networks assume that input images have a fixed number of channels (three for RGB images). However, there are many settings where the number of channels may vary, such as microscopy images where the number of channels changes depending on
Externí odkaz:
http://arxiv.org/abs/2310.19224
3D human pose estimation in outdoor environments has garnered increasing attention recently. However, prevalent 3D human pose datasets pertaining to outdoor scenes lack diversity, as they predominantly utilize only one type of modality (RGB image or
Externí odkaz:
http://arxiv.org/abs/2308.00628
Autor:
Wang, Siqi, Plummer, Bryan A.
Learning with noisy labels (LNL) is challenging as the model tends to memorize noisy labels, which can lead to overfitting. Many LNL methods detect clean samples by maximizing the similarity between samples in each category, which does not make any a
Externí odkaz:
http://arxiv.org/abs/2306.11911
Open World Object Detection (OWOD) is a novel and challenging computer vision task that enables object detection with the ability to detect unknown objects. Existing methods typically estimate the object likelihood with an additional objectness branc
Externí odkaz:
http://arxiv.org/abs/2306.02275
We present an effective method for Intracranial Hemorrhage Detection (IHD) which exceeds the performance of the winner solution in RSNA-IHD competition (2019). Meanwhile, our model only takes quarter parameters and ten percent FLOPs compared to the w
Externí odkaz:
http://arxiv.org/abs/2205.07556
Although deep neural networks (DNNs) enable great progress in video abnormal event detection (VAD), existing solutions typically suffer from two issues: (1) The localization of video events cannot be both precious and comprehensive. (2) The semantics
Externí odkaz:
http://arxiv.org/abs/2108.02356
While classic video anomaly detection (VAD) requires labeled normal videos for training, emerging unsupervised VAD (UVAD) aims to discover anomalies directly from fully unlabeled videos. However, existing UVAD methods still rely on shallow models to
Externí odkaz:
http://arxiv.org/abs/2108.01975