Search Results - "Ding, Xinpeng"

Exploring Segment-Level Semantics for Online Phase Recognition From Surgical Videos by Ding, Xinpeng, Li, Xiaomeng

“…Automatic surgical phase recognition plays a vital role in robot-assisted surgeries. Existing methods ignored a pivotal problem that surgical phases should be…”
Get full text

Adaptively Learning Facial Expression Representation via C-F Labels and Distillation by Li, Hangyu, Wang, Nannan, Ding, Xinpeng, Yang, Xi, Gao, Xinbo

“…Facial expression recognition is of significant importance in criminal investigation and digital entertainment. Under unconstrained conditions, existing…”
Get full text

Weakly Supervised Temporal Action Localization With Bidirectional Semantic Consistency Constraint by Li, Guozhang, Cheng, De, Ding, Xinpeng, Wang, Nannan, Li, Jie, Gao, Xinbo

“…Weakly supervised temporal action localization (WTAL) aims to classify and localize temporal boundaries of actions for the video, given only video-level…”
Get full text

Cyclical Self-Supervision for Semi-Supervised Ejection Fraction Prediction From Echocardiogram Videos by Dai, Weihang, Li, Xiaomeng, Ding, Xinpeng, Cheng, Kwang-Ting

“…Left-ventricular ejection fraction (LVEF) is an important indicator of heart failure. Existing methods for LVEF estimation from video require large amounts of…”
Get full text

Exploring Language Hierarchy for Video Grounding by Ding, Xinpeng, Wang, Nannan, Zhang, Shiwei, Huang, Ziyuan, Li, Xiaomeng, Tang, Mingqian, Liu, Tongliang, Gao, Xinbo

“…The understanding of language plays a key role in video grounding, where a target moment is localized according to a text query. From a biological point of…”
Get full text

Less is More: Surgical Phase Recognition from Timestamp Supervision by Ding, Xinpeng, Yan, Xinjian, Wang, Zixun, Zhao, Wei, Zhuang, Jian, Xu, Xiaowei, Li, Xiaomeng

“…Surgical phase recognition is a fundamental task in computer-assisted surgery systems. Most existing works are under the supervision of expensive and…”
Get full text

KFC: An Efficient Framework for Semi-Supervised Temporal Action Localization by Ding, Xinpeng, Wang, Nannan, Gao, Xinbo, Li, Jie, Wang, Xiaoyu, Liu, Tongliang

“…In temporal action localization (TAL), semi-supervised learning is a promising technique to mitigate the cost of precise boundary annotations. Semi-supervised…”
Get full text

Multi-Hierarchical Category Supervision for Weakly-Supervised Temporal Action Localization by Li, Guozhang, Li, Jie, Wang, Nannan, Ding, Xinpeng, Li, Zhifeng, Gao, Xinbo

“…Weakly Supervised Temporal Action Localization (WTAL) aims to localize action segments in untrimmed videos with only video-level category labels in the…”
Get full text

Group Feedback Capsule Network by Ding, Xinpeng, Wang, Nannan, Gao, Xinbo, Li, Jie, Wang, Xiaoyu, Liu, Tongliang

“…In capsule networks (CapsNets), the capsule is made up of collections of neurons. Their adjacent capsule layers are connected using routing-by-agreement…”
Get full text

Support-Set Based Cross-Supervision for Video Grounding by Ding, Xinpeng, Wang, Nannan, Zhang, Shiwei, Cheng, De, Li, Xiaomeng, Huang, Ziyuan, Tang, Mingqian, Gao, Xinbo

“…Current approaches for video grounding propose kinds of complex architectures to capture the video-text relations, and have achieved impressive improvements…”
Get full text

Boosting Weakly-Supervised Temporal Action Localization with Text Information by Li, Guozhang, Cheng, De, Ding, Xinpeng, Wang, Nannan, Wang, Xiaoyu, Gao, Xinbo

“…Due to the lack of temporal annotation, current Weakly-supervised Temporal Action Localization (WTAL) methods are generally stuck into over-complete or…”
Get full text

Spectrum and Style Transformation Framework for Omni-Domain COVID-19 Diagnosis by Wang, Zhenkun, Gui, Shuangchun, Ding, Xinpeng, Hu, Xiaowei, Xu, Xiaowei, Li, Xiaomeng

“…Coronavirus disease 2019 (COVID-19) is an ongoing global pandemic and profoundly affects almost all people around the world. Thus, many automatic diagnosis…”
Get full text

Exploring Segment-level Semantics for Online Phase Recognition from Surgical Videos by Ding, Xinpeng, Li, Xiaomeng

“…Automatic surgical phase recognition plays a vital role in robot-assisted surgeries. Existing methods ignored a pivotal problem that surgical phases should be…”
Get full text

Tri-Plane Mamba: Efficiently Adapting Segment Anything Model for 3D Medical Images by Wang, Hualiang, Lin, Yiqun, Ding, Xinpeng, Li, Xiaomeng

“…General networks for 3D medical image segmentation have recently undergone extensive exploration. Behind the exceptional performance of these networks lies a…”
Get full text

Free Lunch for Surgical Video Understanding by Distilling Self-Supervisions by Ding, Xinpeng, Liu, Ziwei, Li, Xiaomeng

“…Self-supervised learning has witnessed great progress in vision and NLP; recently, it also attracted much attention to various medical imaging modalities such…”
Get full text

GraphEcho: Graph-Driven Unsupervised Domain Adaptation for Echocardiogram Video Segmentation by Yang, Jiewen, Ding, Xinpeng, Zheng, Ziyang, Xu, Xiaowei, Li, Xiaomeng

“…Echocardiogram video segmentation plays an important role in cardiac disease diagnosis. This paper studies the unsupervised domain adaption (UDA) for…”
Get full text

GL-Fusion: Global-Local Fusion Network for Multi-view Echocardiogram Video Segmentation by Zheng, Ziyang, Yang, Jiewen, Ding, Xinpeng, Xu, Xiaowei, Li, Xiaomeng

“…Cardiac structure segmentation from echocardiogram videos plays a crucial role in diagnosing heart disease. The combination of multi-view echocardiogram data…”
Get full text

HiLM-D: Towards High-Resolution Understanding in Multimodal Large Language Models for Autonomous Driving by Ding, Xinpeng, Han, Jianhua, Xu, Hang, Zhang, Wei, Li, Xiaomeng

“…Autonomous driving systems generally employ separate models for different tasks resulting in intricate designs. For the first time, we leverage singular…”
Get full text

Uniformly Distributed Category Prototype-Guided Vision-Language Framework for Long-Tail Recognition by Fu, Siming, He, Xiaoxuan, Ding, Xinpeng, Cao, Yuchen, Wang, Hualiang

“…ACM MM2023 Recently, large-scale pre-trained vision-language models have presented benefits for alleviating class imbalance in long-tailed recognition…”
Get full text

Context-Aware Pseudo-Label Refinement for Source-Free Domain Adaptive Fundus Image Segmentation by Huai, Zheang, Ding, Xinpeng, Li, Yi, Li, Xiaomeng

“…In the domain adaptation problem, source data may be unavailable to the target client side due to privacy or intellectual property issues. Source-free…”
Get full text