Torthaí cuardaigh - Zhang, Yanning

Learning to Compare Relation: Semantic Alignment for Few-Shot Learning de réir Cao, Congqi, Zhang, Yanning

Faigh an téacs iomlán
Faigh an téacs iomlán

Learnable Locality-Sensitive Hashing for Video Anomaly Detection de réir Lu, Yue, Cao, Congqi, Zhang, Yanning

Faigh an téacs iomlán
Faigh an téacs iomlán

Context Recovery and Knowledge Retrieval: A Novel Two-Stream Framework for Video Anomaly Detection de réir Cao, Congqi, Lu, Yue, Zhang, Yanning

Faigh an téacs iomlán
Faigh an téacs iomlán

Evaluating Local Geometric Feature Representations for 3D Rigid Data Matching de réir Yang, Jiaqi, Quan, Siwen, Wang, Peng, Zhang, Yanning

Faigh an téacs iomlán
Faigh an téacs iomlán

A Cross-Modal Image Fusion Method Guided by Human Visual Characteristics de réir Fang, Aiqing, Zhao, Xinbo, Yang, Jiaqi, Zhang, Yanning

Faigh an téacs iomlán
Faigh an téacs iomlán

Non-linear and Selective Fusion of Cross-Modal Images de réir Fang, Aiqing, Zhao, Xinbo, Yang, Jiaqi, Zhang, Yanning

Faigh an téacs iomlán
Faigh an téacs iomlán

IllumiNet: Transferring Illumination from Planar Surfaces to Virtual Objects in Augmented Reality de réir Xu, Di, Li, Zhen, Zhang, Yanning, Cao, Qi

Faigh an téacs iomlán
Faigh an téacs iomlán

Meta-Generating Deep Attentive Metric for Few-shot Classification de réir Zhang, Lei, Zhou, Fei, Wei, Wei, Zhang, Yanning

Faigh an téacs iomlán
Faigh an téacs iomlán

Dynamic Image Restoration and Fusion Based on Dynamic Degradation de réir Fang, Aiqing, Zhao, Xinbo, Yang, Jiaqi, Zhang, Yanning

Faigh an téacs iomlán
Faigh an téacs iomlán

Inter-sphere consistency-based method for camera-projector pair calibration de réir Qi, Zhaoshuai, Pang, Jingqi, Hao, Yifeng, Zhang, Yanning

Faigh an téacs iomlán
Faigh an téacs iomlán

3D Registration with Maximal Cliques de réir Zhang, Xiyu, Yang, Jiaqi, Zhang, Shikun, Zhang, Yanning

Faigh an téacs iomlán
Faigh an téacs iomlán

A New Comprehensive Benchmark for Semi-supervised Video Anomaly Detection and Anticipation de réir Cao, Congqi, Lu, Yue, Wang, Peng, Zhang, Yanning

Faigh an téacs iomlán
Faigh an téacs iomlán

Semi-Supervised Semantic Segmentation Based on Pseudo-Labels: A Survey de réir Ran, Lingyan, Li, Yali, Liang, Guoqiang, Zhang, Yanning

Faigh an téacs iomlán
Faigh an téacs iomlán

Generating Content for HDR Deghosting from Frequency View de réir Hu, Tao, Yan, Qingsen, Qi, Yuankai, Zhang, Yanning

Faigh an téacs iomlán
Faigh an téacs iomlán

C3L: Content Correlated Vision-Language Instruction Tuning Data Generation via Contrastive Learning de réir Ma, Ji, Suo, Wei, Wang, Peng, Zhang, Yanning

Faigh an téacs iomlán
Faigh an téacs iomlán

Unleashing the Potential of Open-set Noisy Samples Against Label Noise for Medical Image Classification de réir Liao, Zehui, Hu, Shishuai, Zhang, Yanning, Xia, Yong

Faigh an téacs iomlán
Faigh an téacs iomlán

A Plug-and-Play Method for Rare Human-Object Interactions Detection by Bridging Domain Gap de réir Zhang, Lijun, Suo, Wei, Wang, Peng, Zhang, Yanning

Faigh an téacs iomlán
Faigh an téacs iomlán

Learning to Generalize without Bias for Open-Vocabulary Action Recognition de réir Yu, Yating, Cao, Congqi, Zhang, Yifan, Zhang, Yanning

Faigh an téacs iomlán
Faigh an téacs iomlán

Vision and Intention Boost Large Language Model in Long-Term Action Anticipation de réir Cao, Congqi, Hu, Lanshu, Yu, Yating, Zhang, Yanning

Faigh an téacs iomlán
Faigh an téacs iomlán

Short-LVLM: Compressing and Accelerating Large Vision-Language Models by Pruning Redundant Layers de réir Ma, Ji, Suo, Wei, Wang, Peng, Zhang, Yanning

Faigh an téacs iomlán
Faigh an téacs iomlán