Divide-and-Conquer Predictor for Unbiased Scene Graph Generation von Han, Xianjing, Dong, Xingning, Song, Xuemeng, Gan, Tian, Zhan, Yibing, Yan, Yan, Nie, Liqiang

Volltext

DBiased-P: Dual-Biased Predicate Predictor for Unbiased Scene Graph Generation von Han, Xianjing, Song, Xuemeng, Dong, Xingning, Wei, Yinwei, Liu, Meng, Nie, Liqiang

Volltext

SNP-S3: Shared Network Pre-training and Significant Semantic Strengthening for Various Video-Text Tasks von Dong, Xingning, Guo, Qingpei, Gan, Tian, Wang, Qing, Wu, Jianlong, Ren, Xiangyuan, Cheng, Yuan, Chu, Wei

Volltext

SNP-S 3 : Shared Network Pre-Training and Significant Semantic Strengthening for Various Video-Text Tasks von Dong, Xingning, Guo, Qingpei, Gan, Tian, Wang, Qing, Wu, Jianlong, Ren, Xiangyuan, Cheng, Yuan, Chu, Wei

Volltext

METHOD AND APPARATUS FOR TRAINING RELATIONSHIP RECOGNITION MODEL AND METHOD AND APPARATUS FOR ANALYZING IMAGE von DONG, XINGNING, CHENG, YUAN

Volltext bestellen

SHE-Net: Syntax-Hierarchy-Enhanced Text-Video Retrieval von Yu, Xuzheng, Jiang, Chen, Dong, Xingning, Gan, Tian, Yang, Ming, Guo, Qingpei

Volltext bestellen

M2-RAAP: A Multi-Modal Recipe for Advancing Adaptation-based Pre-training towards Effective and Efficient Zero-shot Video-text Retrieval von Dong, Xingning, Feng, Zipeng, Zhou, Chunluan, Yu, Xuzheng, Yang, Ming, Guo, Qingpei

Volltext bestellen

SNP-S3: Shared Network Pre-training and Significant Semantic Strengthening for Various Video-Text Tasks von Dong, Xingning, Guo, Qingpei, Gan, Tian, Wang, Qing, Wu, Jianlong, Ren, Xiangyuan, Cheng, Yuan, Chu, Wei

Volltext

EVE: Efficient zero-shot text-based Video Editing with Depth Map Guidance and Temporal Consistency Constraints von Chen, Yutao, Dong, Xingning, Gan, Tian, Zhou, Chunluan, Yang, Ming, Guo, Qingpei

Volltext bestellen

Stacked Hybrid-Attention and Group Collaborative Learning for Unbiased Scene Graph Generation von Dong, Xingning, Gan, Tian, Song, Xuemeng, Wu, Jianlong, Cheng, Yuan, Nie, Liqiang

Volltext bestellen

Method and device for training relation recognition model and graph analysis von CHENG YUAN, DONG XINGNING

Volltext bestellen

SHE-Net: Syntax-Hierarchy-Enhanced Text-Video Retrieval von Yu, Xuzheng, Chen, Jiang, Dong, Xingning, Gan, Tian, Yang, Ming, Guo, Qingpei

Volltext

M2-RAAP: A Multi-Modal Recipe for Advancing Adaptation-based Pre-training towards Effective and Efficient Zero-shot Video-text Retrieval von Dong, Xingning, Feng, Zipeng, Zhou, Chunluan, Yu, Xuzheng, Yang, Ming, Guo, Qingpei

Volltext

EVE: Efficient zero-shot text-based Video Editing with Depth Map Guidance and Temporal Consistency Constraints von Chen, Yutao, Dong, Xingning, Gan, Tian, Zhou, Chunluan, Yang, Ming, Guo, Qingpei

Volltext

Characterization model training method and device von FENG ZIPENG, GUO QINGPEI, DONG XINGNING

Volltext bestellen

Stacked Hybrid-Attention and Group Collaborative Learning for Unbiased Scene Graph Generation von Dong, Xingning, Gan, Tian, Song, Xuemeng, Wu, Jianlong, Cheng, Yuan, Nie, Liqiang

Volltext

Video editing method and device von GUO QINGPEI, CHEN YUTAO, WANG QING, DONG XINGNING

Volltext bestellen

Video feature model training method and device and video feature extraction method and device von GUO QINGPEI, REN XIANGYUAN, WANG QING, DONG XINGNING

Volltext bestellen

Method for training feature extraction model and feature extraction method and device von GUO QINGPEI, WANG QING, CHENG YUAN, DONG XINGNING

Volltext bestellen

Unbalanced scrap steel sample grade judgment method based on tree-type stratified network von ZHU WENYIN, NIE LIQIANG, FENG XING, LAI BOWEN, GAN TIAN, JIA YONGPO, DONG XINGNING, SHEN PEI

Volltext bestellen