Zobrazeno 1 - 10
of 756
pro vyhledávání: '"Borun A"'
Autor:
Lopushanskyy, Dmytro, Shi, Borun
Training graph neural networks on large datasets has long been a challenge. Traditional approaches include efficiently representing the whole graph in-memory, designing parameter efficient and sampling-based models, and graph partitioning in a distri
Externí odkaz:
http://arxiv.org/abs/2411.11375
Autor:
Liu, Jian, Zhang, Sipeng, Kong, Chuixin, Zhang, Wenyuan, Wu, Yuhang, Ding, Yikang, Xu, Borun, Ming, Ruibo, Wei, Donglai, Liu, Xianming
This technical report presents our solution, "occTransformer" for the 3D occupancy prediction track in the autonomous driving challenge at CVPR 2023. Our method builds upon the strong baseline BEVFormer and improves its performance through several si
Externí odkaz:
http://arxiv.org/abs/2402.18140
Citation field learning is to segment a citation string into fields of interest such as author, title, and venue. Extracting such fields from citations is crucial for citation indexing, researcher profile analysis, etc. User-generated resources like
Externí odkaz:
http://arxiv.org/abs/2309.03559
We analyse the geometric instability of embeddings produced by graph neural networks (GNNs). Existing methods are only applicable for small graphs and lack context in the graph domain. We propose a simple, efficient and graph-native Graph Gram Index
Externí odkaz:
http://arxiv.org/abs/2308.10099
Autor:
Xu, Borun, Wang, Biao, Deng, Jinhong, Tao, Jiale, Ge, Tiezheng, Jiang, Yuning, Li, Wen, Duan, Lixin
Motion transfer aims to transfer the motion of a driving video to a source image. When there are considerable differences between object in the driving video and that in the source image, traditional single domain motion transfer approaches often pro
Externí odkaz:
http://arxiv.org/abs/2209.14529
Autor:
Chen, Borun, Tang, Hongyin, Bu, Jiahao, Zhang, Kai, Wang, Jingang, Wang, Qifan, Zheng, Hai-Tao, Wu, Wei, Yu, Liqian
Pre-trained Language Models (PLMs) have achieved remarkable performance gains across numerous downstream tasks in natural language understanding. Various Chinese PLMs have been successively proposed for learning better Chinese language representation
Externí odkaz:
http://arxiv.org/abs/2208.10844
Given a source image and a driving video depicting the same object type, the motion transfer task aims to generate a video by learning the motion from the driving video while preserving the appearance from the source image. In this paper, we propose
Externí odkaz:
http://arxiv.org/abs/2204.05018
Publikováno v:
In Particuology January 2025 96:126-138
Publikováno v:
Proceedings of the 29th ACM International Conference on Multimedia. 2021: 2759-2761
Creative image animations are attractive in e-commerce applications, where motion transfer is one of the import ways to generate animations from static images. However, existing methods rarely transfer motion to objects other than human body or human
Externí odkaz:
http://arxiv.org/abs/2112.13647
Existing text- and image-based multimodal dialogue systems use the traditional Hierarchical Recurrent Encoder-Decoder (HRED) framework, which has an utterance-level encoder to model utterance representation and a context-level encoder to model contex
Externí odkaz:
http://arxiv.org/abs/2110.09702