Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Li, Hengjia"'
Autor:
Cheng, Haoran, Peng, Liang, Xia, Linxuan, Hu, Yuepeng, Li, Hengjia, Lu, Qinglin, He, Xiaofei, Wu, Boxi
Significant advancements in video diffusion models have brought substantial progress to the field of text-to-video (T2V) synthesis. However, existing T2V synthesis model struggle to accurately generate complex motion dynamics, leading to a reduction
Externí odkaz:
http://arxiv.org/abs/2406.03215
Autor:
Zhang, Zhanwei, Chen, Minghao, Xiao, Shuai, Peng, Liang, Li, Hengjia, Lin, Binbin, Li, Ping, Wang, Wenxiao, Wu, Boxi, Cai, Deng
Recent self-training techniques have shown notable improvements in unsupervised domain adaptation for 3D object detection (3D UDA). These techniques typically select pseudo labels, i.e., 3D boxes, to supervise models for the target domain. However, t
Externí odkaz:
http://arxiv.org/abs/2404.19384
Autor:
Yang, Yang, Wang, Wen, Peng, Liang, Song, Chaotian, Chen, Yao, Li, Hengjia, Yang, Xiaolong, Lu, Qinglin, Cai, Deng, Wu, Boxi, Liu, Wei
Customization generation techniques have significantly advanced the synthesis of specific concepts across varied contexts. Multi-concept customization emerges as the challenging task within this domain. Existing approaches often rely on training a fu
Externí odkaz:
http://arxiv.org/abs/2403.11627
Autor:
Li, Hengjia, Liu, Yang, Lin, Yuqi, Zhang, Zhanwei, Zhao, Yibo, Pan, weihang, Zheng, Tu, Yang, Zheng, Jiang, Yuchun, Wu, Boxi, Cai, Deng
Recently, generative domain adaptation has achieved remarkable progress, enabling us to adapt a pre-trained generator to a new target domain. However, existing methods simply adapt the generator to a single target domain and are limited to a single m
Externí odkaz:
http://arxiv.org/abs/2401.12596
Autor:
Lin, Yuqi, Chen, Minghao, Zhang, Kaipeng, Li, Hengjia, Li, Mingming, Yang, Zheng, Lv, Dongqin, Lin, Binbin, Liu, Haifeng, Cai, Deng
Contrastive Language-Image Pre-training (CLIP) has demonstrated impressive capabilities in open-vocabulary classification. The class token in the image encoder is trained to capture the global features to distinguish different text descriptions super
Externí odkaz:
http://arxiv.org/abs/2312.12828
Autor:
Zhao, Yibo, Peng, Liang, Yang, Yang, Luo, Zekai, Li, Hengjia, Chen, Yao, Yang, Zheng, He, Xiaofei, Zhao, Wei, lu, qinglin, Wu, Boxi, Liu, Wei
Diffusion models have exhibited impressive prowess in the text-to-image task. Recent methods add image-level structure controls, e.g., edge and depth maps, to manipulate the generation process together with text prompts to obtain desired images. This
Externí odkaz:
http://arxiv.org/abs/2312.08768
Autor:
Li, Hengjia, Liu, Yang, Xia, Linxuan, Lin, Yuqi, Zheng, Tu, Yang, Zheng, Wang, Wenxiao, Zhong, Xiaohui, Ren, Xiaobo, He, Xiaofei
Can a pre-trained generator be adapted to the hybrid of multiple target domains and generate images with integrated attributes of them? In this work, we introduce a new task -- Few-shot Hybrid Domain Adaptation (HDA). Given a source generator and sev
Externí odkaz:
http://arxiv.org/abs/2310.19378
Logit based knowledge distillation gets less attention in recent years since feature based methods perform better in most cases. Nevertheless, we find it still has untapped potential when we re-investigate the temperature, which is a crucial hyper-pa
Externí odkaz:
http://arxiv.org/abs/2308.00520
Autor:
Li, Hengjia, Zheng, Tu, Chi, Zhihao, Yang, Zheng, Wang, Wenxiao, Wu, Boxi, Lin, Binbin, Cai, Deng
Transformer-based networks have achieved impressive performance in 3D point cloud understanding. However, most of them concentrate on aggregating local features, but neglect to directly model global dependencies, which results in a limited effective
Externí odkaz:
http://arxiv.org/abs/2303.17815
Publikováno v:
China City Planning Review. Mar2024, Vol. 33 Issue 1, p58-67. 10p.