Zobrazeno 1 - 10
of 459
pro vyhledávání: '"Zhang, Junzhe"'
Autor:
Zhang, Junzhe, Zhang, Huixuan, Yin, Xunjian, Huang, Baizhou, Zhang, Xu, Hu, Xinyu, Wan, Xiaojun
Multimodal large language models (MLLMs) are prone to non-factual or outdated knowledge issues, which can manifest as misreading and misrecognition errors due to the complexity of multimodal knowledge. Previous benchmarks have not systematically anal
Externí odkaz:
http://arxiv.org/abs/2406.13219
Large-scale vision-language models have demonstrated impressive skill in handling tasks that involve both areas. Nevertheless, these models frequently experience significant issues with generating inaccurate information, which is hallucination. In th
Externí odkaz:
http://arxiv.org/abs/2403.01373
News image captioning requires model to generate an informative caption rich in entities, with the news image and the associated news article. Though Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in addressing var
Externí odkaz:
http://arxiv.org/abs/2402.19404
Autor:
Zhang, Junzhe
Causal inference provides a set of principles and tools that allows one to combine data and knowledge about an environment to reason with questions of a counterfactual nature - i.e., what would have happened if the reality had been different - even w
Autor:
Zhang, Junzhe, Lan, Yushi, Yang, Shuai, Hong, Fangzhou, Wang, Quan, Yeo, Chai Kiat, Liu, Ziwei, Loy, Chen Change
In this paper, we address the challenging problem of 3D toonification, which involves transferring the style of an artistic domain onto a target 3D face with stylized geometry and texture. Although fine-tuning a pre-trained 3D GAN on the artistic dom
Externí odkaz:
http://arxiv.org/abs/2309.04410
Real-scanned point clouds are often incomplete due to viewpoint, occlusion, and noise, which hampers 3D geometric modeling and perception. Existing point cloud completion methods tend to generate global shape skeletons and hence lack fine local detai
Externí odkaz:
http://arxiv.org/abs/2304.09131
Autor:
Fei, Ben, Lyu, Zhaoyang, Pan, Liang, Zhang, Junzhe, Yang, Weidong, Luo, Tianyue, Zhang, Bo, Dai, Bo
Existing image restoration methods mostly leverage the posterior distribution of natural images. However, they often assume known degradation and also require supervised training, which restricts their adaptation to complex real applications. In this
Externí odkaz:
http://arxiv.org/abs/2304.01247
Sketch-and-extrude is a common and intuitive modeling process in computer aided design. This paper studies the problem of learning the shape given in the form of point clouds by inverse sketch-and-extrude. We present ExtrudeNet, an unsupervised end-t
Externí odkaz:
http://arxiv.org/abs/2209.15632
A learning-based adaptive loop filter is developed for the Geometry-based Point Cloud Compression (G-PCC) standard to reduce attribute compression artifacts. The proposed method first generates multiple Most-Probable Sample Offsets (MPSOs) as potenti
Externí odkaz:
http://arxiv.org/abs/2209.08276
"Monkey see monkey do" is an age-old adage, referring to na\"ive imitation without a deep understanding of a system's underlying mechanics. Indeed, if a demonstrator has access to information unavailable to the imitator (monkey), such as a different
Externí odkaz:
http://arxiv.org/abs/2208.06276