Zobrazeno 1 - 10
of 57
pro vyhledávání: '"Luo, Tiange"'
Scalable annotation approaches are crucial for constructing extensive 3D-text datasets, facilitating a broader range of applications. However, existing methods sometimes lead to the generation of hallucinated captions, compromising caption quality. T
Externí odkaz:
http://arxiv.org/abs/2404.07984
We introduce Cap3D, an automatic approach for generating descriptive text for 3D objects. This approach utilizes pretrained models from image captioning, image-text alignment, and LLM to consolidate captions from multiple views of a 3D asset, complet
Externí odkaz:
http://arxiv.org/abs/2306.07279
Diffusion probabilistic models have shown great success in generating high-quality images controllably, and researchers have tried to utilize this controllability into text generation domain. Previous works on diffusion-based language models have sho
Externí odkaz:
http://arxiv.org/abs/2305.19512
Autor:
Jang, Yunseok, Sohn, Sungryull, Logeswaran, Lajanugen, Luo, Tiange, Lee, Moontae, Lee, Honglak
Real-world tasks consist of multiple inter-dependent subtasks (e.g., a dirty pan needs to be washed before it can be used for cooking). In this work, we aim to model the causal dependencies between such subtasks from instructional videos describing t
Externí odkaz:
http://arxiv.org/abs/2302.08672
3D shapes have complementary abstractions from low-level geometry to part-based hierarchies to languages, which convey different levels of information. This paper presents a unified framework to translate between pairs of shape abstractions: $\textit
Externí odkaz:
http://arxiv.org/abs/2212.12952
Robustness of neural networks has recently been highlighted by the adversarial examples, i.e., inputs added with well-designed perturbations which are imperceptible to humans but can cause the network to give incorrect outputs. In this paper, we desi
Externí odkaz:
http://arxiv.org/abs/2007.14249
We address the problem of discovering 3D parts for objects in unseen categories. Being able to learn the geometry prior of parts and transfer this prior to unseen categories pose fundamental challenges on data-driven shape segmentation approaches. Fo
Externí odkaz:
http://arxiv.org/abs/2002.06478
Robustness of convolutional neural networks (CNNs) has gained in importance on account of adversarial examples, i.e., inputs added as well-designed perturbations that are imperceptible to humans but can cause the model to predict incorrectly. Recent
Externí odkaz:
http://arxiv.org/abs/1911.08432
In this paper, we propose to tackle the challenging few-shot learning (FSL) problem by learning global class representations using both base and novel class training samples. In each training episode, an episodic class mean computed from a support se
Externí odkaz:
http://arxiv.org/abs/1908.05257
Fine-grained classification is challenging due to the difficulty of finding discriminative features. Finding those subtle traits that fully characterize the object is not straightforward. To handle this circumstance, we propose a novel self-supervisi
Externí odkaz:
http://arxiv.org/abs/1809.00287