Search Results for author: Tian Zheng

Found 15 papers, 4 papers with code

An Early Evaluation of GPT-4V(ision)

1 code implementation25 Oct 2023 Yang Wu, Shilong Wang, Hao Yang, Tian Zheng, Hongbo Zhang, Yanyan Zhao, Bing Qin

In this paper, we evaluate different abilities of GPT-4V including visual understanding, language understanding, visual puzzle solving, and understanding of other modalities such as depth, thermal, video, and audio.


Wasserstein Distributional Learning

no code implementations12 Sep 2022 Chengliang Tang, Nathan Lenssen, Ying WEI, Tian Zheng

To overcome this fundamental issue, we propose Wasserstein Distributional Learning (WDL), a flexible density-on-scalar regression modeling framework that starts with the Wasserstein distance $W_2$ as a proper metric for the space of density outcomes.


INS-Conv: Incremental Sparse Convolution for Online 3D Segmentation

no code implementations CVPR 2022 Leyao Liu, Tian Zheng, Yun-Jou Lin, Kai Ni, Lu Fang

Based on INS-Conv, an online joint 3D semantic and instance segmentation pipeline is proposed, reaching an inference speed of 15 FPS on GPU and 10 FPS on CPU.

Instance Segmentation RGB-D Reconstruction +2

Toward a Taxonomy of Trust for Probabilistic Machine Learning

no code implementations5 Dec 2021 Tamara Broderick, Andrew Gelman, Rachael Meager, Anna L. Smith, Tian Zheng

Probabilistic machine learning increasingly informs critical decisions in medicine, economics, politics, and beyond.

BIG-bench Machine Learning Translation

Weakly Supervised Learning Creates a Fusion of Modeling Cultures

no code implementations2 Jun 2021 Chengliang Tang, Gan Yuan, Tian Zheng

The past two decades have witnessed the great success of the algorithmic modeling framework advocated by Breiman et al. (2001).

Cultural Vocal Bursts Intensity Prediction Weakly-supervised Learning

Artificial Perceptual Learning: Image Categorization with Weak Supervision

no code implementations2 Jun 2021 Chengliang Tang, María Uriarte, Helen Jin, Douglas C. Morton, Tian Zheng

In this paper, we propose a novel machine learning framework, artificial perceptual learning (APL), to tackle the problem of weakly supervised image categorization.

BIG-bench Machine Learning Image Categorization

Online Estimation and Community Detection of Network Point Processes for Event Streams

1 code implementation3 Sep 2020 Guanhua Fang, Owen G. Ward, Tian Zheng

To circumvent this challenge, we propose a fast online variational inference algorithm for estimating the latent structure underlying dynamic event arrivals on a network, using continuous-time point process latent network models.

Online Community Detection Point Processes +1

Next Waves in Veridical Network Embedding

no code implementations10 Jul 2020 Owen G. Ward, Zhen Huang, Andrew Davison, Tian Zheng

Embedding nodes of a large network into a metric (e. g., Euclidean) space has become an area of active research in statistical machine learning, which has found applications in natural and social sciences.

Community Detection Link Prediction +2

OccuSeg: Occupancy-aware 3D Instance Segmentation

no code implementations CVPR 2020 Lei Han, Tian Zheng, Lan Xu, Lu Fang

3D instance segmentation, with a variety of applications in robotics and augmented reality, is in large demands these days.

3D Instance Segmentation Clustering +3

Stabilized Sparse Online Learning for Sparse Data

no code implementations21 Apr 2016 Yuting Ma, Tian Zheng

To mitigate this issue, we introduce a stabilized truncated stochastic gradient descent algorithm.

Boosted Sparse Non-linear Distance Metric Learning

no code implementations10 Dec 2015 Yuting Ma, Tian Zheng

In this paper, we propose a nonlinear sparse metric learning algorithm via boosting.

Metric Learning

Topic-adjusted visibility metric for scientific articles

no code implementations25 Feb 2015 Linda S. L. Tan, Aik Hui Chan, Tian Zheng

In this work, we address the problem of field variation and introduce an article level metric useful for evaluating individual articles' visibility.

Cannot find the paper you are looking for? You can Submit a new open access paper.