Author name cluster

Ming Hou

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

7 papers

2 author rows

IJCAI Conference 2022 Conference Paper

MMT: Multi-way Multi-modal Transformer for Multimodal Learning

Jiajia Tang
Kang Li
Ming Hou
Xuanyu Jin
Wanzeng Kong
Yu Ding
Qibin Zhao

The heart of multimodal learning research lies the challenge of effectively exploiting fusion representations among multiple modalities. However, existing two-way cross-modality unidirectional attention could only exploit the intermodal interactions from one source to one target modality. This indeed fails to unleash the complete expressive power of multimodal fusion with restricted number of modalities and fixed interactive direction. In this work, the multiway multimodal transformer (MMT) is proposed to simultaneously explore multiway multimodal intercorrelations for each modality via single block rather than multiple stacked cross-modality blocks. The core idea of MMT is the multiway multimodal attention, where the multiple modalities are leveraged to compute the multiway attention tensor. This naturally benefits us to exploit comprehensive many-to-many multimodal interactive paths. Specifically, the multiway tensor is comprised of multiple interconnected modality-aware core tensors that consist of the intramodal interactions. Additionally, the tensor contraction operation is utilized to investigate intermodal dependencies between distinct core tensors. Essentially, our tensor-based multiway structure allows for easily extending MMT to the case associated with an arbitrary number of modalities. Taking MMT as the basis, the hierarchical network is further established to recursively transmit the low-level multiway multimodal interactions to high-level ones. The experiments demonstrate that MMT can achieve state-of-the-art or comparable performance.

PDF Details DOI

NeurIPS Conference 2019 Conference Paper

Deep Multimodal Multilinear Fusion with High-order Polynomial Pooling

Ming Hou
Jiajia Tang
Jianhai Zhang
Wanzeng Kong
Qibin Zhao

Tensor-based multimodal fusion techniques have exhibited great predictive performance. However, one limitation is that existing approaches only consider bilinear or trilinear pooling, which fails to unleash the complete expressive power of multilinear fusion with restricted orders of interactions. More importantly, simply fusing features all at once ignores the complex local intercorrelations, leading to the deterioration of prediction. In this work, we first propose a polynomial tensor pooling (PTP) block for integrating multimodal features by considering high-order moments, followed by a tensorized fully connected layer. Treating PTP as a building block, we further establish a hierarchical polynomial fusion network (HPFN) to recursively transmit local correlations into global ones. By stacking multiple PTPs, the expressivity capacity of HPFN enjoys an exponential growth w. r. t. the number of layers, which is shown by the equivalence to a very deep convolutional arithmetic circuits. Various experiments demonstrate that it can achieve the state-of-the-art performance.

PDF Details

IJCAI Conference 2018 Conference Paper

Generative Adversarial Positive-Unlabelled Learning

Ming Hou
Brahim Chaib-draa
Chao Li
Qibin Zhao

In this work, we consider the task of classifying binary positive-unlabeled (PU) data. The existing discriminative learning based PU models attempt to seek an optimal reweighting strategy for U data, so that a decent decision boundary can be found. However, given limited P data, the conventional PU models tend to suffer from overfitting when adapted to very flexible deep neural networks. In contrast, we are the first to innovate a totally new paradigm to attack the binary PU task, from perspective of generative learning by leveraging the powerful generative adversarial networks (GAN). Our generative positive-unlabeled (GenPU) framework incorporates an array of discriminators and generators that are endowed with different roles in simultaneously producing positive and negative realistic samples. We provide theoretical analysis to justify that, at equilibrium, GenPU is capable of recovering both positive and negative data distributions. Moreover, we show GenPU is generalizable and closely related to the semi-supervised classification. Given rather limited P data, experiments on both synthetic and real-world dataset demonstrate the effectiveness of our proposed framework. With infinite realistic and diverse sample streams generated from GenPU, a very flexible classifier can then be trained using deep neural networks.

PDF Details

IJCAI Conference 2017 Conference Paper

Fast Recursive Low-rank Tensor Learning for Regression

Ming Hou
Brahim Chaib-draa

In this work, we develop a fast sequential low-rank tensor regression framework, namely recursive higher-order partial least squares (RHOPLS). It addresses the great challenges posed by the limited storage space and fast processing time required by dynamic environments when dealing with large-scale high-speed general tensor sequences. Smartly integrating a low-rank modification strategy of Tucker into a PLS-based framework, we efficiently update the regression coefficients by effectively merging the new data into the previous low-rank approximation of the model at a small-scale factor (feature) level instead of the large raw data (observation) level. Unlike batch models, which require accessing the entire data, RHOPLS conducts a blockwise recursive calculation scheme and thus only a small set of factors is needed to be stored. Our approach is orders of magnitude faster than all other methods while maintaining a highly comparable predictability with the cutting-edge batch methods, as verified on challenging real-life tasks.

PDF Details

AAAI Conference 2016 Conference Paper

Common and Discriminative Subspace Kernel-Based Multiblock Tensor Partial Least Squares Regression

Ming Hou
Qibin Zhao
Brahim Chaib-draa
Andrzej Cichocki

In this work, we introduce a new generalized nonlinear tensor regression framework called kernel-based multiblock tensor partial least squares (KMTPLS) for predicting a set of dependent tensor blocks from a set of independent tensor blocks through the extraction of a small number of common and discriminative latent components. By considering both common and discriminative features, KMTPLS effectively fuses the information from multiple tensorial data sources and uniﬁes the single and multiblock tensor regression scenarios into one general model. Moreover, in contrast to multilinear model, KMTPLS successfully addresses the nonlinear dependencies between multiple response and predictor tensor blocks by combining kernel machines with joint Tucker decomposition, resulting in a signiﬁcant performance gain in terms of predictability. An efﬁcient learning algorithm for KMTPLS based on sequentially extracting common and discriminative latent vectors is also presented. Finally, to show the effectiveness and advantages of our approach, we test it on the real-life regression task in computer vision, i. e. , reconstruction of human pose from multiview video sequences.

PDF Details

ICRA Conference 1996 Conference Paper

On teleoperation of an arc welding robotic system

Ming Hou
Song Huat Yeo
Lin Wu
Hui Bin Zhang

A remote arc welding robotic system has been built consisting of a six degree-of-freedom master manipulator, a stereo monitoring system, a computer control system and a slave PUMA robot. The arc welding master-slave teleoperation characteristics and the hand-eye coordination are discussed. In this paper, it is shown that the eye-in-hand monitor mode can increase operation efficiency, and that the combination of automatic weld-speed control and master-slave teleoperation mode can enhance operation stability and tracking accuracy in comparison to conventional master-slave control mode.

Details

IROS Conference 1996 Conference Paper

Teleoperation characteristics and human response factor in relation to a robotic welding system

Ming Hou
Song Huat Yeo
Lin Wu
Hui Bin Zhang

A remote robotic welding system has been built consisting of a six degree-of-freedom master manipulator, a stereo monitoring system, a computer control system and a slave PUMA robot. The hand-eye coordination, the human hand respondent simulation test and the influence of master unbalanced torque on arc welding master-slave teleoperation characteristics are discussed. In this paper, the power spectral density of the trajectory deviation shows a "two humps" distribution characteristic, it will also be shown that the eye-in-hand monitor mode can increase operation efficiency, and that the combination of automatic weld-speed control and master-slave teleoperation mode can enhance operation stability and tracking accuracy in comparison to conventional master-slave control mode.

Details