Search Results for author: Minh N. Do

Found 36 papers, 13 papers with code

Improving the Robustness of 3D Human Pose Estimation: A Benchmark and Learning from Noisy Input

no code implementations11 Dec 2023 Trung-Hieu Hoang, Mona Zehni, Huy Phan, Duc Minh Vo, Minh N. Do

We observe the poor generalization of state-of-the-art 3D pose lifters in the presence of corruption and establish two techniques to tackle this issue.

3D Human Pose Estimation Data Augmentation

Persistent Test-time Adaptation in Episodic Testing Scenarios

no code implementations30 Nov 2023 Trung-Hieu Hoang, Duc Minh Vo, Minh N. Do

Current test-time adaptation (TTA) approaches aim to adapt to environments that change continuously.

Test-time Adaptation

Making Vision Transformers Truly Shift-Equivariant

no code implementations25 May 2023 Renan A. Rojas-Gomez, Teck-Yian Lim, Minh N. Do, Raymond A. Yeh

For computer vision, Vision Transformers (ViTs) have become one of the go-to deep net architectures.

Image Classification Semantic Segmentation

MaskDiff: Modeling Mask Distribution with Diffusion Probabilistic Model for Few-Shot Instance Segmentation

1 code implementation9 Mar 2023 Minh-Quan Le, Tam V. Nguyen, Trung-Nghia Le, Thanh-Toan Do, Minh N. Do, Minh-Triet Tran

To overcome the disadvantage of the point estimation mechanism, we propose a novel approach, dubbed MaskDiff, which models the underlying conditional distribution of a binary mask, which is conditioned on an object region and $K-$shot information.

Few-Shot Learning Instance Segmentation +1

Learnable Polyphase Sampling for Shift Invariant and Equivariant Convolutional Networks

1 code implementation14 Oct 2022 Renan A. Rojas-Gomez, Teck-Yian Lim, Alexander G. Schwing, Minh N. Do, Raymond A. Yeh

We propose learnable polyphase sampling (LPS), a pair of learnable down/upsampling layers that enable truly shift-invariant and equivariant convolutional networks.

Image Classification Segmentation +1

Efficient Human Vision Inspired Action Recognition using Adaptive Spatiotemporal Sampling

1 code implementation12 Jul 2022 Khoi-Nguyen C. Mac, Minh N. Do, Minh P. Vo

We validate the system on EPIC-KITCHENS and UCF-101 datasets for action recognition, and show that our proposed approach can greatly speed up inference with a tolerable loss of accuracy compared with those from state-of-the-art baselines.

Action Recognition

Towards a Comprehensive Solution for a Vision-based Digitized Neurological Examination

no code implementations15 May 2022 Trung-Hieu Hoang, Mona Zehni, Huaijin Xu, George Heintz, Christopher Zallek, Minh N. Do

In this paper, we propose an accessible vision-based exam and documentation solution called Digitized Neurological Examination (DNE) to expand exam biomarker recording options and clinical applications using a smartphone/tablet.

Multi-modality fusion using canonical correlation analysis methods: Application in breast cancer survival prediction from histology and genomics

1 code implementation27 Nov 2021 Vaishnavi Subramanian, Tanveer Syeda-Mahmood, Minh N. Do

We propose a two-stage prediction pipeline using pCCA embeddings generated with deflation for latent variable prediction by combining all the above.

Survival Prediction

EH-DNAS: End-to-End Hardware-aware Differentiable Neural Architecture Search

1 code implementation24 Nov 2021 Qian Jiang, Xiaofan Zhang, Deming Chen, Minh N. Do, Raymond A. Yeh

In this work, we propose End-to-end Hardware-aware DNAS (EH-DNAS), a seamless integration of end-to-end hardware benchmarking, and fully automated DNAS to deliver hardware-efficient deep neural networks on various platforms, including Edge GPUs, Edge TPUs, Mobile CPUs, and customized accelerators.

Benchmarking Neural Architecture Search

Multimodal Unrolled Robust PCA for Background Foreground Separation

no code implementations13 Aug 2021 Spencer Markowitz, Corey Snyder, Yonina C. Eldar, Minh N. Do

Background foreground separation (BFS) is a popular computer vision problem where dynamic foreground objects are separated from the static background of a scene.

Rolling Shutter Correction

Inverting Adversarially Robust Networks for Image Synthesis

1 code implementation13 Jun 2021 Renan A. Rojas-Gomez, Raymond A. Yeh, Minh N. Do, Anh Nguyen

Despite unconditional feature inversion being the foundation of many image synthesis applications, training an inverter demands a high computational budget, large decoding capacity and imposing conditions such as autoregressive priors.

Anomaly Detection Deep Feature Inversion +3

Multimodal fusion using sparse CCA for breast cancer survival prediction

1 code implementation9 Mar 2021 Vaishnavi Subramanian, Tanveer Syeda-Mahmood, Minh N. Do

Effective understanding of a disease such as cancer requires fusing multiple sources of information captured across physical scales by multimodal data.

Survival Prediction

Feature-less Stitching of Cylindrical Tunnel

no code implementations27 Jun 2018 Ramanpreet Singh Pahwa, Wei Kiat Leong, Shaohui Foong, Karianto Leman, Minh N. Do

Traditional image stitching algorithms use transforms such as homography to combine different views of a scene.

Image Stitching Position +1

Rotation Equivariance and Invariance in Convolutional Neural Networks

2 code implementations31 May 2018 Benjamin Chidester, Minh N. Do, Jian Ma

Performance of neural networks can be significantly improved by encoding known invariance for particular tasks.

Classification General Classification +1

Unsupervised Textual Grounding: Linking Words to Image Concepts

no code implementations CVPR 2018 Raymond A. Yeh, Minh N. Do, Alexander G. Schwing

Textual grounding, i. e., linking words to objects in images, is a challenging but important task for robotics and human-computer interaction.

Two-sample testing

Multi-Segment Reconstruction Using Invariant Features

1 code implementation25 Feb 2018 Mona Zehni, Minh N. Do, Zhizhen Zhao

Instead of trying to locate the segment within the sequence through pair-wise matching, we propose a new approach that uses shift-invariant features to estimate both the underlying signal and the distribution of the positions of the segments.

Signal Processing

Tracking objects using 3D object proposals

no code implementations19 Dec 2017 Ramanpreet Singh Pahwa, Tian Tsong Ng, Minh N. Do

3D object proposals, quickly detected regions in a 3D scene that likely contain an object of interest, are an effective approach to improve the computational efficiency and accuracy of the object detection framework.

Computational Efficiency Object +2

Calibration of depth cameras using denoised depth images

no code implementations8 Sep 2017 Ramanpreet Singh Pahwa, Minh N. Do, Tian Tsong Ng, Binh-Son Hua

Depth sensing devices have created various new applications in scientific and commercial research with the advent of Microsoft Kinect and PMD (Photon Mixing Device) cameras.

Camera Calibration Denoising

Locating 3D Object Proposals: A Depth-Based Online Approach

no code implementations8 Sep 2017 Ramanpreet Singh Pahwa, Jiangbo Lu, Nianjuan Jiang, Tian Tsong Ng, Minh N. Do

Using efficient but robust registration enables us to combine multiple frames of a scene in near real time and generate 3D bounding boxes for potential 3D regions of interest.

Computational Efficiency Object +3

Matrix Product State for Higher-Order Tensor Compression and Classification

no code implementations15 Sep 2016 Johann A. Bengua, Ho N. Phien, Hoang D. Tuan, Minh N. Do

This paper introduces matrix product state (MPS) decomposition as a new and systematic method to compress multidimensional data represented by higher-order tensors.

General Classification

Semantic Image Inpainting with Deep Generative Models

7 code implementations CVPR 2017 Raymond A. Yeh, Chen Chen, Teck Yian Lim, Alexander G. Schwing, Mark Hasegawa-Johnson, Minh N. Do

In this paper, we propose a novel method for semantic image inpainting, which generates the missing content by conditioning on the available data.

Image Inpainting

Concatenated image completion via tensor augmentation and completion

no code implementations14 Jul 2016 Johann A. Bengua, Hoang D. Tuan, Ho N. Phien, Minh N. Do

The proposed framework performs image completion by concatenating copies of a single image that has missing entries into a third-order tensor, applying a dimensionality augmentation technique to the tensor, utilizing a tensor completion algorithm for recovering its missing entries, and finally extracting the recovered image from the tensor.

Efficient tensor completion for color image and video recovery: Low-rank tensor train

no code implementations5 Jun 2016 Johann A. Bengua, Ho N. Phien, Hoang D. Tuan, Minh N. Do

The approach is based on the tensor train (TT) rank, which is able to capture hidden information from tensors thanks to its definition from a well-balanced matricization scheme.

Numerical Analysis Data Structures and Algorithms

DASC: Robust Dense Descriptor for Multi-modal and Multi-spectral Correspondence Estimation

no code implementations27 Apr 2016 Seungryong Kim, Dongbo Min, Bumsub Ham, Minh N. Do, Kwanghoon Sohn

In this paper, we propose a novel dense descriptor, called dense adaptive self-correlation (DASC), to estimate multi-modal and multi-spectral dense correspondences.

SPM-BP: Sped-up PatchMatch Belief Propagation for Continuous MRFs

no code implementations ICCV 2015 Yu Li, Dongbo Min, Michael S. Brown, Minh N. Do, Jiangbo Lu

However, the quality of the PMBP solution is tightly coupled with the local window size, over which the raw data cost is aggregated to mitigate ambiguity in the data constraint.

Optical Flow Estimation

PatchMatch-Based Automatic Lattice Detection for Near-Regular Textures

no code implementations ICCV 2015 Siying Liu, Tian-Tsong Ng, Kalyan Sunkavalli, Minh N. Do, Eli Shechtman, Nathan Carr

In this work, we investigate the problem of automatically inferring the lattice structure of near-regular textures (NRT) in real-world images.

Direct Structure Estimation for 3D Reconstruction

no code implementations CVPR 2015 Nianjuan Jiang, Daniel Lin, Minh N. Do, Jiangbo Lu

Most conventional structure-from-motion (SFM) techniques require camera pose estimation before computing any scene structure.

3D Reconstruction Homography Estimation +2

DASC: Dense Adaptive Self-Correlation Descriptor for Multi-Modal and Multi-Spectral Correspondence

no code implementations CVPR 2015 Seungryong Kim, Dongbo Min, Bumsub Ham, Seungchul Ryu, Minh N. Do, Kwanghoon Sohn

To further improve the matching quality and runtime efficiency, we propose a patch-wise receptive field pooling, in which a sampling pattern is optimized with a discriminative learning.

Optical Flow Estimation

Weakly Supervised Fine-Grained Image Categorization

no code implementations20 Apr 2015 Yu Zhang, Xiu-Shen Wei, Jianxin Wu, Jianfei Cai, Jiangbo Lu, Viet-Anh Nguyen, Minh N. Do

Most existing works heavily rely on object / part detectors to build the correspondence between object parts by using object or object part annotations inside training images.

Fine-Grained Image Classification Image Categorization +1

Matrix Product State for Feature Extraction of Higher-Order Tensors

no code implementations2 Mar 2015 Johann A. Bengua, Ho N. Phien, Hoang D. Tuan, Minh N. Do

This paper introduces matrix product state (MPS) decomposition as a computational tool for extracting features of multidimensional data represented by higher-order tensors.

General Classification

Patch Match Filter: Efficient Edge-Aware Filtering Meets Randomized Search for Fast Correspondence Field Estimation

no code implementations CVPR 2013 Jiangbo Lu, Hongsheng Yang, Dongbo Min, Minh N. Do

Recent studies on fast cost volume filtering based on efficient edge-aware filters have provided a fast alternative to solve discrete labeling problems, with the complexity independent of the support window size.

Computational Efficiency Optical Flow Estimation +1

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