Search Results for author: Tyng-Luh Liu

Found 30 papers, 7 papers with code

DiffusionAtlas: High-Fidelity Consistent Diffusion Video Editing

no code implementations5 Dec 2023 Shao-Yu Chang, Hwann-Tzong Chen, Tyng-Luh Liu

Despite the success in image editing, diffusion models still encounter significant hindrances when it comes to video editing due to the challenge of maintaining spatiotemporal consistency in the object's appearance across frames.

Object Video Editing

Attention Discriminant Sampling for Point Clouds

no code implementations ICCV 2023 Cheng-Yao Hong, Yu-Ying Chou, Tyng-Luh Liu

The proposed attention discriminant sampling (ADS) starts by efficiently decomposing a given point cloud into clusters to implicitly encode its structural and geometric relatedness among points.

object-detection Object Detection +3

Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation from Monocular Video

no code implementations CVPR 2022 Wen-Li Wei, Jen-Chun Lin, Tyng-Luh Liu, Hong-Yuan Mark Liao

To address this problem, we propose a motion pose and shape network (MPS-Net) to effectively capture humans in motion to estimate accurate and temporally coherent 3D human pose and shape from a video.

3D human pose and shape estimation

Pose Adaptive Dual Mixup for Few-Shot Single-View 3D Reconstruction

no code implementations23 Dec 2021 Ta-Ying Cheng, Hsuan-ru Yang, Niki Trigoni, Hwann-Tzong Chen, Tyng-Luh Liu

We present a pose adaptive few-shot learning procedure and a two-stage data interpolation regularization, termed Pose Adaptive Dual Mixup (PADMix), for single-image 3D reconstruction.

3D Reconstruction Few-Shot Learning +1

Decoupled Contrastive Learning

4 code implementations13 Oct 2021 Chun-Hsiao Yeh, Cheng-Yao Hong, Yen-Chi Hsu, Tyng-Luh Liu, Yubei Chen, Yann Lecun

Further, DCL can be combined with the SOTA contrastive learning method, NNCLR, to achieve 72. 3% ImageNet-1K top-1 accuracy with 512 batch size in 400 epochs, which represents a new SOTA in contrastive learning.

Contrastive Learning Self-Supervised Learning

From Graph Local Embedding to Deep Metric Learning

no code implementations29 Sep 2021 Bing-Jhang Lin, Ding-Jie Chen, He-Yen Hsieh, Tyng-Luh Liu

We comprehensively identify the missing neighborhood relationships issue of conventional embedding and propose a novel approach, termed as Graph Local Embedding (GLE), to deep metric learning.

Metric Learning Retrieval

Adaptive Image Transformer for One-Shot Object Detection

no code implementations CVPR 2021 Ding-Jie Chen, He-Yen Hsieh, Tyng-Luh Liu

One-shot object detection tackles a challenging task that aims at identifying within a target image all object instances of the same class, implied by a query image patch.

Object object-detection +2

Feature Integration and Group Transformers for Action Proposal Generation

no code implementations1 Jan 2021 He-Yen Hsieh, Ding-Jie Chen, Tung-Ying Lee, Tyng-Luh Liu

The task of temporal action proposal generation (TAPG) aims to provide high-quality video segments, i. e., proposals that potentially contain action events.

Temporal Action Proposal Generation

Adaptive and Generative Zero-Shot Learning

1 code implementation ICLR 2021 Yu-Ying Chou, Hsuan-Tien Lin, Tyng-Luh Liu

In addition, to break the limit of training with images only from seen classes, we design a generative scheme to simultaneously generate virtual class labels and their visual features by sampling and interpolating over seen counterparts.

Generalized Zero-Shot Learning

Natural World Distribution via Adaptive Confusion Energy Regularization

no code implementations1 Jan 2021 Yen-Chi Hsu, Cheng-Yao Hong, Wan-Cyuan Fan, Ding-Jie Chen, Ming-Sui Lee, Davi Geiger, Tyng-Luh Liu

The Fine-Grained Visual Classification (FGVC) problem is notably characterized by two intriguing properties, significant inter-class similarity and intra-class variations, which cause learning an effective FGVC classifier a challenging task.

Fine-Grained Image Classification

Self-similarity Student for Partial Label Histopathology Image Segmentation

no code implementations ECCV 2020 Hsien-Tzu Cheng, Chun-Fu Yeh, Po-Chen Kuo, Andy Wei, Keng-Chi Liu, Mong-Chi Ko, Kuan-Hua Chao, Yu-Ching Peng, Tyng-Luh Liu

Following this similarity learning, our similarity ensemble merges similar patches' ensembled predictions as the pseudo-label of a given patch to counteract its noisy label.

Image Segmentation Pseudo Label +2

Non-local RoI for Cross-Object Perception

no code implementations25 Nov 2018 Shou-Yao Roy Tseng, Hwann-Tzong Chen, Shao-Heng Tai, Tyng-Luh Liu

We present a generic and flexible module that encodes region proposals by both their intrinsic features and the extrinsic correlations to the others.

Instance Segmentation Object +5

Non-local RoIs for Instance Segmentation

no code implementations14 Jul 2018 Shou-Yao Roy Tseng, Hwann-Tzong Chen, Shao-Heng Tai, Tyng-Luh Liu

We introduce the concept of Non-Local RoI (NL-RoI) Block as a generic and flexible module that can be seamlessly adapted into different Mask R-CNN heads for various tasks.

Instance Segmentation Segmentation +1

Cube Padding for Weakly-Supervised Saliency Prediction in 360° Videos

no code implementations CVPR 2018 Hsien-Tzu Cheng, Chun-Hung Chao, Jin-Dong Dong, Hao-Kai Wen, Tyng-Luh Liu, Min Sun

Then, we concatenate all six faces while utilizing the connectivity between faces on the cube for image padding (i. e., Cube Padding) in convolution, pooling, convolutional LSTM layers.

Saliency Prediction

Cube Padding for Weakly-Supervised Saliency Prediction in 360° Videos

no code implementations CVPR 2018 Hsien-Tzu Cheng, Chun-Hung Chao, Jin-Dong Dong, Hao-Kai Wen, Tyng-Luh Liu, Min Sun

Then, we concatenate all six faces while utilizing the connectivity between faces on the cube for image padding (i. e., Cube Padding) in convolution, pooling, convolutional LSTM layers.

Saliency Prediction

Guided Co-training for Large-Scale Multi-View Spectral Clustering

no code implementations18 Jul 2017 Tyng-Luh Liu

In this work, we propose a novel multi-view spectral clustering method for large-scale data.

Clustering

Implicit Sparse Code Hashing

no code implementations1 Dec 2015 Tsung-Yu Lin, Tsung-Wei Ke, Tyng-Luh Liu

We address the problem of converting large-scale high-dimensional image data into binary codes so that approximate nearest-neighbor search over them can be efficiently performed.

Dimensionality Reduction

Pixel-wise Deep Learning for Contour Detection

no code implementations8 Apr 2015 Jyh-Jing Hwang, Tyng-Luh Liu

We address the problem of contour detection via per-pixel classifications of edge point.

Contour Detection

Contour Detection Using Cost-Sensitive Convolutional Neural Networks

no code implementations22 Dec 2014 Jyh-Jing Hwang, Tyng-Luh Liu

We address the problem of contour detection via per-pixel classifications of edge point.

Contour Detection

Dimensionality Reduction for Data in Multiple Feature Representations

no code implementations NeurIPS 2008 Yen-Yu Lin, Tyng-Luh Liu, Chiou-Shann Fuh

In solving complex visual learning tasks, adopting multiple descriptors to more precisely characterize the data has been a feasible way for improving performance.

Clustering Dimensionality Reduction +2

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