116 citations · 301 across the 21 of their papers we have counts for
21 papers
Event ActivityNet: A Large-Scale Simulated-Event Benchmark for Untrimmed Action Understanding
Cheng-Yao Hong, Ting-Wei Lin, Yun-Chung Lai +3
Long-horizon event-based action understanding remains underexplored because existing datasets largely comprise short, trimmed clips, while collecting native event streams with dens…
EigenGS Representation: From Eigenspace to Gaussian Image Space
Lo-Wei Tai, Ching-En Li, Cheng-Lin Chen +3
Principal Component Analysis (PCA), a classical dimensionality reduction technique, and 2D Gaussian representation, an adaptation of 3D Gaussian Splatting for image representation,…
DiffusionAtlas: High-Fidelity Consistent Diffusion Video Editing
Shao-Yu Chang, Hwann-Tzong Chen, Tyng-Luh Liu
We present a diffusion-based video editing framework, namely DiffusionAtlas, which can achieve both frame consistency and high fidelity in editing video object appearance. Despite…
Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation from Monocular Video
Wen-Li Wei, Jen-Chun Lin, Tyng-Luh Liu +1
Learning to capture human motion is essential to 3D human pose and shape estimation from monocular video. However, the existing methods mainly rely on recurrent or convolutional op…
Pose Adaptive Dual Mixup for Few-Shot Single-View 3D Reconstruction
Ta-Ying Cheng, Hsuan-Ru Yang, Niki Trigoni +2
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 reconstructi…
Decoupled Contrastive Learning
Chun-Hsiao Yeh, Cheng-Yao Hong, Yen-Chi Hsu +3
Contrastive learning (CL) is one of the most successful paradigms for self-supervised learning (SSL). In a principled way, it considers two augmented "views" of the same image as p…
Learning Gaussian Instance Segmentation in Point Clouds
Shih-Hung Liu, Shang-Yi Yu, Shao-Chi Wu +2
This paper presents a novel method for instance segmentation of 3D point clouds. The proposed method is called Gaussian Instance Center Network (GICN), which can approximate the di…
Self-similarity Student for Partial Label Histopathology Image Segmentation
Hsien-Tzu Cheng, Chun-Fu Yeh, Po-Chen Kuo +6
Delineation of cancerous regions in gigapixel whole slide images (WSIs) is a crucial diagnostic procedure in digital pathology. This process is time-consuming because of the large…
Social Distancing 2.0 with Privacy-Preserving Contact Tracing to Avoid a Second Wave of COVID-19
Yu-Chen Ho, Yi-Hsuan Chen, Shen-Hua Hung +7
How to avoid a second wave of COVID-19 after reopening the economy is a pressing question. The extremely high basic reproductive number (5.7 to 6.4, shown in new studies) of…
A Cascaded Learning Strategy for Robust COVID-19 Pneumonia Chest X-Ray Screening
Chun-Fu Yeh, Hsien-Tzu Cheng, Andy Wei +20
We introduce a comprehensive screening platform for the COVID-19 (a.k.a., SARS-CoV-2) pneumonia. The proposed AI-based system works on chest x-ray (CXR) images to predict whether a…
One-Shot Object Detection with Co-Attention and Co-Excitation
Ting-I Hsieh, Yi-Chen Lo, Hwann-Tzong Chen +1
This paper aims to tackle the challenging problem of one-shot object detection. Given a query image patch whose class label is not included in the training data, the goal of the ta…
ACE: Adaptive Confusion Energy for Natural World Data Distribution
Yen-Chi Hsu, Cheng-Yao Hong, Wan-Cyuan Fan +3
With the development of deep learning, standard classification problems have achieved good results. However, conventional classification problems are often too idealistic. Most dat…
C2S2: Cost-aware Channel Sparse Selection for Progressive Network Pruning
Chih-Yao Chiu, Hwann-Tzong Chen, Tyng-Luh Liu
This paper describes a channel-selection approach for simplifying deep neural networks. Specifically, we propose a new type of generic network layer, called pruning layer, to seaml…
Unsupervised Meta-learning of Figure-Ground Segmentation via Imitating Visual Effects
Ding-Jie Chen, Jui-Ting Chien, Hwann-Tzong Chen +1
This paper presents a "learning to learn" approach to figure-ground image segmentation. By exploring webly-abundant images of specific visual effects, our method can effectively le…
Non-local RoI for Cross-Object Perception
Shou-Yao Roy Tseng, Hwann-Tzong Chen, Shao-Heng Tai +1
We present a generic and flexible module that encodes region proposals by both their intrinsic features and the extrinsic correlations to the others. The proposed non-local region…
Non-local RoIs for Instance Segmentation
Shou-Yao Roy Tseng, Hwann-Tzong Chen, Shao-Heng Tai +1
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. Mask R-C…
Cube Padding for Weakly-Supervised Saliency Prediction in 360° Videos
Hsien-Tzu Cheng, Chun-Hung Chao, Jin-Dong Dong +3
Automatic saliency prediction in 360° videos is critical for viewpoint guidance applications (e.g., Facebook 360 Guide). We propose a spatial-temporal network which is (1) weakly-s…
Guided Co-training for Large-Scale Multi-View Spectral Clustering
Tyng-Luh Liu
In many real-world applications, we have access to multiple views of the data, each of which characterizes the data from a distinct aspect. Several previous algorithms have demonst…
Implicit Sparse Code Hashing
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. D…
Pixel-wise Deep Learning for Contour Detection
Jyh-Jing Hwang, Tyng-Luh Liu
We address the problem of contour detection via per-pixel classifications of edge point. To facilitate the process, the proposed approach leverages with DenseNet, an efficient impl…
Contour Detection Using Cost-Sensitive Convolutional Neural Networks
Jyh-Jing Hwang, Tyng-Luh Liu
We address the problem of contour detection via per-pixel classifications of edge point. To facilitate the process, the proposed approach leverages with DenseNet, an efficient impl…