Search Results for author: Shang-Hong Lai

Found 22 papers, 10 papers with code

HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics

1 code implementation30 Aug 2024 Gueter Josmy Faure, Jia-Fong Yeh, Min-Hung Chen, Hung-Ting Su, Winston H. Hsu, Shang-Hong Lai

Existing research often treats long-form videos as extended short videos, leading to several limitations: inadequate capture of long-range dependencies, inefficient processing of redundant information, and failure to extract high-level semantic concepts.

Video Classification zero-shot long video breakpoint-mode question answering +3

CSAD: Unsupervised Component Segmentation for Logical Anomaly Detection

1 code implementation28 Aug 2024 Yu-Hsuan Hsieh, Shang-Hong Lai

To improve logical anomaly detection, some previous works have integrated segmentation techniques with conventional anomaly detection methods.

Anomaly Detection Segmentation

TAB: Text-Align Anomaly Backbone Model for Industrial Inspection Tasks

no code implementations15 Dec 2023 Ho-Weng Lee, Shang-Hong Lai

The proposed anomaly backbone provides a foundation model for more precise anomaly detection and localization.

Anomaly Classification Anomaly Detection

ReST: A Reconfigurable Spatial-Temporal Graph Model for Multi-Camera Multi-Object Tracking

1 code implementation ICCV 2023 Cheng-Che Cheng, Min-Xuan Qiu, Chen-Kuo Chiang, Shang-Hong Lai

Experimental results show that the proposed graph model is able to extract more discriminating features for object tracking, and our model achieves state-of-the-art performance on several public datasets.

Multi-Object Tracking

Interaction-Aware Prompting for Zero-Shot Spatio-Temporal Action Detection

1 code implementation10 Apr 2023 Wei-Jhe Huang, Jheng-Hsien Yeh, Min-Hung Chen, Gueter Josmy Faure, Shang-Hong Lai

Finally, we calculate the similarity between the interaction feature and the text feature for each label to determine the action category.

Action Detection Language Modelling +1

Kinship Representation Learning with Face Componential Relation

no code implementations10 Apr 2023 Weng-Tai Su, Min-Hung Chen, Chien-Yi Wang, Shang-Hong Lai, Trista Pei-Chun Chen

Kinship recognition aims to determine whether the subjects in two facial images are kin or non-kin, which is an emerging and challenging problem.

Relation Relation Network +1

Generalized Face Anti-Spoofing via Multi-Task Learning and One-Side Meta Triplet Loss

no code implementations29 Nov 2022 Chu-Chun Chuang, Chien-Yi Wang, Shang-Hong Lai

With the increasing variations of face presentation attacks, model generalization becomes an essential challenge for a practical face anti-spoofing system.

Depth Estimation Face Anti-Spoofing +4

MixFairFace: Towards Ultimate Fairness via MixFair Adapter in Face Recognition

1 code implementation28 Nov 2022 Fu-En Wang, Chien-Yi Wang, Min Sun, Shang-Hong Lai

In this paper, we propose MixFairFace framework to improve the fairness in face recognition models.

Attribute Face Recognition +1

Extremely Low-light Image Enhancement with Scene Text Restoration

1 code implementation1 Apr 2022 PoHao Hsu, Che-Tsung Lin, Chun Chet Ng, Jie-Long Kew, Mei Yih Tan, Shang-Hong Lai, Chee Seng Chan, Christopher Zach

Deep learning-based methods have made impressive progress in enhancing extremely low-light images - the image quality of the reconstructed images has generally improved.

Image Restoration Low-Light Image Enhancement +2

Local-Adaptive Face Recognition via Graph-based Meta-Clustering and Regularized Adaptation

no code implementations CVPR 2022 Wenbin Zhu, Chien-Yi Wang, Kuan-Lun Tseng, Shang-Hong Lai, Baoyuan Wang

Leveraging the environment-specific local data after the deployment of the initial global model, LaFR aims at getting optimal performance by training local-adapted models automatically and un-supervisely, as opposed to fixing their initial global model.

Clustering Face Recognition

FedFR: Joint Optimization Federated Framework for Generic and Personalized Face Recognition

1 code implementation23 Dec 2021 Chih-Ting Liu, Chien-Yi Wang, Shao-Yi Chien, Shang-Hong Lai

Current state-of-the-art deep learning based face recognition (FR) models require a large number of face identities for central training.

Face Recognition Federated Learning

High-Accuracy RGB-D Face Recognition via Segmentation-Aware Face Depth Estimation and Mask-Guided Attention Network

no code implementations22 Dec 2021 Meng-Tzu Chiu, Hsun-Ying Cheng, Chien-Yi Wang, Shang-Hong Lai

Our DepthNet is used to augment a large 2D face image dataset to a large RGB-D face dataset, which is used for training an accurate RGB-D face recognition model.

Depth Estimation Face Recognition +2

Disentangled Representation with Dual-stage Feature Learning for Face Anti-spoofing

no code implementations18 Oct 2021 Yu-Chun Wang, Chien-Yi Wang, Shang-Hong Lai

Unlike previous FAS disentanglement works with one-stage architecture, we found that the dual-stage training design can improve the training stability and effectively encode the features to detect unseen attack types.

Disentanglement Face Anti-Spoofing +1

ByeGlassesGAN: Identity Preserving Eyeglasses Removal for Face Images

no code implementations ECCV 2020 Yu-Hui Lee, Shang-Hong Lai

In this paper, we propose a novel image-to-image GAN framework for eyeglasses removal, called ByeGlassesGAN, which is used to automatically detect the position of eyeglasses and then remove them from face images.

Multimedia

Unified Representation Learning for Cross Model Compatibility

no code implementations11 Aug 2020 Chien-Yi Wang, Ya-Liang Chang, Shang-Ta Yang, Dong Chen, Shang-Hong Lai

We propose a unified representation learning framework to address the Cross Model Compatibility (CMC) problem in the context of visual search applications.

Face Identification Face Recognition +2

AugGAN: Cross Domain Adaptation with GAN-based Data Augmentation

no code implementations ECCV 2018 Sheng-Wei Huang, Che-Tsung Lin, Shu-Ping Chen, Yen-Yi Wu, Po-Hao Hsu, Shang-Hong Lai

Deep learning based image-to-image translation methods aim at learning the joint distribution of the two domains and finding transformations between them.

Data Augmentation Domain Adaptation +4

Non-Rigid Registration of Images With Geometric and Photometric Deformation by Using Local Affine Fourier-Moment Matching

no code implementations CVPR 2015 Hong-Ren Su, Shang-Hong Lai

Registration between images taken with different cameras, from different viewpoints or under different lighting conditions is a challenging problem.

Image Registration

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