Search Results for author: Min-Hung Chen

Found 29 papers, 14 papers with code

DoRA: Weight-Decomposed Low-Rank Adaptation

2 code implementations14 Feb 2024 Shih-Yang Liu, Chien-Yi Wang, Hongxu Yin, Pavlo Molchanov, Yu-Chiang Frank Wang, Kwang-Ting Cheng, Min-Hung Chen

By employing DoRA, we enhance both the learning capacity and training stability of LoRA while avoiding any additional inference overhead.

SemPLeS: Semantic Prompt Learning for Weakly-Supervised Semantic Segmentation

no code implementations22 Jan 2024 Ci-Siang Lin, Chien-Yi Wang, Yu-Chiang Frank Wang, Min-Hung Chen

To address the issues, we propose a Semantic Prompt Learning for WSSS (SemPLeS) framework, which learns to effectively prompt the CLIP space to enhance the semantic alignment between the segmented regions and the target object categories.

Object Segmentation +2

PartDistill: 3D Shape Part Segmentation by Vision-Language Model Distillation

no code implementations7 Dec 2023 Ardian Umam, Cheng-Kun Yang, Min-Hung Chen, Jen-Hui Chuang, Yen-Yu Lin

This paper proposes a cross-modal distillation framework, PartDistill, which transfers 2D knowledge from vision-language models (VLMs) to facilitate 3D shape part segmentation.

3D Part Segmentation Language Modelling +1

Conditional Modeling Based Automatic Video Summarization

no code implementations20 Nov 2023 Jia-Hong Huang, Chao-Han Huck Yang, Pin-Yu Chen, Min-Hung Chen, Marcel Worring

The aim of video summarization is to shorten videos automatically while retaining the key information necessary to convey the overall story.

Video Summarization

2D-3D Interlaced Transformer for Point Cloud Segmentation with Scene-Level Supervision

no code implementations ICCV 2023 Cheng-Kun Yang, Min-Hung Chen, Yung-Yu Chuang, Yen-Yu Lin

Considering the high annotation cost of point clouds, effective 2D and 3D feature fusion based on weakly supervised learning is in great demand.

Point Cloud Segmentation Segmentation +1

Probabilistic 3D Multi-Object Cooperative Tracking for Autonomous Driving via Differentiable Multi-Sensor Kalman Filter

2 code implementations26 Sep 2023 Hsu-kuang Chiu, Chien-Yi Wang, Min-Hung Chen, Stephen F. Smith

However, their proposed methods mainly use cooperative detection results as input to a standard single-sensor Kalman Filter-based tracking algorithm.

3D Multi-Object Tracking Autonomous Driving

Frequency-Aware Self-Supervised Long-Tailed Learning

no code implementations9 Sep 2023 Ci-Siang Lin, Min-Hung Chen, Yu-Chiang Frank Wang

Data collected from the real world typically exhibit long-tailed distributions, where frequent classes contain abundant data while rare ones have only a limited number of samples.

Self-Supervised Learning

Learning Continuous Exposure Value Representations for Single-Image HDR Reconstruction

no code implementations ICCV 2023 Su-Kai Chen, Hung-Lin Yen, Yu-Lun Liu, Min-Hung Chen, Hou-Ning Hu, Wen-Hsiao Peng, Yen-Yu Lin

To address this, we propose the continuous exposure value representation (CEVR), which uses an implicit function to generate LDR images with arbitrary EVs, including those unseen during training.

HDR Reconstruction

QuAVF: Quality-aware Audio-Visual Fusion for Ego4D Talking to Me Challenge

1 code implementation30 Jun 2023 Hsi-Che Lin, Chien-Yi Wang, Min-Hung Chen, Szu-Wei Fu, Yu-Chiang Frank Wang

This technical report describes our QuAVF@NTU-NVIDIA submission to the Ego4D Talking to Me (TTM) Challenge 2023.

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

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

PyNet-V2 Mobile: Efficient On-Device Photo Processing With Neural Networks

1 code implementation8 Nov 2022 Andrey Ignatov, Grigory Malivenko, Radu Timofte, Yu Tseng, Yu-Syuan Xu, Po-Hsiang Yu, Cheng-Ming Chiang, Hsien-Kai Kuo, Min-Hung Chen, Chia-Ming Cheng, Luc van Gool

The increased importance of mobile photography created a need for fast and performant RAW image processing pipelines capable of producing good visual results in spite of the mobile camera sensor limitations.

MicroISP: Processing 32MP Photos on Mobile Devices with Deep Learning

no code implementations8 Nov 2022 Andrey Ignatov, Anastasia Sycheva, Radu Timofte, Yu Tseng, Yu-Syuan Xu, Po-Hsiang Yu, Cheng-Ming Chiang, Hsien-Kai Kuo, Min-Hung Chen, Chia-Ming Cheng, Luc van Gool

While neural networks-based photo processing solutions can provide a better image quality compared to the traditional ISP systems, their application to mobile devices is still very limited due to their very high computational complexity.

Self-Supervised Robustifying Guidance for Monocular 3D Face Reconstruction

1 code implementation29 Dec 2021 Hitika Tiwari, Min-Hung Chen, Yi-Min Tsai, Hsien-Kai Kuo, Hung-Jen Chen, Kevin Jou, K. S. Venkatesh, Yong-Sheng Chen

Therefore, we propose a Self-Supervised RObustifying GUidancE (ROGUE) framework to obtain robustness against occlusions and noise in the face images.

3D Face Reconstruction

Network Space Search for Pareto-Efficient Spaces

no code implementations22 Apr 2021 Min-Fong Hong, Hao-Yun Chen, Min-Hung Chen, Yu-Syuan Xu, Hsien-Kai Kuo, Yi-Min Tsai, Hung-Jen Chen, Kevin Jou

We propose an NSS method to directly search for efficient-aware network spaces automatically, reducing the manual effort and immense cost in discovering satisfactory ones.

Neural Architecture Search

Action Segmentation with Mixed Temporal Domain Adaptation

no code implementations15 Apr 2021 Min-Hung Chen, Baopu Li, Yingze Bao, Ghassan AlRegib

The main progress for action segmentation comes from densely-annotated data for fully-supervised learning.

Action Segmentation Domain Adaptation

Traffic Sign Detection under Challenging Conditions: A Deeper Look Into Performance Variations and Spectral Characteristics

2 code implementations29 Aug 2019 Dogancan Temel, Min-Hung Chen, Ghassan AlRegib

We investigate the effect of challenging conditions through spectral analysis and show that challenging conditions can lead to distinct magnitude spectrum characteristics.

Test Traffic Sign Detection +1

Temporal Attentive Alignment for Large-Scale Video Domain Adaptation

5 code implementations ICCV 2019 Min-Hung Chen, Zsolt Kira, Ghassan AlRegib, Jaekwon Yoo, Ruxin Chen, Jian Zheng

Finally, we propose Temporal Attentive Adversarial Adaptation Network (TA3N), which explicitly attends to the temporal dynamics using domain discrepancy for more effective domain alignment, achieving state-of-the-art performance on four video DA datasets (e. g. 7. 9% accuracy gain over "Source only" from 73. 9% to 81. 8% on "HMDB --> UCF", and 10. 3% gain on "Kinetics --> Gameplay").

Unsupervised Domain Adaptation

Temporal Attentive Alignment for Video Domain Adaptation

5 code implementations26 May 2019 Min-Hung Chen, Zsolt Kira, Ghassan AlRegib

Finally, we propose Temporal Attentive Adversarial Adaptation Network (TA3N), which explicitly attends to the temporal dynamics using domain discrepancy for more effective domain alignment, achieving state-of-the-art performance on three video DA datasets.

Domain Adaptation

Challenging Environments for Traffic Sign Detection: Reliability Assessment under Inclement Conditions

2 code implementations19 Feb 2019 Dogancan Temel, Tariq Alshawi, Min-Hung Chen, Ghassan AlRegib

Experimental results show that benchmarked algorithms are highly sensitive to tested challenging conditions, which result in an average performance drop of 0. 17 in terms of precision and a performance drop of 0. 28 in recall under severe conditions.

Traffic Sign Detection

TS-LSTM and Temporal-Inception: Exploiting Spatiotemporal Dynamics for Activity Recognition

4 code implementations30 Mar 2017 Chih-Yao Ma, Min-Hung Chen, Zsolt Kira, Ghassan AlRegib

We demonstrate that using both RNNs (using LSTMs) and Temporal-ConvNets on spatiotemporal feature matrices are able to exploit spatiotemporal dynamics to improve the overall performance.

Action Classification Action Recognition +3

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