89 citations · 188 across the 20 of their papers we have counts for
22 papers
Learning Continuous Exposure Value Representations for Single-Image HDR Reconstruction
Su-Kai Chen, Hung-Lin Yen, Yu-Lun Liu +4
Deep learning is commonly used to reconstruct HDR images from LDR images. LDR stack-based methods are used for single-image HDR reconstruction, generating an HDR image from a deep…
Probabilistic 3D Multi-Object Cooperative Tracking for Autonomous Driving via Differentiable Multi-Sensor Kalman Filter
Hsu-kuang Chiu, Chien-Yi Wang, Min-Hung Chen +1
Current state-of-the-art autonomous driving vehicles mainly rely on each individual sensor system to perform perception tasks. Such a framework's reliability could be limited by oc…
QuAVF: Quality-aware Audio-Visual Fusion for Ego4D Talking to Me Challenge
Hsi-Che Lin, Chien-Yi Wang, Min-Hung Chen +2
This technical report describes our QuAVF@NTU-NVIDIA submission to the Ego4D Talking to Me (TTM) Challenge 2023. Based on the observation from the TTM task and the provided dataset…
A Closer Look at Geometric Temporal Dynamics for Face Anti-Spoofing
Chih-Jung Chang, Yaw-Chern Lee, Shih-Hsuan Yao +4
Face anti-spoofing (FAS) is indispensable for a face recognition system. Many texture-driven countermeasures were developed against presentation attacks (PAs), but the performance…
Causalainer: Causal Explainer for Automatic Video Summarization
Jia-Hong Huang, Chao-Han Huck Yang, Pin-Yu Chen +2
The goal of video summarization is to automatically shorten videos such that it conveys the overall story without losing relevant information. In many application scenarios, improp…
Interaction-Aware Prompting for Zero-Shot Spatio-Temporal Action Detection
Wei-Jhe Huang, Jheng-Hsien Yeh, Min-Hung Chen +2
The goal of spatial-temporal action detection is to determine the time and place where each person's action occurs in a video and classify the corresponding action category. Most o…
Kinship Representation Learning with Face Componential Relation
Weng-Tai Su, Min-Hung Chen, Chien-Yi Wang +2
Kinship recognition aims to determine whether the subjects in two facial images are kin or non-kin, which is an emerging and challenging problem. However, most previous methods foc…
Holistic Interaction Transformer Network for Action Detection
Gueter Josmy Faure, Min-Hung Chen, Shang-Hong Lai
Actions are about how we interact with the environment, including other people, objects, and ourselves. In this paper, we propose a novel multi-modal Holistic Interaction Transform…
MicroISP: Processing 32MP Photos on Mobile Devices with Deep Learning
Andrey Ignatov, Anastasia Sycheva, Radu Timofte +8
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…
PyNet-V2 Mobile: Efficient On-Device Photo Processing With Neural Networks
Andrey Ignatov, Grigory Malivenko, Radu Timofte +8
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…
Self-Supervised Robustifying Guidance for Monocular 3D Face Reconstruction
Hitika Tiwari, Min-Hung Chen, Yi-Min Tsai +5
Despite the recent developments in 3D Face Reconstruction from occluded and noisy face images, the performance is still unsatisfactory. Moreover, most existing methods rely on addi…
Learned Smartphone ISP on Mobile NPUs with Deep Learning, Mobile AI 2021 Challenge: Report
Andrey Ignatov, Cheng-Ming Chiang, Hsien-Kai Kuo +38
As the quality of mobile cameras starts to play a crucial role in modern smartphones, more and more attention is now being paid to ISP algorithms used to improve various perceptual…
Action Segmentation with Mixed Temporal Domain Adaptation
Min-Hung Chen, Baopu Li, Yingze Bao +1
The main progress for action segmentation comes from densely-annotated data for fully-supervised learning. Since manual annotation for frame-level actions is time-consuming and cha…
Network Space Search for Pareto-Efficient Spaces
Min-Fong Hong, Hao-Yun Chen, Min-Hung Chen +5
Network spaces have been known as a critical factor in both handcrafted network designs or defining search spaces for Neural Architecture Search (NAS). However, an effective space…
Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation
Min-Hung Chen, Baopu Li, Yingze Bao +2
Despite the recent progress of fully-supervised action segmentation techniques, the performance is still not fully satisfactory. One main challenge is the problem of spatiotemporal…
Interpretable Self-Attention Temporal Reasoning for Driving Behavior Understanding
Yi-Chieh Liu, Yung-An Hsieh, Min-Hung Chen +3
Performing driving behaviors based on causal reasoning is essential to ensure driving safety. In this work, we investigated how state-of-the-art 3D Convolutional Neural Networks (C…
Traffic Sign Detection under Challenging Conditions: A Deeper Look Into Performance Variations and Spectral Characteristics
Dogancan Temel, Min-Hung Chen, Ghassan AlRegib
Traffic signs are critical for maintaining the safety and efficiency of our roads. Therefore, we need to carefully assess the capabilities and limitations of automated traffic sign…
Temporal Attentive Alignment for Large-Scale Video Domain Adaptation
Min-Hung Chen, Zsolt Kira, Ghassan AlRegib +3
Although various image-based domain adaptation (DA) techniques have been proposed in recent years, domain shift in videos is still not well-explored. Most previous works only evalu…
Image Captioning with Integrated Bottom-Up and Multi-level Residual Top-Down Attention for Game Scene Understanding
Jian Zheng, Sudha Krishnamurthy, Ruxin Chen +3
Image captioning has attracted considerable attention in recent years. However, little work has been done for game image captioning which has some unique characteristics and requir…
Temporal Attentive Alignment for Video Domain Adaptation
Min-Hung Chen, Zsolt Kira, Ghassan AlRegib
Although various image-based domain adaptation (DA) techniques have been proposed in recent years, domain shift in videos is still not well-explored. Most previous works only evalu…
Challenging Environments for Traffic Sign Detection: Reliability Assessment under Inclement Conditions
Dogancan Temel, Tariq Alshawi, Min-Hung Chen +1
State-of-the-art algorithms successfully localize and recognize traffic signs over existing datasets, which are limited in terms of challenging condition type and severity. Therefo…
TS-LSTM and Temporal-Inception: Exploiting Spatiotemporal Dynamics for Activity Recognition
Chih-Yao Ma, Min-Hung Chen, Zsolt Kira +1
Recent two-stream deep Convolutional Neural Networks (ConvNets) have made significant progress in recognizing human actions in videos. Despite their success, methods extending the…