activity
20192023
most citedOpenOOD: Benchmarking Generalized Out-of-Distribution Detection

87 citations · 126 across the 14 of their papers we have counts for

collaborators

15 papers

eess.IV2022

Learned Video Compression for YUV 4:2:0 Content Using Flow-based Conditional Inter-frame Coding

Yung-Han Ho, Chih-Hsuan Lin, Peng-Yu Chen +4

This paper proposes a learning-based video compression framework for variable-rate coding on YUV 4:2:0 content. Most existing learning-based video compression models adopt the trad…

cs.CV202287 cited

OpenOOD: Benchmarking Generalized Out-of-Distribution Detection

Jingkang Yang, Pengyun Wang, Dejian Zou +13

Out-of-distribution (OOD) detection is vital to safety-critical machine learning applications and has thus been extensively studied, with a plethora of methods developed in the lit…

eess.IV2022

Neural Frank-Wolfe Policy Optimization for Region-of-Interest Intra-Frame Coding with HEVC/H.265

Yung-Han Ho, Chia-Hao Kao, Wen-Hsiao Peng +1

This paper presents a reinforcement learning (RL) framework that utilizes Frank-Wolfe policy optimization to solve Coding-Tree-Unit (CTU) bit allocation for Region-of-Interest (ROI…

eess.IV20221 cited

Action-Constrained Reinforcement Learning for Frame-Level Bit Allocation in HEVC/H.265 through Frank-Wolfe Policy Optimization

Yung-Han Ho, Yun Liang, Chia-Hao Kao +1

This paper presents a reinforcement learning (RL) framework that leverages Frank-Wolfe policy optimization to address frame-level bit allocation for HEVC/H.265. Most previous RL-ba…

eess.IV20211 cited

ANFIC: Image Compression Using Augmented Normalizing Flows

Yung-Han Ho, Chih-Chun Chan, Wen-Hsiao Peng +2

This paper introduces an end-to-end learned image compression system, termed ANFIC, based on Augmented Normalizing Flows (ANF). ANF is a new type of flow model, which stacks multip…

cs.CV2021

A Dual-Critic Reinforcement Learning Framework for Frame-level Bit Allocation in HEVC/H.265

Yung-Han Ho, Guo-Lun Jin, Yun Liang +2

This paper introduces a dual-critic reinforcement learning (RL) framework to address the problem of frame-level bit allocation in HEVC/H.265. The objective is to minimize the disto…