Search Results for author: Hong-Han Shuai

Found 44 papers, 22 papers with code

Character-Preserving Coherent Story Visualization

2 code implementations ECCV 2020 Yun-Zhu Song, Zhi Rui Tam, Hung-Jen Chen, Huiao-Han Lu, Hong-Han Shuai

Different from video generation that focuses on maintaining the continuity of generated images (frames), story visualization emphasizes preserving the global consistency of characters and scenes across different story pictures, which is very challenging since story sentences only provide sparse signals for generating images.

Ranked #4 on Story Visualization on Pororo (using extra training data)

Representation Learning Sentence +1

Feature-based One-For-All: A Universal Framework for Heterogeneous Knowledge Distillation

no code implementations15 Jan 2025 Jhe-Hao Lin, Yi Yao, Chan-Feng Hsu, HongXia Xie, Hong-Han Shuai, Wen-Huang Cheng

Knowledge distillation (KD) involves transferring knowledge from a pre-trained heavy teacher model to a lighter student model, thereby reducing the inference cost while maintaining comparable effectiveness.

Knowledge Distillation

IKDP: Inverse Kinematics through Diffusion Process

no code implementations20 Oct 2024 Hao-Tang Tsui, Yu-Rou Tuan, Hong-Han Shuai

This can be solved in two ways, forward kinematics method and inverse kinematics method.

Denoising Position

A Cat Is A Cat (Not A Dog!): Unraveling Information Mix-ups in Text-to-Image Encoders through Causal Analysis and Embedding Optimization

1 code implementation1 Oct 2024 Chieh-Yun Chen, Chiang Tseng, Li-Wu Tsao, Hong-Han Shuai

In this paper, we share a comprehensive analysis of text embedding: i) how text embedding contributes to the generated images and ii) why information gets lost and biases towards the first-mentioned object.

Denoising

ReCorD: Reasoning and Correcting Diffusion for HOI Generation

1 code implementation25 Jul 2024 Jian-Yu Jiang-Lin, Kang-Yang Huang, Ling Lo, Yi-Ning Huang, Terence Lin, Jhih-Ciang Wu, Hong-Han Shuai, Wen-Huang Cheng

Our model couples Latent Diffusion Models with Visual Language Models to refine the generation process, ensuring precise depictions of HOIs.

Object Text-to-Image Generation

The Fabrication of Reality and Fantasy: Scene Generation with LLM-Assisted Prompt Interpretation

no code implementations17 Jul 2024 Yi Yao, Chan-Feng Hsu, Jhe-Hao Lin, HongXia Xie, Terence Lin, Yi-Ning Huang, Hong-Han Shuai, Wen-Huang Cheng

In spite of recent advancements in text-to-image generation, limitations persist in handling complex and imaginative prompts due to the restricted diversity and complexity of training data.

Diversity Scene Generation +1

A DeNoising FPN With Transformer R-CNN for Tiny Object Detection

2 code implementations9 Jun 2024 Hou-I Liu, Yu-Wen Tseng, Kai-Cheng Chang, Pin-Jyun Wang, Hong-Han Shuai, Wen-Huang Cheng

Second, based on the two-stage framework, we replace the obsolete R-CNN detector with a novel Trans R-CNN detector to focus on the representation of tiny objects with self-attention.

Contrastive Learning Denoising +2

SocialNLP Fake-EmoReact 2021 Challenge Overview: Predicting Fake Tweets from Their Replies and GIFs

no code implementations31 May 2024 Chien-Kun Huang, Yi-Ting Chang, Lun-Wei Ku, Cheng-Te Li, Hong-Han Shuai

This paper provides an overview of the Fake-EmoReact 2021 Challenge, held at the 9th SocialNLP Workshop, in conjunction with NAACL 2021.

EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuning

1 code implementation CVPR 2024 HongXia Xie, Chu-Jun Peng, Yu-Wen Tseng, Hung-Jen Chen, Chan-Feng Hsu, Hong-Han Shuai, Wen-Huang Cheng

Visual Instruction Tuning represents a novel learning paradigm involving the fine-tuning of pre-trained language models using task-specific instructions.

Emotion Classification Emotion Recognition

Training-and-Prompt-Free General Painterly Harmonization via Zero-Shot Disentenglement on Style and Content References

1 code implementation19 Apr 2024 Teng-Fang Hsiao, Bo-Kai Ruan, Hong-Han Shuai

TF-GPH incorporates a novel ``Similarity Disentangle Mask'', which disentangles the foreground content and background image by redirecting their attention to corresponding reference images, enhancing the attention mechanism for multi-image inputs.

Image Harmonization

Lightweight Deep Learning for Resource-Constrained Environments: A Survey

no code implementations8 Apr 2024 Hou-I Liu, Marco Galindo, HongXia Xie, Lai-Kuan Wong, Hong-Han Shuai, Yung-Hui Li, Wen-Huang Cheng

Over the past decade, the dominance of deep learning has prevailed across various domains of artificial intelligence, including natural language processing, computer vision, and biomedical signal processing.

Deep Learning Survey

DQ-DETR: DETR with Dynamic Query for Tiny Object Detection

2 code implementations4 Apr 2024 Yi-Xin Huang, Hou-I Liu, Hong-Han Shuai, Wen-Huang Cheng

DQ-DETR uses the prediction and density maps from the categorical counting module to dynamically adjust the number of object queries and improve the positional information of queries.

Object object-detection +1

Distraction is All You Need: Memory-Efficient Image Immunization against Diffusion-Based Image Editing

no code implementations CVPR 2024 Ling Lo, Cheng Yu Yeo, Hong-Han Shuai, Wen-Huang Cheng

To address the concerns we propose an image immunization approach named semantic attack to protect our images from being manipulated by malicious agents using diffusion models.

Denoising Image Inpainting +1

SINC: Self-Supervised In-Context Learning for Vision-Language Tasks

no code implementations ICCV 2023 Yi-Syuan Chen, Yun-Zhu Song, Cheng Yu Yeo, Bei Liu, Jianlong Fu, Hong-Han Shuai

To this end, we raise a question: ``How can we enable in-context learning without relying on the intrinsic in-context ability of large language models?".

Hallucination In-Context Learning

Shilling Black-box Review-based Recommender Systems through Fake Review Generation

no code implementations27 Jun 2023 Hung-Yun Chiang, Yi-Syuan Chen, Yun-Zhu Song, Hong-Han Shuai, Jason S. Chang

Review-Based Recommender Systems (RBRS) have attracted increasing research interest due to their ability to alleviate well-known cold-start problems.

Diversity Recommendation Systems +1

SPEC: Summary Preference Decomposition for Low-Resource Abstractive Summarization

no code implementations24 Mar 2023 Yi-Syuan Chen, Yun-Zhu Song, Hong-Han Shuai

The generated summaries could therefore be constrained by the preference bias in the training set, especially under low-resource settings.

Abstractive Text Summarization Few-Shot Learning +1

Size Does Matter: Size-aware Virtual Try-on via Clothing-oriented Transformation Try-on Network

1 code implementation ICCV 2023 Chieh-Yun Chen, Yi-Chung Chen, Hong-Han Shuai, Wen-Huang Cheng

COTTON leverages clothing structure with landmarks and segmentation to design a novel landmark-guided transformation for precisely deforming clothes, allowing for size adjustment during try-on.

Virtual Try-on

ShuttleNet: Position-aware Fusion of Rally Progress and Player Styles for Stroke Forecasting in Badminton

1 code implementation2 Dec 2021 Wei-Yao Wang, Hong-Han Shuai, Kai-Shiang Chang, Wen-Chih Peng

The increasing demand for analyzing the insights in sports has stimulated a line of productive studies from a variety of perspectives, e. g., health state monitoring, outcome prediction.

Decoder Position

Attack as the Best Defense: Nullifying Image-to-image Translation GANs via Limit-aware Adversarial Attack

1 code implementation ICCV 2021 Chin-Yuan Yeh, Hsi-Wen Chen, Hong-Han Shuai, De-Nian Yang, Ming-Syan Chen

To improve efficiency, we introduce the limit-aware random gradient-free estimation and the gradient sliding mechanism to estimate the gradient that adheres to the adversarial limit, i. e., the pixel value limitations of the adversarial example.

Adversarial Attack Face Swapping +2

Live Multi-Streaming and Donation Recommendations via Coupled Donation-Response Tensor Factorization

no code implementations5 Oct 2021 Hsu-Chao Lai, Jui-Yi Tsai, Hong-Han Shuai, Jiun-Long Huang, Wang-Chien Lee, De-Nian Yang

In contrast to traditional online videos, live multi-streaming supports real-time social interactions between multiple streamers and viewers, such as donations.

Recommendation Systems

Mask or Non-Mask? Robust Face Mask Detector via Triplet-Consistency Representation Learning

no code implementations1 Oct 2021 Chun-Wei Yang, Thanh-Hai Phung, Hong-Han Shuai, Wen-Huang Cheng

To automate the monitoring process, one of the promising solutions is to leverage existing object detection models to detect the faces with or without masks.

object-detection Object Detection +2

Gradient Normalization for Generative Adversarial Networks

1 code implementation ICCV 2021 Yi-Lun Wu, Hong-Han Shuai, Zhi-Rui Tam, Hong-Yu Chiu

In this paper, we propose a novel normalization method called gradient normalization (GN) to tackle the training instability of Generative Adversarial Networks (GANs) caused by the sharp gradient space.

Technical Report for Valence-Arousal Estimation in ABAW2 Challenge

no code implementations8 Jul 2021 Hong-Xia Xie, I-Hsuan Li, Ling Lo, Hong-Han Shuai, Wen-Huang Cheng

In this work, we describe our method for tackling the valence-arousal estimation challenge from ABAW2 ICCV-2021 Competition.

Arousal Estimation

Reproducibility Companion Paper: Knowledge Enhanced Neural Fashion Trend Forecasting

1 code implementation25 May 2021 Yunshan Ma, Yujuan Ding, Xun Yang, Lizi Liao, Wai Keung Wong, Tat-Seng Chua, Jinyoung Moon, Hong-Han Shuai

This companion paper supports the replication of the fashion trend forecasting experiments with the KERN (Knowledge Enhanced Recurrent Network) method that we presented in the ICMR 2020.

Meta-Transfer Learning for Low-Resource Abstractive Summarization

1 code implementation18 Feb 2021 Yi-Syuan Chen, Hong-Han Shuai

Neural abstractive summarization has been studied in many pieces of literature and achieves great success with the aid of large corpora.

Abstractive Text Summarization Transfer Learning

Template-Free Try-on Image Synthesis via Semantic-guided Optimization

no code implementations6 Feb 2021 Chien-Lung Chou, Chieh-Yun Chen, Chia-Wei Hsieh, Hong-Han Shuai, Jiaying Liu, Wen-Huang Cheng

Afterward, given an in-shop clothing image, a user image, and a synthesized pose, we propose a novel model for synthesizing a human try-on image with the target clothing in the best fitting pose.

Image Generation Virtual Try-on

Spatiotemporal Dilated Convolution with Uncertain Matching for Video-based Crowd Estimation

1 code implementation29 Jan 2021 Yu-Jen Ma, Hong-Han Shuai, Wen-Huang Cheng

In this paper, we propose a novel SpatioTemporal convolutional Dense Network (STDNet) to address the video-based crowd counting problem, which contains the decomposition of 3D convolution and the 3D spatiotemporal dilated dense convolution to alleviate the rapid growth of the model size caused by the Conv3D layer.

Crowd Counting

FashionMirror: Co-Attention Feature-Remapping Virtual Try-On With Sequential Template Poses

1 code implementation ICCV 2021 Chieh-Yun Chen, Ling Lo, Pin-Jui Huang, Hong-Han Shuai, Wen-Huang Cheng

In the second stage, we first remove the clothes on the source human via the removed mask and warp the clothing features conditioning on the try-on clothing mask to fit the next frame human.

Segmentation Semantic Segmentation +1

Domain-Adaptive Object Detection via Uncertainty-Aware Distribution Alignment

1 code implementation31 Oct 2020 Dang-Khoa Nguyen, Wei-Lun Tseng, Hong-Han Shuai

Domain adaptation aims to transfer knowledge from the sourcedata with annotations to scarcely-labeled data in the target domain, which has attracted a lot of attention in recent years and facilitatedmany multimedia applications.

Object object-detection +2

Optimizing Item and Subgroup Configurations for Social-Aware VR Shopping

1 code implementation11 Feb 2020 Shao-Heng Ko, Hsu-Chao Lai, Hong-Han Shuai, De-Nian Yang, Wang-Chien Lee, Philip S. Yu

Shopping in VR malls has been regarded as a paradigm shift for E-commerce, but most of the conventional VR shopping platforms are designed for a single user.

Data Structures and Algorithms

Attractive or Faithful? Popularity-Reinforced Learning for Inspired Headline Generation

1 code implementation6 Feb 2020 Yun-Zhu Song, Hong-Han Shuai, Sung-Lin Yeh, Yi-Lun Wu, Lun-Wei Ku, Wen-Chih Peng

To generate inspired headlines, we propose a novel framework called POpularity-Reinforced Learning for inspired Headline Generation (PORL-HG).

Headline Generation Reinforcement Learning +2

Communications and Networking Technologies for Intelligent Drone Cruisers

no code implementations25 Sep 2019 Li-Chun Wang, Chuan-Chi Lai, Hong-Han Shuai, Hsin-Piao Lin, Chi-Yu Li, Teng-Hu Cheng, Chiun-Hsun Chen

Therefore, we propose to develop an "Artificial Intelligence (AI) Drone-Cruiser" base station that can help 5G mobile communication systems and beyond quickly recover the network after a disaster and handle the instant communications by the flash crowd.

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