Hongxia Xie
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Hongxia Xie has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Wen-Huang Cheng
National Taiwan University, Taipei, Taiwan
12 shared publications - Hong-Han Shuai
National Yang Ming Chiao Tung University, Hsinchu, Taiwan
11 shared publications - Ling Lo
National Tsing Hua University, Hsinchu, Taiwan
5 shared publications - Bin Wen
Jilin University, Changchun, China
3 shared publications - Ruoxuan Zhang
Jilin University, Changchun, China
3 shared publications - Yi Yao
National Yang Ming Chiao Tung University, Hsinchu, Taiwan
3 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 17865-17869
AffectiveArt Challenge 2026: Fine-Grained Emotion Understanding and Generation in Artistic Images
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 17865-17869
Open AccessAffectiveArt Challenge 2026: Fine-Grained Emotion Understanding and Generation in Artistic Images
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 17809-17813
TRIDENT: Tri-modal Deepfake Perception, Detection, and Hallucination Grand Challenge
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 17809-17813
Open AccessTRIDENT: Tri-modal Deepfake Perception, Detection, and Hallucination Grand Challenge
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 12644-12650
EmoArt: A Multidimensional Dataset for Emotion-Aware Artistic Generation
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 12644-12650
Open AccessEmoArt: A Multidimensional Dataset for Emotion-Aware Artistic Generation
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 12659-12665
RecipeGen: A Step-Aligned Multimodal Benchmark for Real-World Recipe Generation
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 12659-12665
Open AccessRecipeGen: A Step-Aligned Multimodal Benchmark for Real-World Recipe Generation
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 7854-7863
CookAnything: A Framework for Flexible and Consistent Multi-Step Recipe Image Generation
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 7854-7863
Open AccessCookAnything: A Framework for Flexible and Consistent Multi-Step Recipe Image Generation
- 30 September 2024
- Published by Springer Nature
- p. 422-438
The Fabrication of Reality and Fantasy: Scene Generation with LLM-Assisted Prompt Interpretation
- 30 September 2024
- Published by Springer Nature
- p. 422-438
The Fabrication of Reality and Fantasy: Scene Generation with LLM-Assisted Prompt Interpretation
- Open Access
The Fabrication of Reality and Fantasy: Scene Generation with LLM-Assisted Prompt Interpretation
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. This work explores how diffusion models can generate images from prompts requiring artistic creativity or specialized knowledge. We introduce the Realistic-Fantasy Benchmark (RFBench), a novel evaluation framework blending realistic and fantastical scenarios. To address these challenges, we propose the Realistic-Fantasy Network (RFNet), a training-free approach integrating diffusion models with LLMs. Extensive human evaluations and GPT-based compositional assessments demonstrate our approach's superiority over state-of-the-art methods. Our code and dataset is available at https://leo81005.github.io/Reality-and-Fantasy/.
Open AccessThe Fabrication of Reality and Fantasy: Scene Generation with LLM-Assisted Prompt Interpretation
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. This work explores how diffusion models can generate images from prompts requiring artistic creativity or specialized knowledge. We introduce the Realistic-Fantasy Benchmark (RFBench), a novel evaluation framework blending realistic and fantastical scenarios. To address these challenges, we propose the Realistic-Fantasy Network (RFNet), a training-free approach integrating diffusion models with LLMs. Extensive human evaluations and GPT-based compositional assessments demonstrate our approach's superiority over state-of-the-art methods. Our code and dataset is available at https://leo81005.github.io/Reality-and-Fantasy/.
- Top Cited PapersOpen Access
- 24 June 2024
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 56 (10) , 1-42
Lightweight Deep Learning for Resource-Constrained Environments: A Survey
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. While there have been remarkable improvements in model accuracy, deploying these models on lightweight devices, such as mobile phones and microcontrollers, is constrained by limited resources. In this survey, we provide comprehensive design guidance tailored for these devices, detailing the meticulous design of lightweight models, compression methods, and hardware acceleration strategies. The principal goal of this work is to explore methods and concepts for getting around hardware constraints without compromising the model’s accuracy. Additionally, we explore two notable paths for lightweight deep learning in the future: deployment techniques for TinyML and Large Language Models. Although these paths undoubtedly have potential, they also present significant challenges, encouraging research into unexplored areas.
- 24 June 2024
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 56 (10) , 1-42
Top Cited PapersOpen AccessLightweight Deep Learning for Resource-Constrained Environments: A Survey
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. While there have been remarkable improvements in model accuracy, deploying these models on lightweight devices, such as mobile phones and microcontrollers, is constrained by limited resources. In this survey, we provide comprehensive design guidance tailored for these devices, detailing the meticulous design of lightweight models, compression methods, and hardware acceleration strategies. The principal goal of this work is to explore methods and concepts for getting around hardware constraints without compromising the model’s accuracy. Additionally, we explore two notable paths for lightweight deep learning in the future: deployment techniques for TinyML and Large Language Models. Although these paths undoubtedly have potential, they also present significant challenges, encouraging research into unexplored areas.
- 7 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. 15 (3) , 977-989
CA-FER: Mitigating Spurious Correlation With Counterfactual Attention in Facial Expression Recognition
Although facial expression recognition based on deep learning has become a major trend, existing methods have been found to prefer learning spurious statistical correlations and non-robust features during training. This degenerates the model's generalizability in practical situations. One of the research fields mitigating such misperception of correlations as causality is causal reasoning. In this paper, we propose a learnable counterfactual attention mechanism, CA-FER, that uses causal reasoning to simultaneously optimize feature discrimination and diversity to mitigate spurious correlations in expression datasets. To the best of our knowledge, this is the first work to study the spurious correlations in facial expression recognition from a counterfactual attention perspective. Extensive experiments on a synthetic dataset and four public datasets demonstrate that our method outperforms previous methods, which shows the effectiveness and generalizability of our learnable counterfactual attention mechanism for the expression recognition task.
- 7 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. 15 (3) , 977-989
CA-FER: Mitigating Spurious Correlation With Counterfactual Attention in Facial Expression Recognition
Although facial expression recognition based on deep learning has become a major trend, existing methods have been found to prefer learning spurious statistical correlations and non-robust features during training. This degenerates the model's generalizability in practical situations. One of the research fields mitigating such misperception of correlations as causality is causal reasoning. In this paper, we propose a learnable counterfactual attention mechanism, CA-FER, that uses causal reasoning to simultaneously optimize feature discrimination and diversity to mitigate spurious correlations in expression datasets. To the best of our knowledge, this is the first work to study the spurious correlations in facial expression recognition from a counterfactual attention perspective. Extensive experiments on a synthetic dataset and four public datasets demonstrate that our method outperforms previous methods, which shows the effectiveness and generalizability of our learnable counterfactual attention mechanism for the expression recognition task.
- 8 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 24 (15209210) , 4275-4284
Facial Chirality: From Visual Self-Reflection to Robust Facial Feature Learning
As a fundamental vision task, facial expression recognition has made substantial progress recently. However, the recognition performance often degrades significantly in real-world scenarios due to the lack of robust facial features. In this paper, we propose an effective facial feature learning method that takes the advantage of facial chirality to discover the discriminative features for facial expression recognition. Most previous studies implicitly assume that human faces are symmetric. However, our work reveals that the facial asymmetric effect can be a crucial clue. Given a face image and its reflection without additional labels, we decouple the emotion-invariant facial features from the input image pair to better capture the emotion-related facial features. Moreover, as our model aligns emotion-related features of the image pair to enhance the recognition performance, the value of precise facial landmark alignment as a pre-processing step is reconsidered in this paper. Experiments demonstrate that the learned emotion-related features outperform the state of the art methods on several facial expression recognition benchmarks as well as real-world occlusion datasets, which manifests the effectiveness and robustness of the proposed model.
- 8 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 24 (15209210) , 4275-4284
Facial Chirality: From Visual Self-Reflection to Robust Facial Feature Learning
As a fundamental vision task, facial expression recognition has made substantial progress recently. However, the recognition performance often degrades significantly in real-world scenarios due to the lack of robust facial features. In this paper, we propose an effective facial feature learning method that takes the advantage of facial chirality to discover the discriminative features for facial expression recognition. Most previous studies implicitly assume that human faces are symmetric. However, our work reveals that the facial asymmetric effect can be a crucial clue. Given a face image and its reflection without additional labels, we decouple the emotion-invariant facial features from the input image pair to better capture the emotion-related facial features. Moreover, as our model aligns emotion-related features of the image pair to enhance the recognition performance, the value of precise facial landmark alignment as a pre-processing step is reconsidered in this paper. Experiments demonstrate that the learned emotion-related features outperform the state of the art methods on several facial expression recognition benchmarks as well as real-world occlusion datasets, which manifests the effectiveness and robustness of the proposed model.