arXiv subjects

Cheng-An Hsieh

Publications and source records attributed to Cheng-An Hsieh.

3 recordsLinked to original sources

arXiv2025

Inferring Obscured Cosmic Black Hole Accretion History from AGN Found by JWST/MIRI CEERS Survey

This study presents the black hole accretion history (BHAH) of obscured active galactic nuclei (AGNs) identified from the JWST CEERS survey by Chien et al. (2024) using mid-infrared (MIR) SED fitting. We compute black hole accretion rates (BHARs) to estimate the black hole accretion density (BHAD), $\rho_{L_{\mathrm{disk}}}$, across $0 < z < 4.25$. MIR luminosity functions (LFs) are also constructed for these sources, modeled with modified Schechter and double power law forms, and corresponding BHAD, $\rho_{\mathrm{LF}}$, is derived by integrating the LFs and multiplying by the luminosity. Both $\rho_{\mathrm{LF}}$ extend to luminosities as low as $10^7 \, L_{\odot}$, two orders of magnitude fainter than pre-JWST studies. Our results show that BHAD peaks between redshifts 1 and 3, with the peak varying by method and model, $z \approx 1$--2 for $\rho_{L_{\mathrm{disk}}}$ and the double power law, and $z \approx 2$--3 for the modified Schechter function. A scenario where AGN activity peaks before cosmic star formation would challenge existing black hole formation theories, but our present study, based on early JWST observations, provides an initial exploration of this possibility. At $z \sim 3$, $\rho_{\mathrm{LF}}$ appears higher than X-ray estimates, suggesting that MIR observations are more effective in detecting obscured AGNs missed by X-ray observations. However, given the overlapping error bars, this difference remains within the uncertainties and requires confirmation with larger samples. These findings highlight the potential of JWST surveys to enhance the understanding of co-evolution between galaxies and AGNs.

astro-ph.GA↗

arXiv2024

Sprite Sheet Diffusion: Generate Game Character for Animation

In the game development process, creating character animations is a vital step that involves several stages. Typically for 2D games, illustrators begin by designing the main character image, which serves as the foundation for all subsequent animations. To create a smooth motion sequence, these subsequent animations involve drawing the character in different poses and actions, such as running, jumping, or attacking. This process requires significant manual effort from illustrators, as they must meticulously ensure consistency in design, proportions, and style across multiple motion frames. Each frame is drawn individually, making this a time-consuming and labor-intensive task. Generative models, such as diffusion models, have the potential to revolutionize this process by automating the creation of sprite sheets. Diffusion models, known for their ability to generate diverse images, can be adapted to create character animations. By leveraging the capabilities of diffusion models, we can significantly reduce the manual workload for illustrators, accelerate the animation creation process, and open up new creative possibilities in game development.

cs.GR↗

arXiv2022

Mr. Right: Multimodal Retrieval on Representation of ImaGe witH Text

Multimodal learning is a recent challenge that extends unimodal learning by generalizing its domain to diverse modalities, such as texts, images, or speech. This extension requires models to process and relate information from multiple modalities. In Information Retrieval, traditional retrieval tasks focus on the similarity between unimodal documents and queries, while image-text retrieval hypothesizes that most texts contain the scene context from images. This separation has ignored that real-world queries may involve text content, image captions, or both. To address this, we introduce Multimodal Retrieval on Representation of ImaGe witH Text (Mr. Right), a novel and comprehensive dataset for multimodal retrieval. We utilize the Wikipedia dataset with rich text-image examples and generate three types of text-based queries with different modality information: text-related, image-related, and mixed. To validate the effectiveness of our dataset, we provide a multimodal training paradigm and evaluate previous text retrieval and image retrieval frameworks. The results show that proposed multimodal retrieval can improve retrieval performance, but creating a well-unified document representation with texts and images is still a challenge. We hope Mr. Right allows us to broaden current retrieval systems better and contributes to accelerating the advancement of multimodal learning in the Information Retrieval.

cs.IR↗