SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation [PDF]
Computer Vision and Pattern Recognition, 2023 Open-vocabulary semantic segmentation strives to distinguish pixels into different semantic groups from an open set of categories. Most existing methods explore utilizing pre-trained vision-language models, in which the key is to adapt the image-level ...
Bin Xie +4 more
semanticscholar +1 more source
AST-SED: An Effective Sound Event Detection Method Based on Audio Spectrogram Transformer [PDF]
IEEE International Conference on Acoustics, Speech, and Signal Processing, 2023 In this paper, we propose an effective sound event detection (SED) method based on the audio spectrogram transformer (AST) model, pretrained on the large-scale AudioSet for audio tagging (AT) task, termed AST-SED.
Kang Li +5 more
semanticscholar +1 more source
Accelerated Bayesian SED Modeling Using Amortized Neural Posterior Estimation [PDF]
Astrophysical Journal, 2022 State-of-the-art spectral energy distribution (SED) analyses use a Bayesian framework to infer the physical properties of galaxies from observed photometry or spectra.
C. Hahn, Peter Melchior
semanticscholar +1 more source
mirkwood: Fast and Accurate SED Modeling Using Machine Learning [PDF]
Astrophysical Journal, 2021 Traditional spectral energy distribution (SED) fitting codes used to derive galaxy physical properties are often uncertain at the factor of a few level owing to uncertainties in galaxy star formation histories and dust attenuation curves.
Sankalp Gilda, S. Lower, D. Narayanan
semanticscholar +1 more source
How Well Can We Measure the Stellar Mass of a Galaxy: The Impact of the Assumed Star Formation History Model in SED Fitting [PDF]
Astrophysical Journal, 2020 The primary method for inferring the stellar mass (M *) of a galaxy is through spectral energy distribution (SED) modeling. However, the technique rests on assumptions such as the galaxy star formation history (SFH) and dust attenuation law that can ...
S. Lower +5 more
semanticscholar +1 more source
Galaxy And Mass Assembly (GAMA): a forensic SED reconstruction of the cosmic star formation history and metallicity evolution by galaxy type [PDF]
Monthly notices of the Royal Astronomical Society, 2020 We apply the spectral energy distribution (SED) fitting code ProSpect to multiwavelength imaging for ∼7000 galaxies from the GAMA survey at z < 0.06, in order to extract their star formation histories.
S. Bellstedt +11 more
semanticscholar +1 more source
Metaverse, SED Model, and New Theory of Value
Complex, 2022 The metaverse concept constructs a virtual world parallel to the real world. The social economic dynamics (SED) model establishes a systematic model for social economic dynamics simulation that integrates macroeconomy and microeconomy based on modeling ...
Jian-gang Wang +5 more
semanticscholar +1 more source
A Hierarchical Bayesian SED Model for Type Ia Supernovae in the Optical to Near-Infrared [PDF]
, 2020 While conventional Type Ia supernova (SN Ia) cosmology analyses rely primarily on rest-frame optical light curves to determine distances, SNe Ia are excellent standard candles in near-infrared (NIR) light, which is significantly less sensitive to dust ...
K. Mandel +4 more
semanticscholar +1 more source
Journal of Integrative Bioinformatics, 2021 Computational simulation experiments increasingly inform modern biological research, and bring with them the need to provide ways to annotate, archive, share and reproduce the experiments performed.
Lucian P. Smith +8 more
semanticscholar +1 more source
SeD: Semantic-Aware Discriminator for Image Super-Resolution [PDF]
Computer Vision and Pattern RecognitionGenerative Adversarial Networks (GANs) have been widely used to recover vivid textures in image super-resolution (SR) tasks. In particular, one discriminator is utilized to enable the SR network to learn the distribution of real-world high-quality images
Bingchen Li +6 more
semanticscholar +1 more source