Search

Learning-based underwater image enhancement (UIE) methods have made great progress. However, the lack of large-scale and high-quality paired training samples has become the main bottleneck hindering the development of UIE. The inter-frame information in underwater videos can accelerate or optimize the UIE process. Thus, we constructed the first large-scale high-resolution underwater video enhancement benchmark (UVEB) to promote the development of underwater vision.It contains 1,308 pairs of video sequences and more than 453,000 high-resolution with 38\% Ultra-High-Definition (UHD) 4K frame pairs. UVEB comes from multiple countries, containing various scenes and video degradation types to adapt to diverse and complex underwater environments. We also propose the first supervised underwater video enhancement method, UVE-Net. UVE-Net converts the current frame information into convolutional kernels and passes them to adjacent frames for efficient inter-frame information exchange. By fully utilizing the redundant degraded information of underwater videos, UVE-Net completes video enhancement better. Experiments show the effective network design and good performance of UVE-Net., Comment: 10 pages,CVPR2024 accept

The Hansen-Jagannathan (HJ) distance statistic is one of the most dominant measures of model misspecification. However, the conventional HJ specification test procedure has poor finite sample performance, and we show that it can be size distorted even in large samples when (proxy) factors exhibit small correlations with asset returns. In other words, applied researchers are likely to falsely reject a model even when it is correctly specified. We provide two alternatives for the HJ statistic and two corresponding novel procedures for model specification tests, which are robust against the presence of weak (proxy) factors, and we also offer a novel robust risk premia estimator. Simulation exercises support our theory. Our empirical application documents the non-reliability of the traditional HJ test since it may produce counter-intuitive results when comparing nested models by rejecting a four-factor model but not the reduced three-factor model. At the same time, our proposed methods are practically more appealing and show support for a four-factor model for Fama French portfolios.

We propose identification robust statistics for testing hypotheses on the risk premia in dynamic affine term structure models. We do so using the moment equation specification proposed for these models in Adrian et al. (2013). We extend the subset (factor) Anderson-Rubin test from Guggenberger et al. (2012) to models with multiple dynamic factors and time-varying risk prices. Unlike projection-based tests, it provides a computationally tractable manner to conduct identification robust tests on a larger number of parameters. We analyze the potential identification issues arising in empirical studies. Statistical inference based on the three-stage estimator from Adrian et al. (2013) requires knowledge of the factors' quality and is misleading without full-rank beta's or with sampling errors of comparable size as the loadings. Empirical applications show that some factors, though potentially weak, may drive the time variation of risk prices, and weak identification issues are more prominent in multi-factor models.

Text summarization is essential for information aggregation and demands large amounts of training data. However, concerns about data privacy and security limit data collection and model training. To eliminate this concern, we propose a federated learning text summarization scheme, which allows users to share the global model in a cooperative learning manner without sharing raw data. Personalized federated learning (PFL) balances personalization and generalization in the process of optimizing the global model, to guide the training of local models. However, multiple local data have different distributions of semantics and context, which may cause the local model to learn deviated semantic and context information. In this paper, we propose FedSUMM, a dynamic gradient adapter to provide more appropriate local parameters for local model. Simultaneously, FedSUMM uses differential privacy to prevent parameter leakage during distributed training. Experimental evidence verifies FedSUMM can achieve faster model convergence on PFL algorithm for task-specific text summarization, and the method achieves superior performance for different optimization metrics for text summarization., Comment: Accepted by IJCNN2023. 2023 IEEE International Joint Conference on Neural Network (IJCNN2023)

Buddhism is an influential religion with a long-standing history and profound philosophy. Nowadays, more and more people worldwide aspire to learn the essence of Buddhism, attaching importance to Buddhism dissemination. However, Buddhist scriptures written in classical Chinese are obscure to most people and machine translation applications. For instance, general Chinese-English neural machine translation (NMT) fails in this domain. In this paper, we proposed a novel approach to building a practical NMT model for Buddhist scriptures. The performance of our translation pipeline acquired highly promising results in ablation experiments under three criteria., Comment: This paper is accepted by ICTAI 2022. The 34th IEEE International Conference on Tools with Artificial Intelligence (ICTAI)

This paper introduces a graphical representation approach of prosody boundary (GraphPB) in the task of Chinese speech synthesis, intending to parse the semantic and syntactic relationship of input sequences in a graphical domain for improving the prosody performance. The nodes of the graph embedding are formed by prosodic words, and the edges are formed by the other prosodic boundaries, namely prosodic phrase boundary (PPH) and intonation phrase boundary (IPH). Different Graph Neural Networks (GNN) like Gated Graph Neural Network (GGNN) and Graph Long Short-term Memory (G-LSTM) are utilised as graph encoders to exploit the graphical prosody boundary information. Graph-to-sequence model is proposed and formed by a graph encoder and an attentional decoder. Two techniques are proposed to embed sequential information into the graph-to-sequence text-to-speech model. The experimental results show that this proposed approach can encode the phonetic and prosody rhythm of an utterance. The mean opinion score (MOS) of these GNN models shows comparative results with the state-of-the-art sequence-to-sequence models with better performance in the aspect of prosody. This provides an alternative approach for prosody modelling in end-to-end speech synthesis., Comment: Accepted to SLT 2021