Video Question Answering is a challenging problem in visual information retrieval, which provides the answer to the referenced video content according to the question. However, the existing visual question answering approaches mainly tackle the problem of static image question, which may be ineffectively for video question answering due to the insufficiency of modeling the temporal dynamics of video contents. In this paper, we study the problem of video question answering by modeling its temporal dynamics with frame-level attention mechanism. We propose the attributeaugmented attention network learning framework that enables the joint frame-level attribute detection and unified video representation learning for video question answering. We then incorporate the multi-step reasoning process for our proposed attention network to further improve the performance. We construct a largescale video question answering dataset. We conduct the experiments on both multiple-choice and open-ended video question answering tasks to show the effectiveness of the proposed method.
Portfolio management (PM) is a fundamental financial planning task that aims to achieve investment goals such as maximal profits or minimal risks. Its decision process involves continuous derivation of valuable information from various data sources and sequential decision optimization, which is a prospective research direction for reinforcement learning (RL). In this paper, we propose SARL, a novel State-Augmented RL framework for PM. Our framework aims to address two unique challenges in financial PM: (1) data heterogeneity – the collected information for each asset is usually diverse, noisy and imbalanced (e.g., news articles); and (2) environment uncertainty – the financial market is versatile and non-stationary. To incorporate heterogeneous data and enhance robustness against environment uncertainty, our SARL augments the asset information with their price movement prediction as additional states, where the prediction can be solely based on financial data (e.g., asset prices) or derived from alternative sources such as news. Experiments on two real-world datasets, (i) Bitcoin market and (ii) HighTech stock market with 7-year Reuters news articles, validate the effectiveness of SARL over existing PM approaches, both in terms of accumulated profits and risk-adjusted profits. Moreover, extensive simulations are conducted to demonstrate the importance of our proposed state augmentation, providing new insights and boosting performance significantly over standard RL-based PM method and other baselines.
Background: Nuclear factor I family members nuclear factor I A and nuclear factor I B play important roles during cerebral cortical development. Nuclear factor I A and nuclear factor I B regulate similar biological processes, as their expression patterns, regulation of target genes and individual knockout phenotypes overlap. We hypothesised that the combined allelic loss of Nfia and Nfib would culminate in more severe defects in the cerebral cortex than loss of a single member. Methods: We combined immunofluorescence, co-immunoprecipitation, gene expression analysis and immunohistochemistry on knockout mouse models to investigate whether nuclear factor I A and nuclear factor I B function similarly and whether increasing allelic loss of Nfia and Nfib caused a more severe phenotype. Results: We determined that the biological functions of nuclear factor I A and nuclear factor I B overlap during early cortical development. These proteins are co-expressed and can form heterodimers in vivo. Differentially regulated genes that are shared between Nfia and Nfib knockout mice are highly enriched for nuclear factor I binding sites in their promoters and are associated with neurodevelopment. We found that compound heterozygous deletion of both genes resulted in a cortical phenotype similar to that of single homozygous Nfia or Nfib knockout embryos. This was characterised by retention of the interhemispheric fissure, dysgenesis of the corpus callosum and a malformed dentate gyrus. Double homozygous knockout of Nfia and Nfib resulted in a more severe phenotype, with increased ventricular enlargement and decreased numbers of differentiated glia and neurons. Conclusion: In the developing cerebral cortex, nuclear factor I A and nuclear factor I B share similar biological functions and function additively, as the combined allelic loss of these genes directly correlates with the severity of the developmental brain phenotype.
Corpus callosum dysgenesis (CCD) is a congenital disorder that incorporates either partial or complete absence of the largest cerebral commissure. Remodelling of the interhemispheric fissure (IHF) provides a substrate for callosal axons to cross between hemispheres, and its failure is the main cause of complete CCD. However, it is unclear whether defects in this process could give rise to the heterogeneity of expressivity and phenotypes seen in human cases of CCD. We identify incomplete IHF remodelling as the key structural correlate for the range of callosal abnormalities in inbred and outcrossed BTBR mouse strains, as well as in humans with partial CCD. We identify an eight base-pair deletion in Draxin and misregulated astroglial and leptomeningeal proliferation as genetic and cellular factors for variable IHF remodelling and CCD in BTBR strains. These findings support a model where genetic events determine corpus callosum structure by influencing leptomeningeal-astroglial interactions at the IHF.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.