arXiv subjects

Yan Shu

Publications and source records attributed to Yan Shu.

47 records · Page 3Linked to original sources

arXiv2023

CLiF-VQA: Enhancing Video Quality Assessment by Incorporating High-Level Semantic Information related to Human Feelings

Video Quality Assessment (VQA) aims to simulate the process of perceiving video quality by the human visual system (HVS). The judgments made by HVS are always influenced by human subjective feelings. However, most of the current VQA research focuses on capturing various distortions in the spatial and temporal domains of videos, while ignoring the impact of human feelings. In this paper, we propose CLiF-VQA, which considers both features related to human feelings and spatial features of videos. In order to effectively extract features related to human feelings from videos, we explore the consistency between CLIP and human feelings in video perception for the first time. Specifically, we design multiple objective and subjective descriptions closely related to human feelings as prompts. Further we propose a novel CLIP-based semantic feature extractor (SFE) which extracts features related to human feelings by sliding over multiple regions of the video frame. In addition, we further capture the low-level-aware features of the video through a spatial feature extraction module. The two different features are then aggregated thereby obtaining the quality score of the video. Extensive experiments show that the proposed CLiF-VQA exhibits excellent performance on several VQA datasets.

cs.CV↗

arXiv2023

Read Pointer Meters in complex environments based on a Human-like Alignment and Recognition Algorithm

Recently, developing an automatic reading system for analog measuring instruments has gained increased attention, as it enables the collection of numerous state of equipment. Nonetheless, two major obstacles still obstruct its deployment to real-world applications. The first issue is that they rarely take the entire pipeline's speed into account. The second is that they are incapable of dealing with some low-quality images (i.e., meter breakage, blur, and uneven scale). In this paper, we propose a human-like alignment and recognition algorithm to overcome these problems. More specifically, a Spatial Transformed Module(STM) is proposed to obtain the front view of images in a self-autonomous way based on an improved Spatial Transformer Networks(STN). Meanwhile, a Value Acquisition Module(VAM) is proposed to infer accurate meter values by an end-to-end trained framework. In contrast to previous research, our model aligns and recognizes meters totally implemented by learnable processing, which mimics human's behaviours and thus achieves higher performances. Extensive results verify the good robustness of the proposed model in terms of the accuracy and efficiency.

cs.CV↗

arXiv2022

Condensing a Sequence to One Informative Frame for Video Recognition

Video is complex due to large variations in motion and rich content in fine-grained visual details. Abstracting useful information from such information-intensive media requires exhaustive computing resources. This paper studies a two-step alternative that first condenses the video sequence to an informative "frame" and then exploits off-the-shelf image recognition system on the synthetic frame. A valid question is how to define "useful information" and then distill it from a video sequence down to one synthetic frame. This paper presents a novel Informative Frame Synthesis (IFS) architecture that incorporates three objective tasks, i.e., appearance reconstruction, video categorization, motion estimation, and two regularizers, i.e., adversarial learning, color consistency. Each task equips the synthetic frame with one ability, while each regularizer enhances its visual quality. With these, by jointly learning the frame synthesis in an end-to-end manner, the generated frame is expected to encapsulate the required spatio-temporal information useful for video analysis. Extensive experiments are conducted on the large-scale Kinetics dataset. When comparing to baseline methods that map video sequence to a single image, IFS shows superior performance. More remarkably, IFS consistently demonstrates evident improvements on image-based 2D networks and clip-based 3D networks, and achieves comparable performance with the state-of-the-art methods with less computational cost.

cs.CV↗

arXiv2020

Analytical solution of $k$th price auction

We provide an exact analytical solution of the Nash equilibrium for the $k$th price auction by using inverse of distribution functions. As applications, we identify the unique symmetric equilibrium where the valuations have polynomial distribution, fat tail distribution and exponential distributions.

econ.TH↗

arXiv2019

A Characterization of Mean Squared Error for Estimator with Bagging

Bagging can significantly improve the generalization performance of unstable machine learning algorithms such as trees or neural networks. Though bagging is now widely used in practice and many empirical studies have explored its behavior, we still know little about the theoretical properties of bagged predictions. In this paper, we theoretically investigate how the bagging method can reduce the Mean Squared Error (MSE) when applied on a statistical estimator. First, we prove that for any estimator, increasing the number of bagged estimators $N$ in the average can only reduce the MSE. This intuitive result, observed empirically and discussed in the literature, has not yet been rigorously proved. Second, we focus on the standard estimator of variance called unbiased sample variance and we develop an exact analytical expression of the MSE for this estimator with bagging. This allows us to rigorously discuss the number of iterations $N$ and the batch size $m$ of the bagging method. From this expression, we state that only if the kurtosis of the distribution is greater than $\frac{3}{2}$, the MSE of the variance estimator can be reduced with bagging. This result is important because it demonstrates that for distribution with low kurtosis, bagging can only deteriorate the performance of a statistical prediction. Finally, we propose a novel general-purpose algorithm to estimate with high precision the variance of a sample.

cs.LG↗

arXiv2019

k-price auctions and Combination auctions

We provide an exact analytical solution of the Nash equilibrium for $k$- price auctions. We also introduce a new type of auction and demonstrate that it has fair solutions other than the second price auctions, therefore paving the way for replacing second price auctions.

q-fin.MF↗

arXiv2017

Deep Automated Multi-task Learning

Multi-task learning (MTL) has recently contributed to learning better representations in service of various NLP tasks. MTL aims at improving the performance of a primary task, by jointly training on a secondary task. This paper introduces automated tasks, which exploit the sequential nature of the input data, as secondary tasks in an MTL model. We explore next word prediction, next character prediction, and missing word completion as potential automated tasks. Our results show that training on a primary task in parallel with a secondary automated task improves both the convergence speed and accuracy for the primary task. We suggest two methods for augmenting an existing network with automated tasks and establish better performance in topic prediction, sentiment analysis, and hashtag recommendation. Finally, we show that the MTL models can perform well on datasets that are small and colloquial by nature.

cs.LG↗

arXiv2017

A characterization of a class of convex log-Sobolev inequalities on the real line

We give a sufficient and necessary condition for a probability measure $μ$ on the real line to satisfy the logarithmic Sobolev inequality for convex functions. The condition is expressed in terms of the unique left-continuous and non-decreasing map transporting the symmetric exponential measure onto $μ$. The main tool in the proof is the theory of weak transport costs. As a consequence, we obtain dimension-free concentration bounds for the lower and upper tails of convex functions of independent random variables which satisfy the convex log-Sobolev inequality.

math.PR↗

arXiv2015

Characterization of a class of weak transport-entropy inequalities on the line

We study an optimal weak transport cost related to the notion of convex order between probability measures. On the real line, we show that this weak transport cost is reached for a coupling that does not depend on the underlying cost function. As an application, we give a necessary and sufficient condition for weak transport-entropy inequalities in dimension one. In particular, we obtain a weak transport-entropy form of the convex Poincar{é} inequality in dimension one.

math.PR↗

arXiv2015

Hamilton-Jacobi equations on graph and applications

This paper introduces a notion of gradient and an infimal-convolution operator that extend properties of solutions of Hamilton Jacobi equations to more general spaces, in particular to graphs. As a main application, the hypercontractivity of this class of infimal-convolution operators is connected to some discrete version of the log-Sobolev inequality and to a discrete version of Talagrand's transport inequality.

math.FA↗

arXiv2015

Curvature and transport inequalities for Markov chains in discrete spaces

We study various transport-information inequalities under three different notions of Ricci curvature in the discrete setting: the curvature-dimension condition of Bakry and Émery, the exponential curvature-dimension condition of Bauer \textit{et al.} and the coarse Ricci curvature of Ollivier. We prove that under a curvature-dimension condition or coarse Ricci curvature condition, an $L_1$ transport-information inequality holds; while under an exponential curvature-dimension condition, some weak-transport information inequalities hold. As an application, we establish a Bonnet-Meyer's theorem under the curvature-dimension condition CD$(κ,\infty)$ of Bakry and Émery.

math.PR↗