Cognitive diagnosis is a fundamental task in intelligent education, aiming to measure students' proficiency on knowledge concepts based on practice data. Traditional methods utilize a broadly-defined latent trait θ to represent knowledge proficiency with some cognitive factors like skill or ability. However, existing methods simplify this to a narrowly-defined latent trait θ, which focuses only on knowledge or treats these cognitive factors as implicit features inferred from data. They fail to explicitly model these cognitive factors, resulting in limited performance and interpretability. To this end, we revisit essence of cognition in Educational Psychology Theory and propose a novel Cognition-aware Cognitive Diagnosis (CCD) model, where we first introduce the Cognition factor as a bridge into the long-standing three-basic-factors (Student, Exercise, Knowledge concept) paradigm. CCD has two main parts: cognition representations and a two-stage diagnostic process. In the first part, we explicitly model cognitive process (CP) dimensions from Bloom's Taxonomy of Educational Objectives, leading to two innovative concepts proposed: the student's Subjective Cognitive Ability (SCA) and the exercise's Objective Cognitive Attribute (OCA), derived by regulating the CP through S-K and E-K interactions, respectively. Then, the SCA and OCA are formed into a new cognition-aware latent trait θ. In the second part, we employ a basic interaction function and a slip and guess influence function, inputting our new θ, a continuous Q-matrix (generated by a siamese PLMs), and other features to obtain the ideal result, followed by feeding it into the slip and guess influence function to obtain the actual result. Extensive experiments on real-world datasets demonstrates the superior effectiveness and good interpretability.

Winograd algorithm can effectively reduce the computational complexity of convolution operation. Effectively using the parallelism of Winograd convolution algorithm can effectively improve the performance of accelerator architectures on FPGA. The stride represents the number of elements that the window slides when filter is scanned on the input feature map. The Winograd algorithm with the stride of 2 implemented in previous studies divided the input feature maps into multiple groups of Winograd algorithms to complete the operations, resulting in additional precomputation and hardware resource overhead. In this paper, we propose a new Winograd convolution algorithm with the stride of 2. This method uses the unified Winograd transformation matrices instead of the grouping method to complete the calculation. Therefore, the method proposed in this paper can realize 2D Winograd convolution and 3D Winograd convolution by nested 1D Winograd convolution, just like the Winograd convolution algorithm with the stride of 1. In this paper, Winograd transformation matrices with kernel size of 3, 5, and 7 are provided. In particular, for convolution with the kernel of 3, this method reduces the addition operations of Winograd algorithm by 30.0%-31.5% and removes unnecessary shift operations completely. In addition, we implement Winograd convolution algorithm with the stride of 2 through template design, and realize pipeline and data reuse. Compared to the state-of-the-art implementation, the proposed method results in a speedup of 1.24 and reduces resource usage.

Benefiting from deep learning with large scale face databases, 2D face recognition has made significant progress in recent years. However, it still highly depends on lighting conditions and human poses, and suffers from face spoofing problem. In contrast, 3D face recognition reveals a new path that can overcome the previous limitations of 2D face recognition. One of the most important problems for 3D face recognition is to construct a suitable database, which can be exploited to train different 3D face recognition algorithms. In this work, we propose a new database, CAS-AIR-3D Face, for low-quality 3D face recognition. It includes 24713 videos from 3093 individuals, which is captured by Intel RealSense SR305. The database contains three modalities: color, depth and near infrared, and is rich in pose, expression, occlusion and distance variations. To the best of our konwledge, CAS-AIR-3D Face is the largest low-quality 3D face database in terms of the number of individuals and the sample variations. Moreover, we preprocess the data via a sophisticated face alignment method, and Point Cloud Spherical Cropping Method (SCM) is leveraged to remove the background noise in the depth images. Finally, an evaluation protocol is designed for fair comparison, and extensive experiments are conducted with different backbone networks to provide different baselines on this database.

Face sketch synthesis has made significant progress with the development of deep neural networks in these years. The delicate depiction of sketch portraits facilitates a wide range of applications like digital entertainment and law enforcement. However, accurate and realistic face sketch generation is still a challenging task due to the illumination variations and complex backgrounds in the real scenes. To tackle these challenges, we propose a novel Semantic-Driven Generative Adversarial Network (SDGAN) which embeds global structure-level style injection and local class-level knowledge re-weighting. Specifically, we conduct facial saliency detection on the input face photos to provide overall facial texture structure, which could be used as a global type of prior information. In addition, we exploit face parsing layouts as the semantic-level spatial prior to enforce globally structural style injection in the generator of SDGAN. Furthermore, to enhance the realistic effect of the details, we propose a novel Adaptive Re-weighting Loss (ARLoss) which dedicates to balance the contributions of different semantic classes. Experimentally, our extensive experiments on CUFS and CUFSF datasets show that our proposed algorithm achieves state-of-the-art performance.

A physical modeling approach is used to investigate playing effects in woodwind instruments. This builds upon prior work concerning both empirical studies of the acoustics of the clarinet and extensive development of computer simulations of musical instrument systems. Specifically, explicit implementations of two performance gestures for the clarinet are given and demonstrated: tonguing and pitch bending. Physical modeling for the clarinet is briefly reviewed. Following this we show how both tonguing and pitch bending map to changes in the clarinet physical model itself and in the control parameter data. To our knowledge, tonguing in particular is one effect that has not been widely discussed in the literature, at least in the exact form we present. Finally, some possible future research directions are indicated.

A physical modeling synthesizer is developed and used to parametrically represent digital audio recordings of clarinet soloists. Empirical data, in the form of acoustic impedance measurements, are incorporated in the model definition. Reed dynamics are also included. Algorithms which calculate control parameters from source recordings are presented and examples of both the impedance measurements and the synthesis output are provided. The synthesis results give further support to the idea that music can, in certain circumstances, be adequately represented by a few low bandwidth control parameters. Additionally, the governing equations of clarinet physical modeling are briefly reviewed.

In this paper we describe an application of spread spectrum techniques in audio data hiding for watermarking and steganography. The method is self-synchronizing, cover-dependent, and operates in the time domain. We use a special class of frequency-hop signal known as a Welch-Costas array. Welch-Costas arrays have the properties of range and Doppler resolution. This allows us to recover embedded data with a matched filter. We also demonstrate a special case of an adaptive method due to Su and Girod (2002).

Data hiding in media, including images, video, and audio, and in data files is currently of great interest both commercially, mainly for the protection of copyrighted digital media, and to the government and law enforcement in the context of information system security and covert communications. We present a technique for inserting and recovering "hidden" data in audio files. The phase of chosen components of the host audio signal is manipulated in a way that may be detected by a receiver with the proper "key". Without the key, the hidden data is undetectable, both aurally and via blind digital signal processing attacks. The method described is both aurally transparent and robust and can be applied to both analog and digital audio signals, the latter including uncompressed as well as compressed audio file formats such as MP3.