Search

We apply computer vision pose estimation techniques developed expressly for the data-scarce infant domain to the study of torticollis, a common condition in infants for which early identification and treatment is critical. Specifically, we use a combination of facial landmark and body joint estimation techniques designed for infants to estimate a range of geometric measures pertaining to face and upper body symmetry, drawn from an array of sources in the physical therapy and ophthalmology research literature in torticollis. We gauge performance with a range of metrics and show that the estimates of most these geometric measures are successful, yielding strong to very strong Spearman's $\rho$ correlation with ground truth values. Furthermore, we show that these estimates, derived from pose estimation neural networks designed for the infant domain, cleanly outperform estimates derived from more widely known networks designed for the adult domain

Research in medical visual question answering (MVQA) can contribute to the development of computeraided diagnosis. MVQA is a task that aims to predict accurate and convincing answers based on given medical images and associated natural language questions. This task requires extracting medical knowledge-rich feature content and making fine-grained understandings of them. Therefore, constructing an effective feature extraction and understanding scheme are keys to modeling. Existing MVQA question extraction schemes mainly focus on word information, ignoring medical information in the text. Meanwhile, some visual and textual feature understanding schemes cannot effectively capture the correlation between regions and keywords for reasonable visual reasoning. In this study, a dual-attention learning network with word and sentence embedding (WSDAN) is proposed. We design a module, transformer with sentence embedding (TSE), to extract a double embedding representation of questions containing keywords and medical information. A dualattention learning (DAL) module consisting of self-attention and guided attention is proposed to model intensive intramodal and intermodal interactions. With multiple DAL modules (DALs), learning visual and textual co-attention can increase the granularity of understanding and improve visual reasoning. Experimental results on the ImageCLEF 2019 VQA-MED (VQA-MED 2019) and VQA-RAD datasets demonstrate that our proposed method outperforms previous state-of-the-art methods. According to the ablation studies and Grad-CAM maps, WSDAN can extract rich textual information and has strong visual reasoning ability.

We lay the groundwork for research in the algorithmic comprehension of infant faces, in anticipation of applications from healthcare to psychology, especially in the early prediction of developmental disorders. Specifically, we introduce the first-ever dataset of infant faces annotated with facial landmark coordinates and pose attributes, demonstrate the inadequacies of existing facial landmark estimation algorithms in the infant domain, and train new state-of-the-art models that significantly improve upon those algorithms using domain adaptation techniques. We touch on the closely related task of facial detection for infants, and also on a challenging case study of infrared baby monitor images gathered by our lab as part of in-field research into the aforementioned developmental issues.

Non-nutritive sucking (NNS) is defined as the sucking action that occurs when a finger, pacifier, or other object is placed in the baby's mouth, but there is no nutrient delivered. In addition to providing a sense of safety, NNS even can be regarded as an indicator of infant's central nervous system development. The rich data, such as sucking frequency, the number of cycles, and their amplitude during baby's non-nutritive sucking is important clue for judging the brain development of infants or preterm infants. Nowadays most researchers are collecting NNS data by using some contact devices such as pressure transducers. However, such invasive contact will have a direct impact on the baby's natural sucking behavior, resulting in significant distortion in the collected data. Therefore, we propose a novel contact-less NNS data acquisition and quantification scheme, which leverages the facial landmarks tracking technology to extract the movement signals of baby's jaw from recorded baby's sucking video. Since completion of the sucking action requires a large amount of synchronous coordination and neural integration of the facial muscles and the cranial nerves, the facial muscle movement signals accompanying baby's sucking pacifier can indirectly replace the NNS signal. We have evaluated our method on videos collected from several infants during their NNS behaviors and we have achieved the quantified NNS patterns closely comparable to results from visual inspection as well as contact-based sensor readings.

Most of atoms and molecule found in nature are capable of evolving towards and staying at their ground states, the lowest energy states. This paper offers a global optimization approach to understand the ground state as the equilibrium point of an $n$-player game under cooperation. With the same approach, Nash equilibrium can be viewed as the equilibrium point under competition. The former can offer higher payoffs and stability of game playing than the later. It is truly an inspiration from nature for us to build societies for quality and stability under cooperation rather than competition.

In a society of completely selfish individuals where everybody is only interested in maximizing his own payoff, does any equilibrium exist for the society? John Nash proved more than 50 years ago that an equilibrium always exists such that nobody would benefit from unilaterally changing his strategy. Nash Equilibrium is a central concept in game theory, which offers a mathematical foundation for social science and economy. However, it is important from both a theoretical and a practical point of view to understand game playing where individuals are less selfish. This paper offers a constructive generalization of Nash equilibrium to study n-person games where the selfishness of individuals can be defined at any level, including the extreme of complete selfishness. The generalization is constructive since it offers a protocol for individuals in a society to reach an equilibrium. Most importantly, this paper presents experimental results and theoretical investigation to show that the individuals in a society can reduce their selfishness level together to reach a new equilibrium where they can have better payoffs and the society is more stable at the same time. This study suggests that, for the benefit of everyone in a society (including the financial market), the pursuit of maximal payoff by each individual should be controlled at some level either by voluntary good citizenship or by imposed regulations.

In a society of multiple individuals, if everybody is only interested in maximizing his own payoff, will there exist any equilibrium for the society? John Nash proved more than 50 years ago that an equilibrium always exists such that nobody would benefit from unilaterally changing his strategy. Nash Equilibrium is a central concept in game theory, which offers the mathematical foundation for social science and economy. However, the original definition is declarative without including a solution to find them. It has been found later that it is computationally difficult to find a Nash equilibrium. Furthermore, a Nash equilibrium may be unstable, sensitive to the smallest variation of payoff functions. Making the situation worse, a society with selfish individuals can have an enormous number of equilibria, making it extremely hard to find out the global optimal one. This paper offers a constructive generalization of Nash equilibrium to cover the case when the selfishness of individuals are reduced to lower levels in a controllable way. It shows that the society has one and only one equilibrium when the selfishness is reduced to a certain level. When every individual follows the iterative, soft-decision optimization process presented in this paper, the society converges to the unique equilibrium with an exponential rate under any initial conditions. When it is a consensus equilibrium at the same time, it must be the global optimum. The study of this paper suggests that, to build a good, stable society (including the financial market) for the benefit everyone in it, the pursuing of maximal payoff by each individual should be controlled at some level either by voluntary good citizenship or some proper regulations.

The fundamental laws of quantum world upsets the logical foundation of classic physics. They are completely counter-intuitive with many bizarre behaviors. However, this paper shows that they may make sense from the perspective of a general decision-optimization principle for cooperation. This principle also offers a generalization of Nash equilibrium, a key concept in game theory, for better payoffs and stability of game playing.

The belief propagation algorithm has been recognized in the information theory community as a soft-decision iterative decoding algorithm. It is the most powerful algorithm found so far for attacking hard optimization problems in channel decoding. Quantum mechanics is the foundation of modern physics with the time-independent Schrodinger equation being one of the most important equations. This paper shows that the equation can be derived from a generalized belief propagation algorithm. Such a connection on a mathematical basis might shed new insights into the foundations of quantum mechanics and quantum computing., An extended abstract version of this paper has been presented at International Conference on Quantum Foundation and Technology, August, 2006, HangZhou, China (ICQFT'06)