People live in a 3D world. However, existing works on person re-identification (re-id) mostly consider the semantic representation learning in a 2D space, intrinsically limiting the understanding of people. In this work, we address this limitation by exploring the prior knowledge of the 3D body structure. Specifically, we project 2D images to a 3D space and introduce a novel parameter-efficient omni-scale graph network (OG-Net) to learn the pedestrian representation directly from 3D point clouds. OG-Net effectively exploits the local information provided by sparse 3D points and takes advantage of the structure and appearance information in a coherent manner. With the help of 3D geometry information, we can learn a new type of deep re-id feature free from noisy variants, such as scale and viewpoint. To our knowledge, we are among the first attempts to conduct person re-id in the 3D space. We demonstrate through extensive experiments that the proposed method: (1) eases the matching difficulty in the traditional 2D space; 2) exploits the complementary information of 2D appearance and 3D structure; 3) achieves competitive results with limited parameters on four large-scale person re-id datasets; and 4) has good scalability to unseen datasets. Our code, models, and generated 3D human data are publicly available at https://github.com/layumi/person-reid-3d.

High-dimensional and incomplete (HDI) data commonly arise in various Big Data-related applications, e.g., recommender systems and bioinformatics. Representation is a learning paradigm to map HDI data into low-dimensional latent space for attracting valuable knowledge and patterns. Currently, deep neural network (DNN) is one of the most popular and successful approaches to represent HDI data due to its powerful nonlinear learning ability. However, previous DNNs-based approaches primarily focused on advancing the sophisticated model structure, neglecting the potential adverse effects of outliers. Unfortunately, outliers usually exist in the collected HDI data. For example, HDI data collected from recommender systems inevitably contain many outlier ratings due to some malicious users. To address this issue, this paper proposes a novel outlier-resilient autoencoder (termed ORA). Its core idea is to design an adaptive Cauchy loss strategy to measure the difference between the observed and predicted data for an autoencoder in representing the HDI data. This strategy leverages a more aggressive Cauchy loss to impose a higher penalty on outlier data with large deviation, while utilizing a smoother Cauchy loss to capture the nuanced, deeper features of HDI data. As such, ORA can dynamically adjust the smoothness of the Cauchy loss during training to handle different levels of data deviation. To evaluate the proposed ORA, extensive experiments are conducted on five benchmark HDI datasets. The results validate that: (1) ORA achieves significantly better representation accuracy than State-of-the-Art DNN- and non-DNN-based models, and (2) ORA possesses higher robustness to outlier data than its peers.

To explore the exciting new domain of brain informatics, we invited several well-known experts to discuss the state of the art, the challenges, the opportunities, and the trends. In "Creating Human-Level AI by Educating a Child Machine," Raj Reddy proposes an architecture for a "child machine" that can learn and is teachable. In "Cyborg Intelligence," Zhaohui Wu, Gang Pan, and Nenggan Zheng describe a biological-machine system consisting of both an organic and a computing part. In "Formal Minds and Biological Brains II: From the Mirage of Intelligence to a Science and Engineering of Consciousness," Paul F.M.J. Verschure discusses human-like cognitive architectures and describes the Distributed Adaptive Control (DAC) architecture for perception, cognition, and action. In "The Challenges of Closed-Loop Invasive Brain-Machine Interfaces," Qiaosheng Zhang and Xiaoxiang Zheng discuss the challenges and trends in closed-loop brain-machine interfaces. In "Neural Signal Processing in Brain-Machine Interfaces," Jose C. Principe takes a critical look at the challenges and opportunities of performing computation with pulses, as neurons do. In "Neuroprosthesis Control via a Noninvasive Hybrid Brain-Computer Interface," Alex Kreilinger, Martin Rohm, Vera Kaiser, Robert Leeb, Rüdiger Rupp, and Gernot R. Müller-Putz describe an example of the convergence of biological intelligence and machine intelligence in a hand-elbow neuroprosthesis control unit.

Innate preference toward environmental conditions is crucial for animal survival. Although much is known about the neural processing of sensory information, how the aversive or attractive sensory stimulus is transformed through central brain neurons into avoidance or approaching behavior is largely unclear. Here we show that Drosophila larval light preference behavior is regulated by a disinhibitory mechanism. In the disinhibitory circuit, a pair of GABAergic neurons exerts tonic inhibition on one pair of contralateral projecting neurons that control larval reorientation behavior. When a larva enters the light area, the reorientation-controlling neurons are disinhibited to allow reorientation to occur as the upstream inhibitory neurons are repressed by light. When the larva exits the light area, the inhibition on the downstream neurons is restored to repress further reorientation and thus prevents the larva from re-entering the light area. We suggest that disinhibition may serve as a common neural mechanism for animal innate preference behavior.