Li Fei-Fei

TL;DR: This work proposes an effective probabilistic formulation that allows us to generate, evaluate and optimize layout hypotheses by integrating new image evidence as the observer moves, and demonstrates that this formulation reaches near-real-time computation time and outperforms state-of-the-art methods while operating in significantly less constrained conditions.

TL;DR: In this paper, the authors discuss the ethical challenges of collecting large amounts of sensor data in health care settings, particularly in terms of privacy, data management, bias and fairness, and informed consent.

TL;DR: It is found that, contrary to these claims, workers are extremely stable in their quality over the entire period, and it is demonstrated that it is possible to predict workers' long-term quality using just a glimpse of their quality on the first five tasks.

TL;DR: A data collection system tailored to 6-DoF manipulation settings, that enables remote human operators to monitor and intervene on trained policies and outperforms multiple state-of-the-art baselines for learning from the human interventions on a challenging robot threading task and a coffee making task.

TL;DR: It is shown that in the presence of competing objects, performance in the near absence of attention depends on the relative distance between stimuli: discrimination is good for stimuli far enough apart, and poor for close enough stimuli.