Accurate prediction of future human positions is an essential task for modern video-surveillance systems. Current state-of-the-art models usually rely on a "history" of past tracked locations (e.g., 3 to 5 seconds) to predict a plausible sequence of future locations (e.g., up to the next 5 seconds). We feel that this common schema neglects critical traits of realistic applications: as the collection of input trajectories involves machine perception (i.e., detection and tracking), incorrect detection and fragmentation errors may accumulate in crowded scenes, leading to tracking drifts. On this account, the model would be fed with corrupted and noisy input data, thus fatally affecting its prediction performance.In this regard, we focus on delivering accurate predictions when only few input observations are used, thus potentially lowering the risks associated with automatic perception. To this end, we conceive a novel distillation strategy that allows a knowledge transfer from a teacher network to a student one, the latter fed with fewer observations (just two ones). We show that a properly defined teacher supervision allows a student network to perform comparably to state-of-the-art approaches that demand more observations. Besides, extensive experiments on common trajectory forecasting datasets highlight that our student network better generalizes to unseen scenarios.
Understanding human motion behaviour is a critical task for several possible applications like self-driving cars or social robots, and in general for all those settings where an autonomous agent has to navigate inside a human-centric environment. This is non-trivial because human motion is inherently multi-modal: given a history of human motion paths, there are many plausible ways by which people could move in the future. Additionally, people activities are often driven by goals, e.g. reaching particular locations or interacting with the environment. We address both the aforementioned aspects by proposing a new recurrent generative model that considers both single agents' future goals and interactions between different agents. The model exploits a double attention-based graph neural network to collect information about the mutual influences among different agents and integrates it with data about agents' possible future objectives. Our proposal is general enough to be applied in different scenarios: the model achieves state-of-the-art results in both urban environments and also in sports applications.
Since behavioural symptoms (tremor, irritability, pilo-erection and shaking) induced by imidazole (IMID) in rats suggested an underlying modification of arousal and/or emotionality, further studies were performed in order to extend the range of behavioural influences of IMID. In the open-field test, IMID (37.5-300 mg/kg IP) inhibited crossing and rearing in a dose-dependent fashion, this effect being long lasting (about 3 h at 75 mg/kg). Yohimbine (YOH) (1, 5 and 10 mg/kg IP), described as anxiogenic and fear-inducing in animals and in man, when investigated in this same test, inhibited the activity of rats similarly to IMID. Since diazepam (0.5 and 1 mg/kg) but not clonidine (0.075 and 0.150 mg/kg IP) pretreatment reversed IMID- and YOH-induced hypomotility, the hypothesis that IMID effects in the open field might reflect an anxiety-like state was investigated by means of social interaction and x-maze, two tests considered highly specific for anxiety studies. The data obtained show that IMID depresses social interactions only at doses inhibiting motor activity; YOH, in our experimental conditions, produced a similar effect. In an elevated x-maze, with alternate open and closed arms, IMID (37.5 and 75 mg/kg) decreased the proportion of open-arm entries and the time spent in them, an effect prevented by diazepam pretreatment (1 mg/kg IP). Finally, mean arterial pressure (MAP) was assessed in anesthetized rats treated with IMID and YOH at doses equivalent as regards behavioural effects. MAP was increased by IMID whether IP or IV and decreased by YOH; moreover, YOH, as expected, antagonized clonidine-induced hypotension, while IMID was ineffective.(ABSTRACT TRUNCATED AT 250 WORDS)
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.