This paper targets the task of language-based video moment localization. The language-based setting of this task allows for an open set of target activities, resulting in a large variation of the temporal lengths of video moments. Most existing methods prefer to first sample sufficient candidate moments with various temporal lengths, and then match them with the given query to determine the target moment. However, candidate moments generated with a fixed temporal granularity may be suboptimal to handle the large variation in moment lengths. To this end, we propose a novel multi-stage Progressive Localization Network (PLN) which progressively localizes the target moment in a coarse-to-fine manner. Specifically, each stage of PLN has a localization branch, and focuses on candidate moments that are generated with a specific temporal granularity. The temporal granularities of candidate moments are different across the stages. Moreover, we devise a conditional feature manipulation module and an upsampling connection to bridge the multiple localization branches. In this fashion, the later stages are able to absorb the previously learned information, thus facilitating the more fine-grained localization. Extensive experiments on three public datasets demonstrate the effectiveness of our proposed PLN for language-based moment localization, especially for localizing short moments in long videos.
The Large-scale uneven ground is mostly unsmooth and in the irregular state in which the irregularity is usually unknown (such as footway, carriageway, unexplored desert, mountainous area, surface of the Mars). In order to walk steadily and rapidly on such ground, a chief problem to overcome is that the humanoid robot's foot is not matching with the unknown model of the ground. Therefore, the humanoid robot's foot should have the flexibility mimic the human's foot, and can adapt to and steadily interacted with any unsmooth ground. Also interferences and disjoints between soles and irregular unsmooth ground should be avoided. Aiming at solving the key problem for humanoid robot to steadily and rapidly walk on the large-scale and three-dimension uneven ground, we've set up a new multidegree-of-freedom flexible foot mechanism which can make the humanoid robot's walking gesture and gait automatically adapt to the terrain, and then carry out the research of the globally stable control of the gait. The flexibility can obviously improve the humanoid robot's walking stability and speediness on the large-scale uneven ground.
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.