Figure 1: Given challenging in-the-wild videos, a recent state-of-the-art video-pose-estimation approach [30] (top), fails to produce accurate and kinematically plausible 3D body shapes and poses. To address this, we exploit a large-scale motioncapture dataset to train a motion discriminator model in a GAN style. Our VIBE model (bottom) is able to produce realistic and kinematically plausible body meshes outperforming previous work.
In traditional Distributional Semantic Models (DSMs) the multiple senses of a polysemous word are conflated into a single vector space representation. In this work, we propose a DSM that learns multiple distributional representations of a word based on different topics. First, a separate DSM is trained for each topic and then each of the topic-based DSMs is aligned to a common vector space. Our unsupervised mapping approach is motivated by the hypothesis that words preserving their relative distances in different topic semantic sub-spaces constitute robust semantic anchors that define the mappings between them. Aligned cross-topic representations achieve state-of-the-art results for the task of contextual word similarity. Furthermore, evaluation on NLP downstream tasks shows that multiple topic-based embeddings outperform single-prototype models.
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.