J
Juan Carlos Niebles
Researcher at Stanford University
Publications - 59
Citations - 2369
Juan Carlos Niebles is an academic researcher from Stanford University. The author has contributed to research in topics: Action (philosophy) & Computer science. The author has an hindex of 17, co-authored 59 publications receiving 1143 citations. Previous affiliations of Juan Carlos Niebles include Salesforce.com & Google.
Papers
More filters
Proceedings ArticleDOI
Action Genome: Actions As Compositions of Spatio-Temporal Scene Graphs
TL;DR: This work introduces Action Genome, a representation that decomposes actions into spatio-temporal scene graphs and demonstrates the utility of a hierarchical event decomposition by enabling few-shot action recognition, achieving 42.7% mAP using as few as 10 examples.
Posted Content
Peeking into the Future: Predicting Future Person Activities and Locations in Videos
TL;DR: An end-to-end, multi-task learning system utilizing rich visual features about human behavioral information and interaction with their surroundings is proposed, providing the first empirical evidence that joint modeling of paths and activities benefits future path prediction.
Proceedings ArticleDOI
Spatio-Temporal Graph for Video Captioning With Knowledge Distillation
TL;DR: This paper proposed a spatio-temporal graph model for video captioning that exploits object interactions in space and time to build interpretable links and is able to provide explicit visual grounding, and further proposed an object-aware knowledge distillation mechanism, in which local object information is used to regularize global scene features.
Proceedings ArticleDOI
Peeking Into the Future: Predicting Future Person Activities and Locations in Videos
TL;DR: An end-to-end, multi-task learning system utilizing rich visual features about human behavioral information and interaction with their surroundings is proposed, providing the first empirical evidence that joint modeling of paths and activities benefits future path prediction.
Proceedings ArticleDOI
D3TW: Discriminative Differentiable Dynamic Time Warping for Weakly Supervised Action Alignment and Segmentation
TL;DR: The proposed Discriminative Differentiable Dynamic Time Warping (D3TW) innovatively solves sequence alignment with discriminative modeling and end-to-end training, which substantially improves the performance in weakly supervised action alignment and segmentation tasks.