Trevor Darrell

TL;DR: Uncertainty-guided Continual Bayesian Neural Networks (UCB) is proposed, where the learning rate adapts according to the uncertainty defined in the probability distribution of the weights in networks.

TL;DR: In this article, the authors investigate how contextural information can improve visual recognition of feedback gestures during interactions with embodied conversational agents and present a visual recognition model that integrates cues from the spoken dialogue of spoken dialogue.

TL;DR: This paper introduces a new dataset that is annotated with action tubes containing multi-object interactions, and proposes an end-to-end spatio-temporal action detection model that performs both spatial and temporal regression simultaneously.

TL;DR: This work ground task-relevant words or phrases with attention maps from a pretrained large-scale model and shows that supervising spatial attention in this way improves performance on classification tasks with biased and noisy data, including ~3 −15% worst-group accuracy improvements and ~41-45% relative improvements on fairness metrics.

TL;DR: Quasi-Dense Similarity Learning is presented, which densely samples hundreds of object regions on a pair of images for contrastive learning and which rivals the performance of state-of-the-art tracking methods on all benchmarks and sets a new state of theart on the large-scale BDD100K MOT benchmark, while introducing negligible computational overhead to the detector.