Trevor Darrell

TL;DR: A new approach to introspective explanations is proposed which uses a visual (spatial) attention model to train a convolutional network end-to-end from images to the vehicle control commands, and two approaches to attention alignment, strong- and weak-alignment are explored.

TL;DR: Pfinder as mentioned in this paper is a real-time system for tracking and interpretation of people, which uses a multiclass statistical model of color and shape to segment a person from a background scene, and implements heuristics which can find and track people's head and hands in a wide range of viewing conditions.

TL;DR: It is concluded, with a few exceptions, that it is best to copy as many layers of a pre-trained network as possible, and then adjust the level of fine-tuning based on the visual distance from source.

TL;DR: In this paper, the authors propose an online framework for 3D vehicle detection and tracking from monocular videos, which can not only associate detections of vehicles in motion over time, but also estimate their complete 3D bounding box information from a sequence of 2D images captured on a moving platform.

TL;DR: A new Equalizer model is introduced that ensures equal gender probability when gender Evidence is occluded in a scene and confident predictions when gender evidence is present and has lower error than prior work when describing images with people and mentioning their gender and more closely matches the ground truth ratio of sentences including women to sentences including men.