Search Results - "Kraehenbuehl, Philipp"

Joint Monocular 3D Vehicle Detection and Tracking by Hu, Hou-Ning, Cai, Qi-Zhi, Wang, Dequan, Lin, Ji, Sun, Min, Kraehenbuehl, Philipp, Darrell, Trevor, Yu, Fisher

“…Vehicle 3D extents and trajectories are critical cues for predicting the future location of vehicles and planning future agent ego-motion based on those…”
Get full text

Constrained Convolutional Neural Networks for Weakly Supervised Segmentation by Pathak, Deepak, Krahenbuhl, Philipp, Darrell, Trevor

“…We present an approach to learn a dense pixel-wise labeling from image-level tags. Each image-level tag imposes constraints on the output labeling of a…”
Get full text

Learning from All Vehicles by Chen, Dian, Krahenbuhl, Philipp

“…In this paper, we present a system to train driving policies from experiences collected not just from the ego-vehicle, but all vehicles that it observes. This…”
Get full text

Saliency filters: Contrast based filtering for salient region detection by Perazzi, F., Krahenbuhl, P., Pritch, Y., Hornung, A.

“…Saliency estimation has become a valuable tool in image processing. Yet, existing approaches exhibit considerable variation in methodology, and it is often…”
Get full text

A Century of Portraits: A Visual Historical Record of American High School Yearbooks by Ginosar, Shiry, Rakelly, Kate, Sachs, Sarah M., Yin, Brian, Lee, Crystal, Krahenbuhl, Philipp, Efros, Alexei A.

“…Imagery offers a rich description of our world and communicates a volume and type of information that cannot be captured by text alone. Since the invention of…”
Get full text

Does Spatial Cognition Emerge in Frontier Models? by Ramakrishnan, Santhosh Kumar, Wijmans, Erik, Kraehenbuehl, Philipp, Koltun, Vladlen

“…Not yet. We present SPACE, a benchmark that systematically evaluates spatial cognition in frontier models. Our benchmark builds on decades of research in…”
Get full text

Language Conditioned Traffic Generation by Tan, Shuhan, Ivanovic, Boris, Weng, Xinshuo, Pavone, Marco, Kraehenbuehl, Philipp

“…Simulation forms the backbone of modern self-driving development. Simulators help develop, test, and improve driving systems without putting humans, vehicles,…”
Get full text

Dense Random Fields by Kräehenbüehl, Philipp

“…Random field models are commonly used to express prior knowledge about image formation and are one of the central tools of computer vision and image…”
Get full text