Recent work leverages the expressive power of generative adversarial net...
Contemporary autonomous vehicle (AV) benchmarks have advanced techniques...
Motion planning for safe autonomous driving requires learning how the
en...
Multiple existing benchmarks involve tracking and segmenting objects in ...
Contrastively trained image-text models such as CLIP, ALIGN, and BASIC h...
By design, average precision (AP) for object detection aims to treat all...
Monocular object detection and tracking have improved drastically in rec...
We study how robust current ImageNet models are to distribution shifts
a...
For many years, multi-object tracking benchmarks have focused on a handf...
Object tracking can be formulated as "finding the right object in a vide...
We introduce a systematic framework for quantifying the robustness of
cl...
Video analysis is the task of perceiving the world as it changes. Often,...
While deep feature learning has revolutionized techniques for static-ima...