[ICLR 2025] Binary Spherical Quantization + [CVPR 2026] Leech Spherical Quantization

Global Tracking Transformers, CVPR 2022

(CVPR 2022) A minimalist, mapless, end-to-end self-driving stack for joint perception, prediction, planning and control.

(ICCV 2021, Oral) RL and distillation in CARLA using a factorized world model

Compressed Video Action Recognition

Video Compression through Image Interpolation (ECCV'18) [PyTorch]

Long-Term Feature Banks for Detailed Video Understanding

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

Simultaneous object detection and tracking using center points.

Code for Domain Adaptation Through Task Distillation (ECCV 20)

MONeT framework for reducing memory consumption of DNN training

Object detection on multiple datasets with an automatically learned unified label space.

Code to accompany "Does computer vision matter for action?"

(CoRL 2019) Driving in CARLA using waypoint prediction and two-stage imitation learning

Object detection, 3D detection, and pose estimation using center point detection:

Bottom-up Object Detection by Grouping Extreme and Center Points