activity
20172021
most citedSemantically-Guided Representation Learning for Self-Supervised Monocular Depth

47 citations · 122 across the 10 of their papers we have counts for

collaborators

17 papers

cs.CV20211 cited

Denoised Non-Local Neural Network for Semantic Segmentation

Qi Song, Jie Li, Hao Guo +1

The non-local network has become a widely used technique for semantic segmentation, which computes an attention map to measure the relationships of each pixel pair. However, most o…

cs.CV2021

LocTex: Learning Data-Efficient Visual Representations from Localized Textual Supervision

Zhijian Liu, Simon Stent, Jie Li +2

Computer vision tasks such as object detection and semantic/instance segmentation rely on the painstaking annotation of large training datasets. In this paper, we propose LocTex th…

cs.CV2021

Is Pseudo-Lidar needed for Monocular 3D Object detection?

Dennis Park, Rares Ambrus, Vitor Guizilini +2

Recent progress in 3D object detection from single images leverages monocular depth estimation as a way to produce 3D pointclouds, turning cameras into pseudo-lidar sensors. These…

cs.CV2021

Hierarchical Lovász Embeddings for Proposal-free Panoptic Segmentation

Tommi Kerola, Jie Li, Atsushi Kanehira +3

Panoptic segmentation brings together two separate tasks: instance and semantic segmentation. Although they are related, unifying them faces an apparent paradox: how to learn simul…

cs.CV2021

Geometric Unsupervised Domain Adaptation for Semantic Segmentation

Vitor Guizilini, Jie Li, Rares Ambrus +1

Simulators can efficiently generate large amounts of labeled synthetic data with perfect supervision for hard-to-label tasks like semantic segmentation. However, they introduce a d…

cs.CV2021

Learning to Track with Object Permanence

Pavel Tokmakov, Jie Li, Wolfram Burgard +1

Tracking by detection, the dominant approach for online multi-object tracking, alternates between localization and association steps. As a result, it strongly depends on the qualit…