Publication

Journal

• An Individual-difference-aware Model for Cross-person Gaze Estimation (Our method ranks the first on Gaze Estimation Benchmark!) TIP 2021

• Concept Parser with Multi-modal Graph Learning for Video Captioning TSCVT 2023

Conference

2023

• Follow-me: Deceiving Trackers with Fabricated Paths

S Lou*, B Liu*, J Bao, J Ding, J Yu. In ACM MM 2023

• NeurOCS: Neural NOCS Supervision for Monocular 3D Object Localization

Z Min, B Zhuang, S Schulter, B Liu, E Dunn, M Chandraker. In CVPR 2023

2022

• Weakly But Deeply Supervised Occlusion-Reasoned Parametric Road Layouts

  B Liu, B Zhuang and M Chandraker. In CVPR, 2022

• ESCNet: Gaze Target Detection with the Understanding of 3D Scenes

  J Bao, B Liu and J Yu. In CVPR, 2022

• MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation

I Shin, Y Tsai, S Schulter, B Zhuang, B Liu, S Garg, I Kweon, K Yoon  In CVPR, 2022

2021

• Divide-and-Conquer for Lane-Aware Diverse Trajectory Prediction

S Narayanan, R Moslemi, F Pittaluga, B Liu, M Chandraker. In CVPR, 2021

2020

• SMART: Simultaneous Multi-Agent Recurrent Trajectory Prediction

NN Sriram, B Liu, F Pittaluga, M Chandraker. In ECCV, 2020

• Understanding Road Layout from Videos as a Whole

B Liu, B Zhuang, S Schulter, P Ji, M Chandraker In CVPR, 2020 

• Peek-a-boo: Occlusion Reasoning in Indoor Scenes with Plane Representations

Z Jiang, B Liu, S Schulter, Z Wang, M Chandraker. In CVPR 2020

• Active Adversarial Domain Adaptation 

JC Su, YH Tsai, K Sohn, B Liu, S Maji, M Chandraker. In WACV 2020. [pdf]

2019

• A Parametric Top-View Representation of Complex Road Scenes

Ziyan Wang , Buyu Liu, Samuel Schulter and Manmohan Chandraker. In CVPR, 2019 [pdf]