Darren's Homepage

About Me

I'm Da Zhang (张达), currently a tech lead & senior applied scientist in Autonomous Driving Lab, Alibaba DAMO Academy. The areas I work on include 3D object detection and segmentation, multi-sensor fusion and temporal reasoning. I obtained my Ph.D. degree from UCSB in 2020, advised by Prof. Yuan-Fang Wang, Prof. Matthew Turk and Prof. Xifeng Yan, where I worked on temporal activity localization and detection. Prior to UCSB, I received my B.S. degree from SJTU in 2014.

Education

University of California, Santa Barbara, CA, USA (Oct 2014 - Mar 2020)

Doctor of Philosophy, Computer Science
Advisor: Prof. Yuan-Fang Wang, Prof. Matthew Turk and Prof. Xifeng Yan

Shanghai Jiao Tong University, Shanghai, China (Sep 2010 - Jun 2014)

Bachelor of Science, Electronic Engineering
College Graduate Excellence Award of Shanghai

News

  • Check our Apsara Conference 2021 Onsite video on YouTube, and our intro video for autonomous driving under bad weather conditions on bilibili
  • [2022.4] Our paper on 3D object detection using efficient relational modeling is submitted to T-PAMI. We achieve the new SOTA for 3D detection on Waymo Open Dataset.
  • [2022.3] Our paper on 3D object detection via multi-modal multi-frame transformer is accepted to CVPR 2022. We set the new SOTA for 3D multi-modal detection on nuScenes and Waymo.
  • [2021.11] Our driveless logistics robot powered by Alibaba AD Lab delivers more than 2,000,000 parcels during double 11 shopping festival in China. Congratulations!
  • [2021.4] We improve CenterPoint with graph neural network and our latest submission ranks 1st on the LiDAR-only Waymo 3D object detection leaderboard.
  • [2020.3] Our paper on few-shot weakly-supervised activity detection is accepted for oral presentation at CVPR 2020.
  • [2019.12] I successfully defended my Ph.D. thesis. Thanks to my committee: Prof. Yuan-Fang Wang, Prof. Matthew Turk and Prof. Xifeng Yan.

Experience

Autonomous Driving Lab, Alibaba DAMO Academy, Beijing, China

Tech Lead & Senior Applied Scientist, present
Area: 3D Perception

Amazon Go, Seattle, USA

Applied Scientist Intern, summer 2019
Area: Image Recognition

Stanford Research International, Princeton, USA

Research Intern, summer 2017
Area: Visual Question Answering

Samsung Research America, Mountain View, USA

Research Intern, summer 2016
Area: Object Detection and Tracking

Selected Publications

  • INT: Towards Infinite-frames 3D Detection with An Efficient Framework
    Jianyun Xu, Zhenwei Miao, Da Zhang, Hongyu Pan, Kaixuan Liu, Peihan Hao, Jun Zhu, Zhengyang Sun, Hongmin Li, Xin Zhan
    European Conference on Computer Vision (ECCV) 2022, in submission
    [paper]
  • Ret3D: Rethinking Object Relations for Efficient 3D Object Detection in Driving Scenes
    Yu-Huan Wu, Da Zhang*, Le Zhang, Xin Zhan, Ming-Ming Cheng, Dengxin Dai, Yun Liu
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), in submission
    [paper] *: project lead
  • LIFT: Learning 4D LiDAR Image Fusion Transformer for 3D Object Detection
    Yihan Zeng, Da Zhang*, Chunwei Wang, Zhenwei Miao, Ting Liu, Xin Zhan, Dayang Hao, Chao Ma
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
    [paper] *: project lead
  • METAL: Minimum Effort Temporal Activity Localization in Untrimmed Videos
    Da Zhang, Xiyang Dai, Yuan-Fang Wang
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020
    Oral presentation
    [paper]
  • MAN: Moment Alignment Network for Natural Language Moment Retrieval via Iterative Graph Adjustment
    Da Zhang, Xiyang Dai, Xin Wang, Yuan-Fang Wang, Larry Davis
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019
    [paper]
  • Learning to Compose Topic-Aware Mixture of Experts for Zero-Shot Video Captioning
    Xin Wang, Jiawei Wu, Da Zhang, Yu Su, William Yang Wang
    AAAI Conference on Artificial Intelligence (AAAI), 2019
    [paper]
  • Dynamic Temporal Pyramid Network: A Closer Look at Multi-Scale Modeling for Activity Detection
    Da Zhang, Xiyang Dai, Yuan-Fang Wang
    Asian Conference on Computer Vision (ACCV), 2018
    Oral presentation
    [paper]
  • S3D: Single Shot multi-Span Detector via Fully 3D Convolutional Network
    Da Zhang, Xiyang Dai, Xin Wang, Yuan-Fang Wang
    British Machine Vision Conference (BMVC), 2018
    Oral presentation
    [paper]
  • Multimodal Transfer: A Hierarchical Deep Convolutional Neural Network for Fast Artistic Style Transfer
    Xin Wang, Geoffrey Oxholm, Da Zhang, Yuan-Fang Wang
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2017
    [paper]
  • Deep Reinforcement Learning for Visual Object Tracking in Videos
    Da Zhang, Hamid Maei, Xin Wang, Yuan-Fang Wang
    Technical report
    [paper]

Service

Conference Reviewer for CVPR, ECCV, ICCV, AAAI
Journal Reviewer for T-PAMI, IJCV