Di Huang  ()

Ph.D., Professor, IEEE Senior Member and CCF/CAAI Distinguished Member
Intelligent Recognition and Image Processing Lab
School of Computer Science and Engineering
Beihang University (formerly known as Beijing University of Aeronautics and Astronautics, BUAA)

Address: Room G906, New Main Building, No.37, Xueyuan Road, Haidian District, Beijing, China, 100191
Tel.: +86-10-82316379;  Email: dhuang (at) buaa (dot) edu (dot) cn

[Work Experience][Education][Research Interests][Publications][Projects][Professional Activities][Teaching][Honors and Awards][Hobbies]

Homepage

 

 

News [More]

下载 Our paper, titled “Align-DETR: Enhancing End-to-end Object Detection with Aligned Loss” is accepted by British Machine Vision Conference, 2024 (20 Jul. 2024).

下载 Our paper, titled “PS-TTL: Prototype-based Soft-labels and Test-Time Learning for Few-shot Object Detection” is accepted by ACM Multimedia Conference, 2024 (16 Jul. 2024).

下载 Our paper, titled “OTAMatch: Optimal Transport Assignment with PseudoNCE for Semi-supervised Learning” is accepted by IEEE Transactions on Image Processing (2 Jul. 2024).

下载 Our paper, titled “Multi-modal Relation Distillation for Unified 3D Representation Learning” is accepted by European Conference on Computer Vision, 2024 (1 Jul. 2024).

下载 Our paper, titled “Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenes” is accepted by European Conference on Computer Vision, 2024 (1 Jul. 2024).

下载 Our paper, titled “AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizer” is accepted by European Conference on Computer Vision, 2024 (1 Jul. 2024).

下载 Our paper, titled “DrFER: Learning Disentangled Representations for 3D Facial Expression Recognition” won the Honorable Mention award of the Best Student Paper at IEEE International Conference on Automatic Face and Gesture Recognition, 2024 (31 May 2024).

下载 Our paper, titled “STAL3D: Unsupervised Domain Adaptation for 3D Object Detection via Collaborating Self-Training and Adversarial Learning” is accepted by IEEE Transactions on Intelligent Vehicles (28 Apr. 2024).

下载 Our paper, titled “SA3WT: Adaptive Wavelet-based Transformer with Self-paced Auto Augmentation for Face Forgery Detection” is accepted by International Journal of Computer Vision (23 Apr. 2024).

Work Experience

Education

Research Interests

Computer Vision; Pattern Recognition; Representation Learning; Biometrics; etc.

Selected Publications [Google Scholar]

Books/Book Chapters:

Preprints:

Online and Accepted Papers:

Journal Papers:

Conference Papers:

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010 and Before

Projects

Principal Investigator:

Key Participant:

Professional Activities

Talk:

Chair and PC Member:

Editor:

Reviewer:

Teaching

Honors and Awards

Non-Academic Hobbies

Racing sports; Traveling; Photography; etc.