Aims & Scope

The Vision and Learning Seminar Series was started in 2020. It covers topics of the cutting-edge research on applying machine learning (or deep learning) techniques for visual recognition tasks, including image classification, object detection, visual segmentation, video understanding, vision-language techniques, etc. The talks will cover well-known or recent works accepted by prestigious conferences/journals such as CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, IJCV, PAMI. Beyond the speakers from my group, we will occasionally invite worldwide researchers to share their latest progress. We welcome all researchers or students from BJTU to physically or virtually attend our seminar series and hope it is helpful to their future research. Please send an email to if you are interested to join our seminar series.

Upcoming Presentations

Date Presenter Affiliation Paper or topic
Dec. 11 Zekang Zhang
Shiyin Zhang
Paper Sharing (TBA)

Finished Presentations, 2022

Date Presenter Affiliation Paper or topic
Dec. 4 Yanda Li
Zhongwei Ren
Yuyang Yin
Diffusion Model [pdf]
Segmentation with diffusion [pdf]
Diffusion Application on low-level vision [pdf]
Nov. 27 Yan Fang
Yihan Hu
BJTU Learning from Future: A Novel Self-Training Framework for Semantic Segmentation [pdf]
XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model [pdf]
Nov. 20 Chenyi Zhang
Qian Yang
BJTU Reviving Iterative Training with Mask Guidance for Interactive Segmentation [pdf] Fine-Grained Entity Segmentation [pdf]
Oct. 30 Hongguang Zhu
Weiqi Jin
BJTU Unsupervised Visual Representation Learning by Synchronous Momentum Grouping [pdf]
Effective Adaptation in Multi-Task Co-Training for Unified Autonomous Driving [pdf]
Oct. 23 Qiqi Gong
Ziling Wang
BJTU CP2: Copy-Paste Contrastive Pretraining for Semantic Segmentation [pdf]
Bi-directional Contrastive Learning for Domain Adaptive Semantic Segmentation [pdf]
Oct. 16 Siyu Jiao
Xinhao Zhong
BJTU VITA: Video Instance Segmentation via Object Token Association [pdf]
Accelerating DETR Convergence via Semantic-Aligned Matching [pdf]
Oct. 9 Zhongwei Ren
Feng Zhu
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation [pdf]
Rethinking Resolution in the Context of Efficient Video Recognition [pdf]
Sep. 25 Haojie Ding BJTU Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation [pdf]
Sep. 18 Mengxue Qu
Kunyang Han
BJTU MILAN: Masked Image Pretraining on Language Assisted Representation [pdf]
PromptDet: Towards Open-Vocabulary Detection using Uncurated Images [pdf]
Jul. 10 Mengxue Qu
Qiqi Gong
Zilin Wang
BJTU Referring Related Tasks (CVPR22) [pdf1]
Ultra High Resolution (CVPR22) [pdf2]
Domain Adaptation (CVPR22) [pdf3]
Jul. 3 Hongguang Zhu
Kunyang Han
BJTU VL Modeling Pre-training (CVPR22) [pdf1]
Open-set (CVPR22) [pdf2]
Jun. 26 Zhongwei Ren
Zhiyuan Fang
Siyu Jiao
Video Segmentation (CVPR22) [pdf1]
Few-shot Segmentation (CVPR22) [pdf2] [pdf3]
Jun. 19 Feng Zhu
Haojie Ding
Instance Segmentation (CVPR22) [pdf1]
Semantic / Panoptic Segmentation (CVPR22) [pdf2]
Jun. 12 Gengwei Zhang
Zekang Zhang
Yan Fang
Continual Learning (CVPR22) [pdf1] [pdf2]
Semi-supervised Learning (CVPR22) [pdf3]
Jun. 5 Yanda Li
Yihan Hu
Matting (CVPR22) [pdf1] [pdf2]
May. 8 Zhiyuan Fang BIT Learning What Not to Segment: A New Perspective on Few-Shot Segmentation [pdf]
Apr. 24 Liyuan Wang Tsinghua [Distinguished Lectures] Brain-inspired Continual Learning [pdf]
Apr. 17 Yan Fang
Zhongwei Ren
BJTU Rethinking Semantic Segmentation: A Prototype View [pdf]
Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation [pdf]
Apr. 10 Shiyin Zhang
Qiqi Gong
BJTU Focal Self-attention for Local-Global Interactions in Vision Transformers [pdf]
Revisiting Multi-scale Feature Fusion for Semantic Segmentation [pdf]
Mar. 27 Yihan Hu
Mengxue Qu
BJTU Semantic Image Matting [pdf]
Conditional Prompt Learning for Vision-Language Models [pdf]
Mar. 20 Zilin Wang
Kunyang Han
BJTU DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation [pdf]
Revitalize Region Feature for Democratizing Video-Language Pre-training [pdf]
Mar. 13 Siyu Jiao
Haojie Ding
BJTU Few-Shot Segmentation via Cycle-Consistent Transformer [pdf]
DN-DETR: Accelerate DETR Training by Introducing Query DeNoising [pdf]
Feb. 20 Siyu Jiao
Kunyang Han
BJTU Few-Shot Segmentation via Cycle-Consistent Transformer [pdf]
Open-Vocabulary Image Segmentation [pdf]
Feb. 13 Haojie Ding
Yihan Hu
BJTU K-Net: Towards Unified Image Segmentation [pdf]
Vision Transformer with Deformable Attention [pdf]
Jan. 23 Shiyin Zhang
Mengxue Qu
BJTU Pyramid Fusion Transformer for Semantic Segmentation [pdf]
Language-Driven Semantic Segmentation [pdf]
Jan. 16 Tianlong Chen UT Austin [Distinguished Lectures] How to be a qualified PhD? [pdf]
Jan. 9 Zhongwei Ren BJTU Weekly Supervised Instance Segmentation for Videos with Temporal Mask Consistency [pdf]

Finished Presentations, 2021

Date Presenter Affiliation Paper or topic
Dec. 26 Yihan Hu
Kunyang Han
BJTU Robust High-Resolution Video Matting with Temporal Guidance [pdf]
DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting [pdf]
Dec. 19 Haojie Ding
Yihang Hu
BJTU TokenLearner: What Can 8 Learned Tokens Do for Images and Videos? [pdf]
Associating Objects with Transformers for Video Object Segmentation [pdf]
Dec. 12 Shiyin Zhang
Mengxue Qu
BJTU Masked-attention Mask Transformer for Universal Image Segmentation [pdf]
LAVT: Language-Aware Vision Transformer for Referring Image Segmentation [pdf]
Dec. 5 Zhiyuan Fang
Zekang Zhang
BJTU Per-Pixel Classification is Not All You Need for Semantic Segmentation [pdf]
Prototype Augmentation and Self-Supervision for Incremental Learning [pdf]
Nov. 28 Qiqi Gong
Zilin Wang
BJTU Continual learning in cross-modal retrieval [pdf]
Open-World Entity Segmentation [pdf]
Oct. 24 Qiqi Gong
Zilin Wang
BJTU VL-BERT:Pretraining of Generic Visual-Linguistic Representations [pdf]
Uncertainty-aware Pseudo Label Refinery for Domain Adaptive Semantic Segmentation [pdf]
Oct. 17 Haojie Ding BJTU Panoptic SegFormer [pdf]
Sep. 26 Zhongwei Ren
Yan Fang
BJTU End-to-End Video Instance Segmentation with Transformers
Semi-supervised Semantic Segmentation with Directional Context-aware Consistency [pdf]
Sep. 18 Siyu Jiao
Kunyang Han
BJTU HyperSeg: Patch-wise Hypernetwork for Real-time Semantic Segmentation [pdf]
Emerging Properties in Self-Supervised Vision Transformers [pdf]
Sep. 12 Kao Liao
Yihan Hu
BJTU Global Pooling, More than Meets the Eye: Position Information is Encoded Channel-Wise in CNNs [pdf]
Associating Objects with Transformers for Video Object Segmentation [pdf]
Sep. 3 Shiyin Zhang
Mengxue Qu
BJTU Sparse R-CNN: End-to-End Object Detection with Learnable Proposals [pdf]
Instances as Queries [pdf]
Aug. 27 Zeikang Zhang
Zhiyuan Fang
BIT SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers [pdf]
SOTR: Segmenting Objects with Transformers [pdf]
Aug. 20 Qiqi Gong
Zilin Wang
BJTU Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation [pdf]
SSH: A Self-Supervised Framework for Image Harmonization
Aug. 13 Zhongwei Ren BJTU OpenMMLab Architecture [pdf]
Aug. 6 Xin Wang BJTU On Data-Augmentation and Consistency-based SSL [pdf]
Aug. 30 Shiyin Zhang
Mengxue Qu
BJTU Per-Pixel Classification is Not All You Need for Semantic Segmentation [pdf]
End-to-End Vision-Language Pre-training Enhanced by Visual Learning [pdf]
Jul. 23 Zhiyuan Fang
Zekang Zhang
BIT Scale-Aware Graph Neural Network for Few-Shot Semantic Segmentation [pdf]
Not All Images are Worth 16x16 Words: Dynamic Vision Transformers with Adaptive Sequence Length [pdf]
Jul. 16 Kang Liao
Shiyin Zhang
BJTU TransFill: Reference-guided Image Inpainting by Merging Multiple Color and Spatial Transformations [pdf]
Lite-HRNet: A Lightweight High-Resolution Network [pdf]
Jul. 9 Siyu Jiao
Qiqi Gong
BJTU SegFix: Model-Agnostic Boundary Refinement for Segmentation [pdf]
PointRend: Image Segmentation as Rendering [pdf]
Jul. 2 Mengxue Qu
Kunyang Han
BJTU Swin-Transformer [pdf]
Aligning Pretraining for Detection via Object-Level Contrastive Learning [pdf]
Jun. 18 Zhiyuan Fang
Zekang Zhang
BIT Hypercorrelation Squeeze for Few-Shot Segmenation[pdf]
Semi-Supervised Semantic Segmentation with Cross Pseudo[pdf]
Jun. 11 Kang Liao
Qiqi Gong
BJTU Positional Encoding as Spatial Inductive Bias in GANs [Upload Soon]
Rethinking BiSeNet for Real-time Semantic Segmentation [pdf]
Jun. 4 Siyu Jiao
Kunyang Han
BJTU Interactive Two-Stream Decoder for Accurate and Fast Saliency Detection [pdf]
Cross-Dataset Collaborative Learning for Semantic Segmentation [pdf]
May. 28 Shiyin Zhang
Mengxue Qu
BJTU Repurposing GANs for One-shot Semantic Part Segmentation [pdf]
Improve Vision Transformer Training by Suppressing Over-smoothing [pdf]
May. 14 Zhiyuan Fang
Zekang Zhang
BIT Few-shot Learning [pdf]
May. 7 Kunyang Han BJTU Self-Supervised Learning [pdf]
Apr. 17 Mengxue Qu BJTU Transformer [pdf]
Apr. 10 Siyu Jiao BJTU Video object segmentation [pdf]
Mar. 27 Qiqi Gong BJTU One stage object detection [pdf]
Feb. 20 Shiyin Zhang BJTU Interactive object segmentation [pdf]
Feb. 06 Guoliang Kang CMU Domain Adaptive Semantic Segmentation and Object Recognition [pdf]
Jan. 30 Kunyang Han BJTU Deep Image/Video Matting [pdf]
Jan. 23 Siyu Jiao BJTU Panoptic Segmentation Networks [pdf]
Jan. 16 Qiqi Gong BJTU Detection Networks [pdf]
Jan. 09 Mengxue Qu BJTU Referring Segmentation Networks [pdf]

Finished Presentations, 2020

Date Presenter Affiliation Paper or topic
Dec. 19 Kunyang Han BJTU Instance Segmentation Networks [pdf]
Dec. 12 Shiyin Zhang BJTU Classification Networks [pdf]
Nov. 28 Tao Ruan BJTU Programming at Deep Learning Field [pdf]
Oct. 23 Siyu Jiao BJTU Sematic Segmentation Networks [pdf]
Oct. 09 Qiqi Gong BJTU Basic Knowledge about Computer Vision [pdf]
Sep. 25 Kunyang Han BJTU Basic Layers in Deep Learning [pdf]
Sep. 18 Zhedong Zheng UTS Person Re-ID and Building Re-ID [pdf]
Sep. 11 Mengxue Qu BJTU Popular Datasets in Computer Vision [pdf]
Sep. 04 Xiaolin Zhang UTS Weakly Supervised Object Localization [pdf]
Aug. 28 Shiyin Zhang BJTU Interactive Object Segmentation with Inside-Outside Guidance [pdf]