IIS Computer Vision & Machine Learning Lab

  

** IIS - CVML Update **

new

We are currently recruiting full-time research assistants and postdocs. Applicants that have background in computer vision and machine learning are welcome to apply for the positions.

 

Applications and inquiries can be emailed to liutyng@iis.sinica.edu.tw (Tyng-Luh Liu)

 

 

 

07/2024

 

** Our paper entitled "Learning Diffusion Models for Multi-View Anomaly Detection" is accepted to ECCV 2024. 

 

07/2024

 

** Our paper entitled "Pseudo-Embedding for Generalized Few-Shot Point Cloud Segmentation" is accepted to ECCV 2024. 

 

07/2024

 

** Thomas Lin has joined IIS-CVML Lab as a full-time RA. 

 

03/2024

 

** Two papers on DeepFake Detection and Face Anti-Spoofing are accepted to CVPR 2024. 

 

07/2023

 

** Congratulations to lab member Yen-Chi Hsu for obtianing Ph.D. in CS from NTU. 

 

07/2023

 

** Our paper entitled "Attention Discriminant Sampling for Point Clouds" is accepted by ICCV 2023.

 

05/2023

 

** Our paper entitled "ABC-Norm Regularization for Fine-Grained and Long-Tailed Image Classification" is accepted by IEEE TIP.

 

04/2023

 

** Our paper entitled "Shape-Guided Dual-Memory Learning for 3D Anomaly Detection" is accepted by ICML 2023.  

 

02/2023

 

** Our paper entitled "One-shot Action Detection via Attention Zooming In" is accepted by ICASSP 2023.

 

02/2023

 

** Our paper entitled "IoU-Aware Multi-Expert Cascade Network via Dynamic Ensemble for Long-tailed Object Detection" is accepted by ICASSP 2023.

 

08/2022

 

** Our paper entitled "Aggregating Bilateral Attention for Few-Shot Instance Localization" is accepted by WACV 2023.

 

07/2022

 

** Our paper entitled "Self-Supervised Sparse Representation for Video Anomaly Detection" is accepted by ECCV 2022.

 

07/2022

 

** Our paper entitled "Decoupled Contrastive Learning" is accepted by ECCV 2022.

 

03/2022

 

** Our paper entitled "Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation from Monocular Video" is accepted by CVPR 2022.

 

01/2022

 

** Our paper entitled "SAGA: Self-Augmentation with Guided Attention for Representation Learning" is accepted by ICASSP 2022.

 

12/2021

 

** Our paper entitled "Pose Adaptive Dual Mixup for Few-Shot Single-View Reconstruction" is accepted by AAAI 2022.

 

07/2021

 

** Our paper entitled "Learning Unsupervised Metaformer for Anomaly Detection" is accepted by ICCV 2021.

 

02/2021

 

** Our paper entitled "Adaptive Image Transformer for One-Shot Object Detection is accepted by CVPR 2021.

 

01/2021

 

** Our paper entitled "Referring Image Segmentation via Language-Driven Attention" is accepted by ICRA 2021.

 

12/2020

 

** Our paper entitled "Adaptive and Generative Zero-Shot Learning" is accepted by ICLR 2021.

 

12/2020

 

** Our paper entitled "Text-guided Graph Neural Networks for Referring 3D Instance Segmentation" is accepted by AAAI 2021.

 

07/2020

 

** Our paper entitled "Learning from Music to VIsual Storytelling of Shots: A Deep Interactive Learning Mechanism" is accepted by ACM MM 2020.

 

07/2020

 

** Our paper entitled "Self-similarity Student for Partial Label Histopathology Image Segmentation" is accepted by ECCV 2020.

 

12/2019

 

** Our paper entitled "Query-driven Multi-Instance Learning" is accepted by AAAI 2020.

 

09/2019

 

** Our paper entitled "One-Shot Object Detection with Co-Attention and Co-Excitation" is accepted by NeurIPS 2019.

 

07/2019

 

** Our paper entitled "See-through-Text Grouping for Referring Image Segmentation" is accepted by ICCV 2019.

 

07/2019

 

** Our paper entitled "Tell Me Where It is Still Blurry: Adversarial Blurred Region Mining and Refining" is accepted by ACM MM 2019.

 

11/2018

 

** Our paper entitled "Unsupervised Meta-learning of Figure-Ground Segmentation via Imitating Visual Effects" is accepted by AAAI 2019.

 

10/2018

 

** Our paper entitled "Attention Discriminant Sampling for Point Clouds" is accepted by ICCV 2003.

 

06/2018

 

** The joint effort with Prof. Hwann-Tzong Chen and his students (Shou-Yao Roy Tseng & Shao-Heng Tai) has won the first place for Instance Segmentation Challenge in Robust Vision Challenge at CVPR 2018.

 

03/2018

 

** Our paper entitled "Coherent Deep-Net Fusion To Classify Shots In Concert Videos" is accepted by IIEEE TMM.

 

02/2018

 

** Our paper entitled "Cube Padding for Weakly-Supervised Saliency Prediction in 360¢X Videos" is accepted by CVPR 2018.