About
Welcome to the Video, Image, and Sound Analysis Lab (VISAL) at the City University of Hong Kong! The lab is directed by Prof. Antoni Chan in the Department of Computer Science.
Our main research activities include:
- Computer Vision, Surveillance
- Machine Learning, Pattern Recognition
- Computer Audition, Music Information Retrieval
- Eye Gaze Analysis
For more information about our current research, please visit the projects and publication pages.
Opportunities for graduate students and research assistants – if you are interested in joining the lab, please check this information.
Latest News [more]
- [Aug 16, 2021]
Congratulations Qingzhong for defending his thesis!
- [Aug 12, 2021]
Congratulations to Jia for defending his thesis!
- [Jul 1, 2021]
Dr. Chan was promoted to Professor!
- [Apr 29, 2021]
Congratulations to Yufei for defending his thesis!
Recent Publications [more]
- Dynamic Momentum Adaptation for Zero-Shot Cross-Domain Crowd Counting.
,
In: ACM Multimedia (MM), Oct 2021. - Group-based Distinctive Image Captioning with Memory Attention.
,
In: ACM Multimedia (MM), Oct 2021 (oral). [supplemental] - BEV-Net: Assessing Social Distancing Compliance by Joint People Localization and Geometric Reasoning.
,
In: Intl. Conference on Computer Vision (ICCV), Oct 2021. - A Comparative Survey: Benchmarking for Pool-based Active Learning.
,
In: International Joint Conf. on Artificial Intelligence (IJCAI), Survey Track, Aug 2021. - Clustering Hidden Markov Models With Variational Bayesian Hierarchical EM.
,
IEEE Trans. on Neural Networks and Learning Systems (TNNLS), To appear 2021. - The effects of attentional and interpretation biases on later pain outcomes among younger and older adults: A prospective study.
,
European Journal of Pain, [online] Aug 2021. - Hierarchical Learning of Hidden Markov Models with Clustering Regularization.
,
In: 37th Conference on Uncertainty in Artificial Intelligence (UAI), Jul 2021. - Multiple-criteria Based Active Learning with Fixed-size Determinantal Point Processes.
,
In: Subset Selection in Machine Learning: From Theory to Applications, ICML Workshop, July 2021. - Improve Generalization and Robustness of Neural Networks via Weight Scale Shifting Invariant Regularizations.
,
In: ICML workshop on Adversarial Machine Learning, July 2021. - Meta-Graph Adaptation for Visual Object Tracking.
,
In: IEEE International Conference on Multimedia and Expo (ICME), Jul 2021 (oral).
Recent Project Pages [more]
We analyze eye movement data on stimuli with different feature layouts. Through co-clustering HMMs, we discover common strategies on each stimuli and cluster subjects with similar strategies.
- , "Eye Movement analysis with Hidden Markov Models (EMHMM) with co-clustering." Behavior Research Methods, April 2021.
In this paper, we propose a novel meta-graph adaptation network (MGA-Net) to effectively adapt backbone feature extractors in existing deep trackers to a specific online tracking task.
- , "Meta-Graph Adaptation for Visual Object Tracking." In: IEEE International Conference on Multimedia and Expo (ICME), Jul 2021 (oral).
In this paper, we propose a progressive unsupervised learning (PUL) framework, which entirely removes the need for annotated training videos in visual tracking.
- , "Progressive Unsupervised Learning for Visual Object Tracking." In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2021 (oral). [supplemental]
We propose a fully nested neural network (FN3) that runs only once to build a nested set of compressed/quantized models, which is optimal for different resource constraints. We then propose a Bayesian version that estimates the ordered dropout hyperparameter and has well calibrated uncertainty.
- , "Fully Nested Neural Network for Adaptive Compression and Quantization." In: International Joint Conf. on Artificial Intelligence (IJCAI), Yokohama, July 2020. [supplemental]
- , "Bayesian Nested Neural Networks for Uncertainty Calibration and Adaptive Compression." In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2021.
We propose a generalized loss function for density map regression based on unbalanced optimal transport. We prove that pixel-wise L2 loss and Bayesian loss are special cases and sub-optimal solutions to our proposed loss. Since the predicted density will be pushed toward annotation positions, the density map prediction will be sparse and can naturally be used for localization.
- , "A Generalized Loss Function for Crowd Counting and Localization." In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2021. [supplemental]
Recent Datasets and Code [more]
CVCS: Cross-View Cross-Scene Multi-View Crowd Counting Dataset
Synthetic dataset for cross-view cross-scene multi-view counting. The dataset contains 31 scenes, each with about ~100 camera views. For each scene, we capture 100 multi-view images of crowds.
- Files: Google Drive
- Project page
- If you use this dataset please cite:
Cross-View Cross-Scene Multi-View Crowd Counting.
,
In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR):557-567, Jun 2021.
Fine-Grained Crowd Counting Dataset
Dataset for fine-grained crowd counting, which differentiates a crowd into categories based on the low-level behavior attributes of the individuals (e.g. standing/sitting or violent behavior) and then counts the number of people in each category.
- Files: dataset (1.2GB), code
- Project Page
- If you use this dataset please cite:
Parametric Manifold Learning of Gaussian Mixture Models (PRIMAL-GMM) Toolbox
This is a python toolbox learning parametric manifolds of Gaussian mixture models (GMMs).
- Files: download here
- Project page
- If you use this toolbox please cite:
PRIMAL-GMM: PaRametrIc MAnifold Learning of Gaussian Mixture Models.
,
IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), to appear 2021.
Eye Movement analysis with Switching HMMs (EMSHMM) Toolbox
This is a MATLAB toolbox for analyzing eye movement data using switching hidden Markov models (SHMMs), for analyzing eye movement data in cognitive tasks involving cognitive state changes. It includes code for learning SHMMs for individuals, as well as analyzing the results.
- Files: download here
- Project page
- If you use this toolbox please cite:
Eye movement analysis with switching hidden Markov models.
,
Behavior Research Methods, 52:1026-1043, June 2020.
EgoDaily – Egocentric dataset for Hand Disambiguation
Egocentric hand detection dataset with variability on people, activities and places, to simulate daily life situations.
- Files: download page
- If you use this dataset please cite:
Is that my hand? An egocentric dataset for hand disambiguation.
,
Image and Vision Computing, 89:131-143, Sept 2019.