About
Welcome to the Video, Image, and Sound Analysis Lab (VISAL) at the City University of Hong Kong! The lab is directed by Dr. 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]
- [May 6, 2019]
Congratulations to Di for defending his thesis!
- [Nov 1, 2018]
Congratulations to Lei for defending her thesis!
- [Jun 28, 2016]
Congratulations to Sijin for defending his thesis!
- [Jun 25, 2016]
Congratulations to Adeel for winning a “Best Research Paper Award 2013/14” from the Higher Education Commission (HEC) of Pakistan for his TPAMI 2013 paper!
Recent Publications [more]
- ButtonTips: Designing Web Buttons with Suggestions.
,
In: IEEE International Conference on Multimedia and Expo (ICME), Shanghai, to appear Jul 2019. - Describing like Humans: on Diversity in Image Captioning.
,
In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , Long Beach, June 2019. [code] - Residual Regression with Semantic Prior for Crowd Counting.
,
In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , Long Beach, June 2019. - Wide-Area Crowd Counting via Ground-Plane Density Maps and Multi-View Fusion CNNs.
,
In: IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), Long Bach, June 2019. - Density-Preserving Hierarchical EM Algorithm: Simplifying Gaussian Mixture Models for Approximate Inference.
,
IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), 41(6):1323-1337, June 2019. - Beyond Counting: Comparisons of Density Maps for Crowd Analysis Tasks - Counting, Detection, and Tracking.
,
IEEE Trans. on Circuits and Systems for Video Technology (TCSVT), 29(5):1408-1422, May 2019. - Hidden Markov modelling of eye movements in social anxiety: a data-driven machine-learning approach to eye-tracking research in psychopathology.
,
In: 2019 ADAA Annual Conference, Chicago, March 2019. - Eye Movement Patterns in Face Recognition are Associated with Cognitive Decline in Older Adults.
,
Psychonomic Bulletin & Review, 25(6):2200-2207, Dec 2018. - Hand detection using deformable part models on an egocentric perspective.
,
In: Digital Image Computing: Techniques and Applications (DICTA), Canberra, Dec 2018.
Recent Project Pages [more]
In this paper, a residual regression framework is proposed for crowd counting harnessing the correlation information among samples. By incorporating such information into our network, we discover that more intrinsic characteristics can be learned by the network which thus generalizes better to unseen scenarios. Besides, we show how to effectively leverage the semantic prior to improve the performance of crowd counting.
- , "Residual Regression with Semantic Prior for Crowd Counting." In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , Long Beach, June 2019.
An algorithm is proposed to simplify the Gaussian Mixture Models into a reduced mixture model with fewer mixture components, by maximizing a variational lower bound of the expected log-likelihood of a set of virtual samples.
- , "Approximate Inference for Generic Likelihoods via Density-Preserving GMM Simplification." In: NIPS 2016 Workshop on Advances in Approximate Bayesian Inference, Barcelona, Dec 2016.
- , "Density-Preserving Hierarchical EM Algorithm: Simplifying Gaussian Mixture Models for Approximate Inference." IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), 41(6):1323-1337, June 2019.
RNN-based models dominate the field of image captioning, however, (1) RNNs have to be calculated step-by-step, which is not easily parallelized. (2) There is a long path between the start and end of the sentence using RNNs. Tree structures can make a shorter path, but trees require special processing. (3) RNNs only learn single-level representations at each time step, while convolutional decoders are able to learn multi-level representations of concepts, and each of them should corresponds to an image area, which should benefit word prediction.
- , "CNN+CNN: Convolutional Decoders for Image Captioning." In: IEEE Computer Vision and Pattern Recognition: Language and Vision Workshop, Salt Lake City, Jun 2018. [code]
- , "Gated Hierarchical Attention for Image Captioning." In: Asian Conference on Computer Vision (ACCV), Perth, Dec 2018. [code]
