1 code implementation • ECCV 2020 • Yan Luo, Yongkang Wong, Mohan S. Kankanhalli, Qi Zhao
The proposed framework is gradient-based and model-agnostic.
1 code implementation • 11 Nov 2023 • Xudong Shen, Chao Du, Tianyu Pang, Min Lin, Yongkang Wong, Mohan Kankanhalli
The rapid adoption of text-to-image diffusion models in society underscores an urgent need to address their biases.
1 code implementation • 28 Sep 2023 • Yangyang Guo, Haoyu Zhang, Yongkang Wong, Liqiang Nie, Mohan Kankanhalli
Learning a versatile language-image model is computationally prohibitive under a limited computing budget.
1 code implementation • 6 Sep 2023 • Zeyu Ling, Bo Han, Yongkang Wong, Mohan Kangkanhalli, Weidong Geng
We also introduce a Transformer-based diffusion model MWNet (DDPM-like) as our main branch that can capture the spatial complexity and inter-joint correlations in motion sequences through a channel-dimension self-attention module.
no code implementations • 13 Jul 2023 • Yi Cheng, Ziwei Xu, Fen Fang, Dongyun Lin, Hehe Fan, Yongkang Wong, Ying Sun, Mohan Kankanhalli
Our research focuses on the innovative application of a differentiable logic loss in the training to leverage the co-occurrence relations between verb and noun, as well as the pre-trained Large Language Models (LLMs) to generate the logic rules for the adaptation to unseen action labels.
1 code implementation • 6 Jul 2022 • Guangzhi Wang, Yangyang Guo, Yongkang Wong, Mohan Kankanhalli
To quantitatively study the object bias problem, we advocate a new protocol for evaluating model performance.
1 code implementation • 5 Jul 2022 • Guangzhi Wang, Yangyang Guo, Yongkang Wong, Mohan Kankanhalli
2) Insufficient number of distant interactions in benchmark datasets results in under-fitting on these instances.
1 code implementation • 30 Jun 2022 • Yangyang Guo, Liqiang Nie, Yongkang Wong, Yibing Liu, Zhiyong Cheng, Mohan Kankanhalli
On the other hand, pertaining to the implicit knowledge, the multi-modal implicit knowledge for knowledge-based VQA still remains largely unexplored.
1 code implementation • 23 Jan 2022 • Yan Luo, Yongkang Wong, Mohan S. Kankanhalli, Qi Zhao
To this end, we propose a new learning approach, namely gradient adjustment learning (GAL), to leverage the knowledge learned from the past training iterations to adjust vanilla gradients, such that the remainders are minimized and the approximations are improved.
1 code implementation • 23 Jan 2022 • Yan Luo, Yongkang Wong, Mohan Kankanhalli, Qi Zhao
To explore these issues, we formulate a new semi-supervised continual learning method, which can be generically applied to existing continual learning models.
1 code implementation • NeurIPS 2021 • Ziwei Xu, Xudong Shen, Yongkang Wong, Mohan S Kankanhalli
We propose the Motion Capsule Autoencoder (MCAE), which addresses a key challenge in the unsupervised learning of motion representations: transformation invariance.
1 code implementation • NeurIPS 2021 • Yan Luo, Yongkang Wong, Mohan S. Kankanhalli, Qi Zhao
Secondly, due to the data complexity, it is challenging to differentiate the incorrect predictions from the correct ones on real-world large-scale datasets.
1 code implementation • 1 Sep 2021 • Xudong Shen, Yongkang Wong, Mohan Kankanhalli
Motivated by scenarios where data is used for diverse prediction tasks, we study whether fair representation can be used to guarantee fairness for unknown tasks and for multiple fairness notions simultaneously.
1 code implementation • 10 Aug 2021 • Ziwei Xu, Guangzhi Wang, Yongkang Wong, Mohan Kankanhalli
The concept module generates semantically meaningful features for primitive concepts, whereas the visual module extracts visual features for attributes and objects from input images.
no code implementations • ICCV 2021 • Xiheng Zhang, Yongkang Wong, Xiaofei Wu, Juwei Lu, Mohan Kankanhalli, Xiangdong Li, Weidong Geng
In this work, we take a step towards training robust models for cross-domain pose estimation task, which brings together ideas from causal representation learning and generative adversarial networks.
1 code implementation • 9 Jul 2020 • Yan Luo, Yongkang Wong, Mohan S. Kankanhalli, Qi Zhao
The proposed framework is gradient-based and model-agnostic.
no code implementations • 9 Feb 2020 • Junnan Li, Jianquan Liu, Yongkang Wong, Shoji Nishimura, Mohan Kankanhalli
To enable research in this direction, we introduce 360Action, the first omnidirectional video dataset for multi-person action recognition.
no code implementations • 9 Feb 2020 • Junnan Li, Ziwei Xu, Yongkang Wong, Qi Zhao, Mohan Kankanhalli
Therefore, it is important to develop algorithms that can leverage off-the-shelf labeled dataset to learn useful knowledge for the target task.
1 code implementation • 17 Dec 2019 • Yan Luo, Yongkang Wong, Mohan S. Kankanhalli, Qi Zhao
We propose a Direction Concentration Learning (DCL) method to improve congruency in the learning process, where enhancing congruency influences the convergence path to be less circuitous.
Ranked #8 on Image Classification on Tiny ImageNet Classification (using extra training data)
1 code implementation • 28 Aug 2019 • Tao Zhuo, Zhiyong Cheng, Peng Zhang, Yongkang Wong, Mohan Kankanhalli
Finally, by sequentially examining each state transition in the video graph, our method can detect and explain how those actions are executed with prior knowledge, just like the logical manner of thinking by humans.
no code implementations • ICLR 2019 • Andrey Sakryukin, Yongkang Wong, Mohan S. Kankanhalli
This property is particularly useful for user modeling (as for dialog agents) and recommendation tasks, as allows learning personalized representations of different user states.
1 code implementation • 8 Apr 2019 • Yan Luo, Yongkang Wong, Mohan Kankanhalli, Qi Zhao
In addition, analysis of the intra-class compactness and inter-class separability demonstrates the advantages of the proposed function over the softmax function, which is consistent with the performance improvement.
1 code implementation • CVPR 2019 • Junnan Li, Yongkang Wong, Qi Zhao, Mohan Kankanhalli
Despite the success of deep neural networks (DNNs) in image classification tasks, the human-level performance relies on massive training data with high-quality manual annotations, which are expensive and time-consuming to collect.
Ranked #26 on Image Classification on Clothing1M (using extra training data)
no code implementations • 13 Dec 2018 • Junnan Li, Yongkang Wong, Qi Zhao, Mohan S. Kankanhalli
Social relationships form the basis of social structure of humans.
1 code implementation • IEEE Transactions on Image Processing 2019 • Tao Zhuo, Zhiyong Cheng, Peng Zhang, Yongkang Wong, Mohan Kankanhalli
Moreover, our method achieves better performance than the best unsupervised offline algorithm on the DAVIS-2016 benchmark dataset.
1 code implementation • NeurIPS 2018 • Junnan Li, Yongkang Wong, Qi Zhao, Mohan S. Kankanhalli
Different from previous works in video representation learning, our unsupervised learning task is to predict 3D motion in multiple target views using video representation from a source view.
no code implementations • 29 Aug 2018 • Bingjie Xu, Junnan Li, Yongkang Wong, Mohan S. Kankanhalli, Qi Zhao
The recent advances in instance-level detection tasks lay strong foundation for genuine comprehension of the visual scenes.
no code implementations • 25 Jul 2018 • Junnan Li, Yongkang Wong, Qi Zhao, Mohan S. Kankanhalli
Video storytelling introduces new challenges, mainly due to the diversity of the story and the length and complexity of the video.
no code implementations • 3 Aug 2017 • Junnan Li, Yongkang Wong, Qi Zhao, Mohan Kankanhalli
However, due to the domain shift problem, the performance of Web images trained deep classifiers tend to degrade when directly deployed to videos.
1 code implementation • ICCV 2017 • Junnan Li, Yongkang Wong, Qi Zhao, Mohan S. Kankanhalli
Since the beginning of early civilizations, social relationships derived from each individual fundamentally form the basis of social structure in our daily life.
Ranked #3 on Visual Social Relationship Recognition on PIPA
no code implementations • 21 Jul 2016 • Wenhui Li, Yongkang Wong, An-An Liu, Yang Li, Yu-Ting Su, Mohan Kankanhalli
To enable the study of this problem, there exist a vast number of action datasets, which are recorded under controlled laboratory settings, real-world surveillance environments, or crawled from the Internet.
no code implementations • CVPR 2015 • Yan Luo, Yongkang Wong, Qi Zhao
In addition, since new datasets are built and shared in the community from time to time, it would be good not to retrain the entire model when new data are added.
no code implementations • 15 Mar 2014 • Arnold Wiliem, Conrad Sanderson, Yongkang Wong, Peter Hobson, Rodney F. Minchin, Brian C. Lovell
This paper describes a novel system for automatic classification of images obtained from Anti-Nuclear Antibody (ANA) pathology tests on Human Epithelial type 2 (HEp-2) cells using the Indirect Immunofluorescence (IIF) protocol.
no code implementations • 8 Apr 2013 • Yongkang Wong, Conrad Sanderson, Sandra Mau, Brian C. Lovell
While existing face recognition systems based on local features are robust to issues such as misalignment, they can exhibit accuracy degradation when comparing images of differing resolutions.
no code implementations • 4 Apr 2013 • Arnold Wiliem, Yongkang Wong, Conrad Sanderson, Peter Hobson, Shaokang Chen, Brian C. Lovell
In this paper, we propose a cell classification system comprised of a dual-region codebook-based descriptor, combined with the Nearest Convex Hull Classifier.
no code implementations • 3 Apr 2013 • Yongkang Wong, Shaokang Chen, Sandra Mau, Conrad Sanderson, Brian C. Lovell
In video based face recognition, face images are typically captured over multiple frames in uncontrolled conditions, where head pose, illumination, shadowing, motion blur and focus change over the sequence.
no code implementations • 12 Mar 2013 • Conrad Sanderson, Mehrtash T. Harandi, Yongkang Wong, Brian C. Lovell
In contrast to comparing faces via single exemplars, matching sets of face images increases robustness and discrimination performance.
no code implementations • 7 Mar 2013 • Yongkang Wong, Mehrtash T. Harandi, Conrad Sanderson
Thorough experiments on AR, FERET, exYaleB, BANCA and ChokePoint datasets show that the proposed local SR approach obtains considerably better and more robust performance than several previous state-of-the-art holistic SR methods, in both verification and closed-set identification problems.