Scheduled Maintenance Notice
Please note that Researcher Profiles will be undergoing scheduled maintenance on Wednesday 7th Oct, from 8:00am to 9:00am. During this time, the Researcher Profiles system will be unavailable. We apologise for any inconvenience and appreciate your understanding.
Select Publications
Preprints
, 2021, 3D Skeleton-based Few-shot Action Recognition with JEANIE is not so Naïve, https://arxiv.org/abs/2112.12668v1
, 2021, Manifold Learning Benefits GANs, https://arxiv.org/abs/2112.12618v2
, 2021, Few-shot Keypoint Detection with Uncertainty Learning for Unseen Species, https://arxiv.org/abs/2112.06183v3
, 2021, Meta-Learning for Multi-Label Few-Shot Classification, https://arxiv.org/abs/2110.13494v1
, 2021, Simple Dialogue System with AUDITED, https://arxiv.org/abs/2110.11881v1
, 2021, Towards a Robust Differentiable Architecture Search under Label Noise, https://arxiv.org/abs/2110.12197v1
, 2021, High-order Tensor Pooling with Attention for Action Recognition, https://arxiv.org/abs/2110.05216v4
, 2021, REFINE: Random RangE FInder for Network Embedding, https://doi.org/10.1145/3459637.3482168
, 2021, Graph Convolutional Network with Generalized Factorized Bilinear Aggregation, https://arxiv.org/abs/2107.11666v1
, 2021, Predicting Flight Delay with Spatio-Temporal Trajectory Convolutional Network and Airport Situational Awareness Map, http://dx.doi.org/10.48550/arxiv.2105.08969
, 2020, Tensor Representations for Action Recognition, https://doi.org/10.1109/TPAMI.2021.3107160
, 2020, Power Normalizations in Fine-grained Image, Few-shot Image and Graph Classification, https://doi.org/10.1109/TPAMI.2021.3107164
, 2020, A Token-wise CNN-based Method for Sentence Compression, http://dx.doi.org/10.48550/arxiv.2009.11260
, 2020, Relation Embedding for Personalised POI Recommendation, http://dx.doi.org/10.48550/arxiv.2002.03461
, 2020, 6DoF Object Pose Estimation via Differentiable Proxy Voting Loss, https://arxiv.org/abs/2002.03923v2
, 2020, Self-supervising Action Recognition by Statistical Moment and Subspace Descriptors, https://doi.org/10.1145/3474085.3475572
, 2020, Few-shot Action Recognition with Permutation-invariant Attention, https://arxiv.org/abs/2001.03905v3
, 2020, Rethinking Class Relations: Absolute-relative Supervised and Unsupervised Few-shot Learning, https://arxiv.org/abs/2001.03919v4
, 2020, Improving Few-shot Learning by Spatially-aware Matching and CrossTransformer, https://arxiv.org/abs/2001.01600v2
, 2019, COLTRANE: ConvolutiOnaL TRAjectory NEtwork for Deep Map Inference, http://dx.doi.org/10.48550/arxiv.1909.11048
, 2019, A Comparative Review of Recent Kinect-based Action Recognition Algorithms, https://doi.org/10.1109/TIP.2019.2925285
, 2019, Hallucinating IDT Descriptors and I3D Optical Flow Features for Action Recognition with CNNs, https://arxiv.org/abs/1906.05910v2
, 2018, A Deeper Look at Power Normalizations, https://arxiv.org/abs/1806.09183v1
, 2018, Artwork Identification from Wearable Camera Images for Enhancing Experience of Museum Audiences, https://arxiv.org/abs/1806.09084v1
, 2018, CNN-based Action Recognition and Supervised Domain Adaptation on 3D Body Skeletons via Kernel Feature Maps, https://arxiv.org/abs/1806.09078v1
, 2018, Face Destylization, https://arxiv.org/abs/1802.01237v1
, 2018, Zero-Shot Kernel Learning, https://arxiv.org/abs/1802.01279v2
, 2018, Museum Exhibit Identification Challenge for Domain Adaptation and Beyond, https://arxiv.org/abs/1802.01093v1
, 2018, Identity-preserving Face Recovery from Portraits, https://arxiv.org/abs/1801.02279v2
, 2017, Higher-order Pooling of CNN Features via Kernel Linearization for Action Recognition, https://arxiv.org/abs/1701.05432v1
, 2016, Domain Adaptation by Mixture of Alignments of Second- or Higher-Order Scatter Tensors, https://arxiv.org/abs/1611.08195v2
, 2016, Tensor Representations via Kernel Linearization for Action Recognition from 3D Skeletons (Extended Version), https://arxiv.org/abs/1604.00239v2
, 2015, Dictionary Learning and Sparse Coding for Third-order Super-symmetric Tensors, https://arxiv.org/abs/1509.02970v1