no code implementations • 13 Apr 2024 • Jiyang Li, Lechao Cheng, Zhangye Wang, Tingting Mu, Jingxuan He
In this paper, inspired by significant progress in the field of novel view synthesis (NVS) achieved by 3D Gaussian Splatting (3D-GS), we propose LoopGaussian to elevate cinemagraph from 2D image space to 3D space using 3D Gaussian modeling.
no code implementations • 27 Mar 2024 • Yusuf Sulehman, Tingting Mu
We prove an upper-bound on the Lipschitz constant of the larger block in terms of the Lipschitz constants of the smaller blocks.
1 code implementation • 14 Dec 2023 • Jingxuan He, Lechao Cheng, Chaowei Fang, Zunlei Feng, Tingting Mu, Mingli Song
Building upon this, we introduce a complementary self-enhancement method that constrains the semantic consistency between these confident regions and an augmented image with the same class labels.
Weakly supervised Semantic Segmentation Weakly-Supervised Semantic Segmentation
1 code implementation • CVPR 2023 • Zhicai Wang, Yanbin Hao, Tingting Mu, Ouxiang Li, Shuo Wang, Xiangnan He
It is well-known that zero-shot learning (ZSL) can suffer severely from the problem of domain shift, where the true and learned data distributions for the unseen classes do not match.
no code implementations • 22 Feb 2023 • Yian Deng, Tingting Mu
The proposed algorithm exhibits improved computational speed and convergence behavior compared to a large set of state-of-the-art Riemannian optimization algorithms.
1 code implementation • 10 Jan 2023 • Danny Wood, Tingting Mu, Andrew Webb, Henry Reeve, Mikel Luján, Gavin Brown
We present a theory of ensemble diversity, explaining the nature of diversity for a wide range of supervised learning scenarios.
no code implementations • 6 Oct 2022 • H. Rhys Jones, Tingting Mu, Andrei C. Popescu, Yusuf Sulehman
Each of these methods have seen widespread use in the field of machine learning, however, here we apply them specifically to surrogate machine learning model development.
1 code implementation • 15 Jul 2022 • Zhicai Wang, Yanbin Hao, Xingyu Gao, Hao Zhang, Shuo Wang, Tingting Mu, Xiangnan He
They use token-mixing layers to capture cross-token interactions, as opposed to the multi-head self-attention mechanism used by Transformers.
no code implementations • 26 Apr 2022 • Danny Wood, Tingting Mu, Gavin Brown
We introduce a novel bias-variance decomposition for a range of strictly convex margin losses, including the logistic loss (minimized by the classic LogitBoost algorithm), as well as the squared margin loss and canonical boosting loss.
no code implementations • 19 Sep 2021 • Mirantha Jayathilaka, Tingting Mu, Uli Sattler
The approach consists of two components - converting symbolic knowledge of an ontology into continuous space by learning n-ball embeddings that capture properties of subsumption and disjointness, and guiding the training and inference of a vision model using the learnt embeddings.
no code implementations • 21 Sep 2020 • Mirantha Jayathilaka, Tingting Mu, Uli Sattler
With respect to both standard and zero-shot image classification, our approach shows superior performance compared with the original approach, which uses word embeddings.
no code implementations • 2 Sep 2020 • Alessio Sarullo, Tingting Mu
We propose a loss function with the aim of distilling the knowledge contained in the graph into the model, while also using the graph to regularise learnt representations by imposing a local structure on the latent space.
1 code implementation • NAACL 2019 • Maolin Li, Arvid Fahlström Myrman, Tingting Mu, Sophia Ananiadou
It can automatically estimate the per-instance reliability of each annotator and the correct label for each instance.
no code implementations • 20 Mar 2019 • Alessio Sarullo, Tingting Mu
In this paper we investigate the problems of class imbalance and irrelevant relationships in Visual Relationship Detection (VRD).
no code implementations • 17 Nov 2018 • Haoxin Ma, Haotian Li, Zhiwen Qian, Shengxian Shi, Tingting Mu
The precise combination of image sensor and micro-lens array enables lenslet light field cameras to record both angular and spatial information of incoming light, therefore, one can calculate disparity and depth from light field images.
no code implementations • EACL 2017 • Motoki Sato, Austin J. Brockmeier, Georgios Kontonatsios, Tingting Mu, John Y. Goulermas, Jun{'}ichi Tsujii, Sophia Ananiadou
Descriptive document clustering aims to automatically discover groups of semantically related documents and to assign a meaningful label to characterise the content of each cluster.