no code implementations • 10 Mar 2024 • Guodong Ding, Hans Golong, Angela Yao
Data replay is a successful incremental learning technique for images.
no code implementations • 31 Jul 2023 • Guodong Ding, Fadime Sener, Shugao Ma, Angela Yao
Our framework constructs a knowledge base with spatial and temporal beliefs based on observed mistakes.
2 code implementations • 19 Oct 2022 • Guodong Ding, Fadime Sener, Angela Yao
Temporal action segmentation (TAS) in videos aims at densely identifying video frames in minutes-long videos with multiple action classes.
no code implementations • 18 Jul 2022 • Guodong Ding, Angela Yao
To this end, we propose two novel loss functions for the unlabelled data: an action affinity loss and an action continuity loss.
no code implementations • 13 Jul 2022 • Qingze Yin, GuanAn Wang, Guodong Ding, Qilei Li, Shaogang Gong, Zhenmin Tang
To strike a balance between the model accuracy and efficiency, we propose a novel Sub-space Consistency Regularization (SCR) algorithm that can speed up the ReID procedure by $0. 25$ times than real-value features under the same dimensions whilst maintaining a competitive accuracy, especially under short codes.
no code implementations • 20 Aug 2021 • Guodong Ding, Daniele Marazzina
In this work we analytically solve an optimal retirement problem, in which the agent optimally allocates the risky investment, consumption and leisure rate to maximise a gain function characterised by a power utility function of consumption and leisure, through the duality method.
no code implementations • 15 Aug 2021 • Guodong Ding, Angela Yao
Due to the lack of action-level supervision, we adopt the Hungarian matching algorithm to relate latent action prototypes to ground truth semantic classes for evaluation.
no code implementations • 29 Jun 2021 • Guodong Ding, Daniele Marazzina
In our framework, the agent is endowed by an initial debt, and she is required to repay her debt continuously.
1 code implementation • 4 Jun 2019 • Guodong Ding, Salman Khan, Zhenmin Tang, Jian Zhang, Fatih Porikli
With this insight, we design a novel Dispersion-based Clustering (DBC) approach which can discover the underlying patterns in data.
Ranked #19 on Unsupervised Person Re-Identification on Market-1501
no code implementations • 16 May 2018 • Guodong Ding, Shanshan Zhang, Salman Khan, Zhenmin Tang, Jian Zhang, Fatih Porikli
Our approach measures the affinity of unlabeled samples with the underlying clusters of labeled data samples using the intermediate feature representations from deep networks.
no code implementations • 20 Nov 2017 • Guodong Ding, Salman Khan, Zhenmin Tang, Fatih Porikli
Person re-identification aims at establishing the identity of a pedestrian from a gallery that contains images of multiple people obtained from a multi-camera system.