Continual semantic segmentation via image and latent space consistency by Wang, Zhichao

“…In this thesis, my continual-learning research process is introduced in detail, including a novel method and two regulators, which contribute to anti-forgetting Result in continual learning in the semantic segmentation area. Firstly a real-time semantic segmentation model called ERFnet is evaluated, then based on this network and Cityscapes dataset, a model-recall method is proposed which could significantly reduce the catastrophic forgetting which happens in the process of continual learning in the semantic segmentation area; inspired by mentors, 2 regulators are also conducted which were expected to further improve performance (one regulator is come up by mentors and another is by myself). …”
Get full text

Segmentation and analysis of cement particles in cement paste with deep learning by Qian, Hanjie, Li, Ye, Yang, Jianfei, Xie, Lihua, Tan, Kang Hai

Subjects: Get full text

Segment anything: real-time AI model interaction and visualization by Wang, Jingwei

Subjects: Get full text

The Japanese economy in crises : a time series segmentation study by Cheong, Siew Ann, Fornia, Robert Paulo, Lee, Gladys Hui Ting, Kok, Jun Liang, Yim, Woei Shyr, Xu, Danny Yuan, Zhang, Yiting

“…The authors performed a comprehensive time series segmentation study on the 36 Nikkei Japanese industry indices from 1 January 1996 to 11 June 2010. …”
Get full text
Get full text

3D-aware instance segmentation and tracking in egocentric videos by Bhalgat, Y, Tschernezki, V, Laina, I, Henriques, JF, Vedaldi, A, Zisserman, A

“…Leveraging our tracked instance segmentations, we showcase downstream applications in 3D object reconstruction and amodal video object segmentation in these egocentric settings.…”

Humanising GrabCut: learning to segment humans using the Kinect by Gulshan, V, Lempitsky, V, Zisserman, A

“…To this end we investigate learning to automatically segment humans from cluttered images (without depth information) given a bounding box. …”

Placing objects in context via inpainting for out-of-distribution segmentation by De Jorge, P, Volpi, R, Dokania, PK, Torr, PHS, Rogez, G

“…When deploying a semantic segmentation model into the real world, it will inevitably encounter semantic classes that were not seen during training. …”

Using multiple segmentations to discover objects and their extent in image collections by Russell, BC, Efros, AA, Sivic, J, Freeman, WT, Zisserman, A

“…Given a large dataset of images, we seek to automatically determine the visually similar object and scene classes together with their image segmentation. To achieve this we combine two ideas: (i) that a set of segmented objects can be partitioned into visual object classes using topic discovery models from statistical text analysis; and (ii) that visual object classes can be used to assess the accuracy of a segmentation. …”

DiffuSeg: domain-driven diffusion for medical image segmentation by Zhang, L, Wu, F, Bronik, K, Papiez, BW

“…Initially, we apply our method to the MNIST dataset and subsequently adapt it for use with medical image segmentation datasets, such as retinal fundus images for vessel segmentation and MRI images for heart segmentation. …”

Empowerment or Reinforcement of Gender Regime: Rethinking Social Enterprises’ Intentions and Impact through Gender Lens by Tymosiewicz, Natalia Elizabeth

Get full text

Response time characterization of Organic Rankine Cycle evaporators for dynamic regime analysis with fluctuating load by Jiménez-Arreola, Manuel, Wieland, Christoph, Romagnoli, Alessandro

Get full text
Get full text

Constructing Convex Inner Approximations of Steady-State Security Regions by Nguyen, Hung D., Dvijotham, Krishnamurthy, Turitsyn, Konstantin

“…It establishes a certificate for the self-mapping of a polytope region constructed around a given feasible operating point. …”
Get full text

Rain attenuation prediction model for satellite communications in tropical regions by Yeo, Jun Xiang, Lee, Yee Hui, Ong, Jin Teong

“…Results show that although three of these models have relatively good prediction capability for the tropical region, they could be improved. Therefore, in this paper, a slant path rain attenuation model suitable for the tropical region is proposed. …”
Get full text
Get full text

Video data mining using configurations of viewpoint invariant regions by Sivic, J, Zisserman, A

Learning to detect cells using non-overlapping extremal regions by Arteta, C, Lempitsky, V, Noble, JA, Zisserman, A

“…The method consists of three steps: first, a set of candidate cell-like regions is identified. Then, each candidate region is evaluated using a statistical model of the cell appearance. …”

Conference report: authoritative speech in the Himalayan region by Mazard, Mireille

“…The conference included papers on both the Nepalese and Tibeto-Burman oral traditions of the Himalayan region, including Nepal itself, Tibet, Northern India, and Southwest China.…”
Get full text

Region of interest in images using tagged information by Meena C.

“…Besides that, different regions of an image can be indicated with different tags and this idea is being employed in the methodology covered in our project. …”
Get full text

Is regional shopping in Singapore a viable concept? by Chick, Yuet Fun, Lal, Christina, Lim, Bee Leng

“…The emergence of regional/sub-regional shopping centres in the suburban parts of Singapore marks a milestone in the retail industry. …”
Get full text

Cloud detection and attenuation modelling in tropical region by Yuan, Feng

“…The improved model incorporates precipitable water vapor (PWV) value to estimate integrated liquid water content (ILWC), and then determine the cloud attenuation for the tropical region. From the analysis of 2 year radiosonde data from 8 cites in the tropical region, the results show that the ILWC along the path can be approximated by a power function relationship with the PWV. …”
Get full text

Regional planning situation report on Sri Lanka by Morapaya, R. B.

Get full text
Get full text