1. |
- Bhat, Goutam, et al.
(author)
-
NTIRE 2022 Burst Super-Resolution Challenge
- 2022
-
In: 2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW 2022). - : IEEE. - 9781665487399 - 9781665487405 ; , s. 1040-1060
-
Conference paper (peer-reviewed)abstract
- Burst super-resolution has received increased attention in recent years due to its applications in mobile photography. By merging information from multiple shifted images of a scene, burst super-resolution aims to recover details which otherwise cannot be obtained using a simple input image. This paper reviews the NTIRE 2022 challenge on burst super-resolution. In the challenge, the participants were tasked with generating a clean RGB image with 4x higher resolution, given a RAW noisy burst as input. That is, the methods need to perform joint denoising, demosaicking, and super-resolution. The challenge consisted of 2 tracks. Track 1 employed synthetic data, where pixel-accurate high-resolution ground truths are available. Track 2 on the other hand used real-world bursts captured from a handheld camera, along with approximately aligned reference images captured using a DSLR. 14 teams participated in the final testing phase. The top performing methods establish a new state-of-the-art on the burst super-resolution task.
|
|
2. |
- Chen, Jialin, et al.
(author)
-
Characterization and comparison of post-natal rat Achilles tendon-derived stem cells at different development stages
- 2016
-
In: Scientific Reports. - : Springer Science and Business Media LLC. - 2045-2322. ; 6
-
Journal article (peer-reviewed)abstract
- Tendon stem/progenitor cells (TSPCs) are a potential cell source for tendon tissue engineering. The striking morphological and structural changes of tendon tissue during development indicate the complexity of TSPCs at different stages. This study aims to characterize and compare post-natal rat Achilles tendon tissue and TSPCs at different stages of development. The tendon tissue showed distinct differences during development: the tissue structure became denser and more regular, the nuclei became spindle-shaped and the cell number decreased with time. TSPCs derived from 7 day Achilles tendon tissue showed the highest self-renewal ability, cell proliferation, and differentiation potential towards mesenchymal lineage, compared to TSPCs derived from 1 day and 56 day tissue. Microarray data showed up-regulation of several groups of genes in TSPCs derived from 7 day Achilles tendon tissue, which may account for the unique cell characteristics during this specific stage of development. Our results indicate that TSPCs derived from 7 day Achilles tendon tissue is a superior cell source as compared to TSPCs derived from 1 day and 56 day tissue, demonstrating the importance of choosing a suitable stem cell source for effective tendon tissue engineering and regeneration.
|
|
3. |
- Chen, Jialin, et al.
(author)
-
Fos Promotes Early Stage Teno-Lineage Differentiation of Tendon Stem/Progenitor Cells in Tendon
- 2017
-
In: Stem Cells Translational Medicine. - : John Wiley & Sons. - 2157-6564 .- 2157-6580. ; 6:11, s. 2009-2019
-
Journal article (peer-reviewed)abstract
- Stem cells have been widely used in tendon tissue engineering. The lack of refined and controlled differentiation strategy hampers the tendon repair and regeneration. This study aimed to find new effective differentiation factors for stepwise tenogenic differentiation. By microarray screening, the transcript factor Fos was found to be expressed in significantly higher amounts in postnatal Achilles tendon tissue derived from 1 day as compared with 7-days-old rats. It was further confirmed that expression of Fos decreased with time in postnatal rat Achilles tendon, which was accompanied with the decreased expression of multiply tendon markers. The expression of Fos also declined during regular in vitro cell culture, which corresponded to the loss of tendon phenotype. In a cell-sheet and a three-dimensional cell culture model, the expression of Fos was upregulated as compared with in regular cell culture, together with the recovery of tendon phenotype. In addition, significant higher expression of tendon markers was found in Fos-overexpressed tendon stem/progenitor cells (TSPCs), and Fos knock-down gave opposite results. In situ rat tendon repair experiments found more normal tendon-like tissue formed and higher tendon markers expression at 4 weeks postimplantation of Fos-overexpressed TSPCs derived nonscaffold engineering tendon (cell-sheet), as compared with the control group. This study identifies Fos as a new marker and functional driver in the early stage teno-lineage differentiation of tendon, which paves the way for effective stepwise tendon differentiation and future tendon regeneration.
|
|
4. |
- Kristanl, Matej, et al.
(author)
-
The Seventh Visual Object Tracking VOT2019 Challenge Results
- 2019
-
In: 2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW). - : IEEE COMPUTER SOC. - 9781728150239 ; , s. 2206-2241
-
Conference paper (peer-reviewed)abstract
- The Visual Object Tracking challenge VOT2019 is the seventh annual tracker benchmarking activity organized by the VOT initiative. Results of 81 trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in the recent years. The evaluation included the standard VOT and other popular methodologies for short-term tracking analysis as well as the standard VOT methodology for long-term tracking analysis. The VOT2019 challenge was composed of five challenges focusing on different tracking domains: (i) VOT-ST2019 challenge focused on short-term tracking in RGB, (ii) VOT-RT2019 challenge focused on "real-time" short-term tracking in RGB, (iii) VOT-LT2019 focused on long-term tracking namely coping with target disappearance and reappearance. Two new challenges have been introduced: (iv) VOT-RGBT2019 challenge focused on short-term tracking in RGB and thermal imagery and (v) VOT-RGBD2019 challenge focused on long-term tracking in RGB and depth imagery. The VOT-ST2019, VOT-RT2019 and VOT-LT2019 datasets were refreshed while new datasets were introduced for VOT-RGBT2019 and VOT-RGBD2019. The VOT toolkit has been updated to support both standard short-term, long-term tracking and tracking with multi-channel imagery. Performance of the tested trackers typically by far exceeds standard baselines. The source code for most of the trackers is publicly available from the VOT page. The dataset, the evaluation kit and the results are publicly available at the challenge website(1).
|
|