SwePub
Sök i SwePub databas

  Utökad sökning

Träfflista för sökning "WFRF:(Zhou Qi) ;mspu:(conferencepaper)"

Sökning: WFRF:(Zhou Qi) > Konferensbidrag

  • Resultat 1-10 av 21
Sortera/gruppera träfflistan
   
NumreringReferensOmslagsbildHitta
1.
  • Kristanl, Matej, et al. (författare)
  • The Seventh Visual Object Tracking VOT2019 Challenge Results
  • 2019
  • Ingår i: 2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW). - : IEEE COMPUTER SOC. - 9781728150239 ; , s. 2206-2241
  • Konferensbidrag (refereegranskat)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).
  •  
2.
  • Chang, Qi, et al. (författare)
  • DeepRecon : Joint 2D Cardiac Segmentation and 3D Volume Reconstruction via a Structure-Specific Generative Method
  • 2022
  • Ingår i: Medical Image Computing and Computer Assisted Intervention – MICCAI 2022 - 25th International Conference, Proceedings. - Cham : Springer Nature Switzerland. - 1611-3349 .- 0302-9743. - 9783031164392 ; 13434 LNCS, s. 567-577
  • Konferensbidrag (refereegranskat)abstract
    • Joint 2D cardiac segmentation and 3D volume reconstruction are fundamental in building statistical cardiac anatomy models and understanding functional mechanisms from motion patterns. However, due to the low through-plane resolution of cine MR and high inter-subject variance, accurately segmenting cardiac images and reconstructing the 3D volume are challenging. In this study, we propose an end-to-end latent-space-based framework, DeepRecon, that generates multiple clinically essential outcomes, including accurate image segmentation, synthetic high-resolution 3D image, and 3D reconstructed volume. Our method identifies the optimal latent representation of the cine image that contains accurate semantic information for cardiac structures. In particular, our model jointly generates synthetic images with accurate semantic information and segmentation of the cardiac structures using the optimal latent representation. We further explore downstream applications of 3D shape reconstruction and 4D motion pattern adaptation by the different latent-space manipulation strategies. The simultaneously generated high-resolution images present a high interpretable value to assess the cardiac shape and motion. Experimental results demonstrate the effectiveness of our approach on multiple fronts including 2D segmentation, 3D reconstruction, downstream 4D motion pattern adaption performance.
  •  
3.
  • Kristan, Matej, et al. (författare)
  • The Sixth Visual Object Tracking VOT2018 Challenge Results
  • 2019
  • Ingår i: Computer Vision – ECCV 2018 Workshops. - Cham : Springer Publishing Company. - 9783030110086 - 9783030110093 ; , s. 3-53
  • Konferensbidrag (refereegranskat)abstract
    • The Visual Object Tracking challenge VOT2018 is the sixth annual tracker benchmarking activity organized by the VOT initiative. Results of over eighty 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 and a “real-time” experiment simulating a situation where a tracker processes images as if provided by a continuously running sensor. A long-term tracking subchallenge has been introduced to the set of standard VOT sub-challenges. The new subchallenge focuses on long-term tracking properties, namely coping with target disappearance and reappearance. A new dataset has been compiled and a performance evaluation methodology that focuses on long-term tracking capabilities has been adopted. The VOT toolkit has been updated to support both standard short-term and the new long-term tracking subchallenges. 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 (http://votchallenge.net).
  •  
4.
  •  
5.
  • Ansari, Farhan, et al. (författare)
  • Cellulose nanocomposites - Controlling dispersion and material properties through nanocellulose surface modification
  • 2015
  • Ingår i: 20th International Conference on Composite Materials, ICCM 2015. - : International Committee on Composite Materials.
  • Konferensbidrag (refereegranskat)abstract
    • The use of cellulosic nanofibers as reinforcement in polymer composites offers great advantages over their petroleum counterparts. Apart from being strong, stiff and low density; they are obtained from naturally occurring resources and as such are favorable from an environmental point of view. A major problem while studying nanomaterials is their tendency to agglomerate, thus leading to inhomogeneous distribution within the polymer matrix. This often results in stress concentrations in the matrix rich regions when the material is subjected to load and therefore, limits the potential application of these materials. A common approach to circumvent this is by surface modification, which facilitates the dispersion in non-polar matrices. An environmental friendly approach, inspired by clay chemistry, was used to functionalize the CNC surface. It was shown that the CNC could be modified in a rather convenient way to attach a variety of functional groups on the surface. Primarily, the problem of cellulose nanocrystal (CNC) distribution in a hydrophobic polymer matrix is investigated. Composites prepared from modified CNC were studied and compared with unmodified CNC. The distribution of the CNC is carefully monitored at different stages via UV-Vis spectroscopy and scanning electron microscopy (SEM). The mechanical properties of the resulting materials were characterized by dynamic mechanical as well as uniaxial tensile tests. It was shown that a homogeneous distribution of the CNC exposes a tremendous amount of surface area to interact with the matrix. In such a case, the stress transfer is much more efficient and perhaps, the matrix behavior is modified, which leads to significant improvements in the mechanical properties.
  •  
6.
  • Bhat, Goutam, et al. (författare)
  • NTIRE 2022 Burst Super-Resolution Challenge
  • 2022
  • Ingår i: 2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW 2022). - : IEEE. - 9781665487399 - 9781665487405 ; , s. 1040-1060
  • Konferensbidrag (refereegranskat)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.
  •  
7.
  • Cukurova, Mutlu, et al. (författare)
  • Modelling Collaborative Problem-solving Competence with Transparent Learning Analytics : Is Video Data Enough?
  • 2020
  • Ingår i: LAK20. - New York, NY, USA : Association for Computing Machinery (ACM). ; , s. 270-275
  • Konferensbidrag (refereegranskat)abstract
    • In this study, we describe the results of our research to model collaborative problem-solving (CPS) competence based on analytics generated from video data. We have collected similar to 500 mins video data from 15 groups of 3 students working to solve design problems collaboratively. Initially, with the help of OpenPose, we automatically generated frequency metrics such as the number of the face-in-the-screen; and distance metrics such as the distance between bodies. Based on these metrics, we built decision trees to predict students' listening, watching, making, and speaking behaviours as well as predicting the students' CPS competence. Our results provide useful decision rules mined from analytics of video data which can be used to inform teacher dashboards. Although, the accuracy and recall values of the models built are inferior to previous machine learning work that utilizes multimodal data, the transparent nature of the decision trees provides opportunities for explainable analytics for teachers and learners. This can lead to more agency of teachers and learners, therefore can lead to easier adoption. We conclude the paper with a discussion on the value and limitations of our approach.
  •  
8.
  • Gehrmann, Sebastian, et al. (författare)
  • GEMv2: Multilingual NLG Benchmarking in a Single Line of Code
  • 2022
  • Ingår i: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. - : Association for Computational Linguistics (ACL). ; , s. 266-281
  • Konferensbidrag (refereegranskat)abstract
    • Evaluations in machine learning rarely use the latest metrics, datasets, or human evaluation in favor of remaining compatible with prior work. The compatibility, often facilitated through leaderboards, thus leads to outdated but standardized evaluation practices. We pose that the standardization is taking place in the wrong spot. Evaluation infrastructure should enable researchers to use the latest methods and what should be standardized instead is how to incorporate these new evaluation advances.We introduce GEMv2, the new version of the Generation, Evaluation, and Metrics Benchmark which uses a modular infrastructure for dataset, model, and metric developers to benefit from each other’s work. GEMv2 supports 40 documented datasets in 51 languages, ongoing online evaluation for all datasets, and our interactive tools make it easier to add new datasets to the living benchmark.
  •  
9.
  • Geng, Shiyu, et al. (författare)
  • Aligned biodegradable cellulose-reinforced nanocomposites with high strength and toughness
  • 2017
  • Konferensbidrag (refereegranskat)abstract
    • Cellulose, as the most abundant component in wood, has attracted a lot of attention for utilizing it in environmentally-friendly applications to replace the fossil-based materials. Nanocellulose materials with high stiffness and strength, large surface area and biodegradability, are promising reinforcement in polymers. However, the energy consumption of nano-scale isolation of cellulose and the dispersion of nanocellulose materials in the polymers are still challenging for obtaining low-cost and ultra-strong nanocomposites. To overcome these, we focus on investigating the aligned nanocomposites reinforced by a very low cellulose nanofibers (CNF) content (0.1 wt%), and grafting polyethylene glycol (PEG) on CNF was performed to improve the dispersion of them. We found that the alignment can improve mechanical properties of the polylactic acid (PLA)/CNF composites dramatically. With a draw ratio of 8, the strength of the aligned composite reached 320 MPa and the toughness was 30 times enhanced compared to the isotropic material. Much better dispersion of the CNF grafted with PEG in PLA matrix was confirmed by scanning electron microscopy (SEM) compared to the ungrafted CNF, and further supported by the mechanical testing results. Furthermore, the aligned nanocomposites exhibited light scattering behavior indicating they have the potential to be used in optical applications.
  •  
10.
  • Geng, Shiyu, et al. (författare)
  • Aligned polylactic acid based nanocomposite reinforced using a tiny amount of functionalized cellulose nanofibers
  • 2018
  • Konferensbidrag (refereegranskat)abstract
    • Due to the challenges of the cost of nanocellulose materials and the dispersion of them in polymer matrix, small amount and well-dispersed nanocellulose materials are desired as reinforcement to achieve environmentally-friendly nanocomposites with high performance. In this study, an aligned polylactic acid (PLA) based nanocomposite reinforced by 0.1 wt% of functionalized cellulose nanofibers (CNFs) was investigated. The CNFs were covalently grafted by polyethylene glycol (PEG), which improves the dispersion of the CNFs in the PLA significantly compared to the native CNFs. The improved dispersion was examined by scanning electron microscopy (SEM), polarized optical microscopy (POM) and mechanical testing. Furthermore, it was found that the alignment can improve mechanical properties of the nanocomposite dramatically. The strength of the aligned nanocomposite reaches 343 MPa with a draw ratio of 8, meanwhile the toughness is about 30 times enhanced compared to the isotropic material. The aligned nanocomposite also exhibits light scattering behavior, indicating that it has the potential to be used in optical applications.
  •  
Skapa referenser, mejla, bekava och länka
  • Resultat 1-10 av 21

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

 
pil uppåt Stäng

Kopiera och spara länken för att återkomma till aktuell vy