| 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. |
- Kristan, Matej, et al.
(författare)
-
The first visual object tracking segmentation VOTS2023 challenge results
- 2023
-
Ingår i: 2023 IEEE/CVF International conference on computer vision workshops (ICCVW). - : Institute of Electrical and Electronics Engineers Inc.. - 9798350307443 - 9798350307450 ; , s. 1788-1810
-
Konferensbidrag (refereegranskat)abstract
- The Visual Object Tracking Segmentation VOTS2023 challenge is the eleventh annual tracker benchmarking activity of the VOT initiative. This challenge is the first to merge short-term and long-term as well as single-target and multiple-target tracking with segmentation masks as the only target location specification. A new dataset was created; the ground truth has been withheld to prevent overfitting. New performance measures and evaluation protocols have been created along with a new toolkit and an evaluation server. Results of the presented 47 trackers indicate that modern tracking frameworks are well-suited to deal with convergence of short-term and long-term tracking and that multiple and single target tracking can be considered a single problem. A leaderboard, with participating trackers details, the source code, the datasets, and the evaluation kit are publicly available at the challenge website1
|
|
| 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. |
- Kristan, Matej, et al.
(författare)
-
The Ninth Visual Object Tracking VOT2021 Challenge Results
- 2021
-
Ingår i: 2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2021). - : IEEE COMPUTER SOC. - 9781665401913 ; , s. 2711-2738
-
Konferensbidrag (refereegranskat)abstract
- The Visual Object Tracking challenge VOT2021 is the ninth annual tracker benchmarking activity organized by the VOT initiative. Results of 71 trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in recent years. The VOT2021 challenge was composed of four sub-challenges focusing on different tracking domains: (i) VOT-ST2021 challenge focused on short-term tracking in RGB, (ii) VOT-RT2021 challenge focused on "real-time" short-term tracking in RGB, (iii) VOT-LT2021 focused on long-term tracking, namely coping with target disappearance and reappearance and (iv) VOT-RGBD2021 challenge focused on long-term tracking in RGB and depth imagery. The VOT-ST2021 dataset was refreshed, while VOT-RGBD2021 introduces a training dataset and sequestered dataset for winner identification. The source code for most of the trackers, the datasets, the evaluation kit and the results along with the source code for most trackers are publicly available at the challenge website(1).
|
|
| 5. |
- Aamodt, K., et al.
(författare)
-
Alignment of the ALICE Inner Tracking System with cosmic-ray tracks
- 2010
-
Ingår i: Journal of Instrumentation. - 1748-0221. ; 5
-
Konferensbidrag (refereegranskat)abstract
- ALICE (A Large Ion Collider Experiment) is the LHC (Large Hadron Collider) experiment devoted to investigating the strongly interacting matter created in nucleus-nucleus collisions at the LHC energies. The ALICE ITS, Inner Tracking System, consists of six cylindrical layers of silicon detectors with three different technologies; in the outward direction: two layers of pixel detectors, two layers each of drift, and strip detectors. The number of parameters to be determined in the spatial alignment of the 2198 sensor modules of the ITS is about 13,000. The target alignment precision is well below 10 mu m in some cases (pixels). The sources of alignment information include survey measurements, and the reconstructed tracks from cosmic rays and from proton-proton collisions. The main track-based alignment method uses the Millepede global approach. An iterative local method was developed and used as well. We present the results obtained for the ITS alignment using about 10(5) charged tracks from cosmic rays that have been collected during summer 2008, with the ALICE solenoidal magnet switched off.
|
|
| 6. |
- Xu, Lei, et al.
(författare)
-
Quantized Distributed Nonconvex Optimization with Linear Convergence
- 2022
-
Ingår i: 2022 IEEE 61ST CONFERENCE ON DECISION AND CONTROL (CDC). - : IEEE. ; , s. 5837-5842
-
Konferensbidrag (refereegranskat)abstract
- This paper considers distributed nonconvex optimization for minimizing the average of local cost functions, by using local information exchange over undirected communication networks. Since the communication channels often have limited bandwidth or capacity, we first introduce a quantization rule and an encoder/decoder scheme to reduce the transmission bits. By integrating them with a distributed algorithm, we then propose a distributed quantized nonconvex optimization algorithm. Assuming the global cost function satisfies the Polyak-Lojasiewicz condition, which does not require the global cost function to be convex and the global minimizer is not necessarily unique, we show that the proposed algorithm linearly converges to a global optimal point. Moreover, a low data rate is shown to be sufficient to ensure linear convergence when the algorithm parameters are properly chosen. The theoretical results are illustrated by numerical simulation examples.
|
|
| 7. |
- Chen, Kun-Chih (Jimmy), et al.
(författare)
-
NoC-based DNN Accelerator: A Future Design Paradigm
- 2019
-
Ingår i: Proceedings of the 13th IEEE/ACM International Symposium on Networks-on-Chip, NOCS 2019. - New York, NY, USA : Association for Computing Machinery (ACM). - 9781450367004
-
Konferensbidrag (refereegranskat)abstract
- Deep Neural Networks (DNN) have shown significant advantagesin many domains such as pattern recognition, prediction, and controloptimization. The edge computing demand in the Internet-of-Things era has motivated many kinds of computing platforms toaccelerate the DNN operations. The most common platforms areCPU, GPU, ASIC, and FPGA. However, these platforms suffer fromlow performance (i.e., CPU and GPU), large power consumption(i.e., CPU, GPU, ASIC, and FPGA), or low computational flexibilityat runtime (i.e., FPGA and ASIC). In this paper, we suggest theNoC-based DNN platform as a new accelerator design paradigm.The NoC-based designs can reduce the off-chip memory accessesthrough a flexible interconnect that facilitates data exchange betweenprocessing elements on the chip. We first comprehensivelyinvestigate conventional platforms and methodologies used in DNNcomputing. Then we study and analyze different design parametersto implement the NoC-based DNN accelerator. The presentedaccelerator is based on mesh topology, neuron clustering, randommapping, and XY-routing. The experimental results on LeNet, MobileNet,and VGG-16 models show the benefits of the NoC-basedDNN accelerator in reducing off-chip memory accesses and improvingruntime computational flexibility.
|
|
| 8. |
- Desjardins, Kewin, et al.
(författare)
-
Characterization of a back-illuminated CMOS camera for soft x-ray coherent scattering
- 2019
-
Ingår i: Proceedings of the 13th International Conference on Synchrotron Radiation Instrumentation, SRI 2018. - : Author(s). - 9780735417823 ; 2054
-
Konferensbidrag (refereegranskat)abstract
- A commercial scientific camera has been adapted and characterized at the SOLEIL Synchrotron with the aim to improve the acquisition capabilities on the soft X-ray coherent scattering experimental station at SEXTANTS beamline. This device is equipped by the last generation of back side illuminated scientific CMOS (BSI-sCMOS) of 2048 by 2048 pixels of 11 μm2 able to acquire low noise images with a frame rate up to 48 Hz. The camera's performance measurements have been done and shows a good level of readout noise, a large full-well capacity, a medium dark current and a good homogeneity, respectively, 1.6 e- rms (in High Gain mode), 80 000 e- (in Low Gain mode),<5 e-/pixel/s and ∼ 1%. The quantum efficiency (QE) measurement has been performed at the soft x-ray branch of the METROLOGIE beamline and gives a relatively good agreement with the expected theoretical values. Finally, the demonstration of the camera's efficiency and of the gain in useful time measurement related to the high frame rate have been performed with a series of Airy patterns images compared with an image recorded using the standard BSI-CDD already in operation at the SEXTANTS beamline.
|
|
| 9. |
- Ding, Yi, 1992, et al.
(författare)
-
Construct Validity and Measurement Invariance of Mathematics Self-Efficacy and Self-Concept in Swedish PISA 2003 and 2012
- 2021
-
Ingår i: World Education Research Association (WERA) Virtual Focal Meeting. - Santiago de Compostela, Spain.
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- A large amount of research has shown that individuals’ beliefs in their ability have a major impact on their actions in different situations (Bandura, 1986; Marsh et al., 2018; Usher & Pajares, 2006). According to Bandura (1986), students’ self-related beliefs plays a vital role in their academic achievements. Self-belief of competence is a broad conception which involves several facets and constructs, among which, self-efficacy and self-concept have been given considerable attention (Bong & Skaalvik, 2003; Lee, 2009; Marsh, 1987; Shavelson et al., 1976). According to Bong and Skaalvik (2003), both self-efficacy and self-concept can contribute to the prediction of academic performance. Students with different self-beliefs demonstrate different level of cognitive engagement as well as well-being in school (Bong & Skaalvik, 2003). Self-efficacy refers to one’s thoughts and belief in the self’s capability, which is built through previous experiences. According to Bandura’s (1986) social cognitive theory, self-efficacy captures the one’s belief in his or her competence on a specific task or process. Mathematics self-efficacy (MSE) in Programme for International Student Assessment (PISA) is a measure of student’s expectation and conviction of what can be accomplished when they need to solve pure and applied mathematics tasks. The students are asked to report on their perceived ability by responses whether they feel confident, confident, not very confident or not at all confident towards "using a train timetable", "calculating TV discount", "calculating square metres of tiles" etc (OECD, 2012). Self-concept is generally defined as one’s perception of his- or herself, which is established through experiences as well as interpretations of social atmosphere and with reference with their peers (Rosenberg, 1979; Marsh, 1987; Parker et al., 2014). It refers to general perception of the competence to a subject matter but not linked to specific tasks in that subject. Mathematics self-concept (MSC) in PISA is constructed index based on students’ responses about their perceived competence in mathematics, whether they strongly agree, agree, disagree or strongly disagree with the statements towards "get good grades", "learn quickly", "not good at math", etc (OECD, 2012). The aim of the study is two-fold. First, to evaluate construct validity of mathematics self-efficacy and self-concept as measured in PISA through exploring the measurement property of these constructs. Second, to examine measurement invariance of mathematics self-efficacy and self-concept scales over time. Data on Swedish students participating in PISA 2003 and PISA 2012 was used, which consists of 4624 and 4736 students respectively.
|
|
| 10. |
- Ding, Yi, 1992, et al.
(författare)
-
Examining the Role of Students’ Mathematics Self-concept and Self-efficacy in Mathematics Achievement in Sweden over Time: A Multigroup Multilevel Analysis
- 2022
-
Ingår i: The European Conference on Educational Research (ECER), 2022, Yerevan (online).
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- Mathematics, as one of the mandatory and key school subjects worldwide, plays a vital role in equipping young people with mathematical knowledge and skills and preparing them not only for higher education but also for later private and professional life in modern society. Previous research has established that student self-concept and self-efficacy could predict and impact academic achievement (Bong & Skaalvik, 2003; Multon et al., 1991). It has also been observed for many decades that student gender, socioeconomic status and immigration background influence academic achievement, directly and indirectly (Bondy et al., 2017; Leder, 1992; Tate, 1997; White, 1982). By using data from the Programme for International Student Assessment (PISA), it is possible not only to analyse the relationships among students’ characteristics, self-related constructs and academic achievement but also review to what extent differences in these relationships are conditioned across the Swedish educational system and over time. The main aim of the study was to investigate the relative importance of student mathematics self-concept and self-efficacy for mathematics achievement in Sweden.
|
|
