| 1. |
- Kristan, M., et al.
(författare)
-
The Eighth Visual Object Tracking VOT2020 Challenge Results
- 2020
-
Ingår i: Computer Vision. - Cham : Springer International Publishing. - 9783030682378 ; , s. 547-601
-
Konferensbidrag (refereegranskat)abstract
- The Visual Object Tracking challenge VOT2020 is the eighth annual tracker benchmarking activity organized by the VOT initiative. Results of 58 trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in the recent years. The VOT2020 challenge was composed of five sub-challenges focusing on different tracking domains: (i) VOT-ST2020 challenge focused on short-term tracking in RGB, (ii) VOT-RT2020 challenge focused on “real-time” short-term tracking in RGB, (iii) VOT-LT2020 focused on long-term tracking namely coping with target disappearance and reappearance, (iv) VOT-RGBT2020 challenge focused on short-term tracking in RGB and thermal imagery and (v) VOT-RGBD2020 challenge focused on long-term tracking in RGB and depth imagery. Only the VOT-ST2020 datasets were refreshed. A significant novelty is introduction of a new VOT short-term tracking evaluation methodology, and introduction of segmentation ground truth in the VOT-ST2020 challenge – bounding boxes will no longer be used in the VOT-ST challenges. A new VOT Python toolkit that implements all these novelites was introduced. 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 ).
|
|
| 2. |
|
|
| 3. |
|
|
| 4. |
|
|
| 5. |
- Ding, Z., et al.
(författare)
-
Effects of electrode contact on geometry structure and transport properties of the graphene-based nanomolecule devices
- 2010
-
Ingår i: INEC 2010 - 2010 3rd International Nanoelectronics Conference, Proceedings. - : IEEE. - 9781424435432 ; , s. 217-218
-
Konferensbidrag (refereegranskat)abstract
- A series of graphene-based nanomolecule devices are constructed by connecting the graphene nanodot to two Au electrodes through different bond length between the electrodes and molecules. The geometric structure and electronic properties are studied by using density functional theory calculations. Basing on the optimized structure, we calculate the quantum conductance of the system by using the Green's function method. We find that the geometry structures of the molecule and the transport properties are sensitive to the bond length dAu-H. The plane of carbon atoms increasingly bends with the decrease of the dAu-H. The ISD-V SD curves have the same threshold value under different d Au-H.
|
|
| 6. |
|
|
| 7. |
|
|
| 8. |
- Fu, Z., et al.
(författare)
-
Experimental Study on Machine Learning with Approximation to Data Streams
- 2019
-
Ingår i: 2019 6th International Conference on Internet of Things. - : Institute of Electrical and Electronics Engineers Inc.. - 9781728129495 ; , s. 561-566
-
Konferensbidrag (refereegranskat)abstract
- Realtime transferring of data streams enables many data analytics and machine learning applications in the areas of e.g. massive IoT and industrial automation. Big data volume of those streams is a significant burden or overhead not only to the transportation network, but also to the corresponding application servers. Therefore, researchers and scientists focus on reducing the amount of data needed to be transferred via data compressions and approximations. However, how to do data compression and approximation is highly dependent on the corresponding applications. In this paper, we did a study on the impact of data approximation to the machine learning applications. In particular, from the experimental perspective, we show the tradeoff among the approximation error bound, compression ratio and the prediction accuracy of multiple machine learning methods. We believe that, with proper choice, data approximation can dramatically reduce the amount of data transferred with limited impact on the machine learning applications.
|
|
| 9. |
- Jiang, M., et al.
(författare)
-
Performance analysis of a photovoltaics aided coal-fired power plant
- 2019
-
Ingår i: Energy Procedia. - : Elsevier Ltd. - 1876-6102. ; , s. 1348-1353
-
Konferensbidrag (refereegranskat)abstract
- In this article, integration of photovoltaics (PV) into a coal-fired power plant was proposed. The performance including economic analysis and environmental impact was conducted by a case study in the northwest area of China. The results show that the PV system can replace part of auxiliary power consumption using renewable electricity to reduce internal power consumption and the emissions. Due to the feature of the integration into a power plant, the curtailment of solar PV electricity does not occur compared to stand-alone PV system. The investment cost, operation and maintenance (O&M) expenditure were feasible compared with other PV power generation plants.
|
|
| 10. |
- Jiang, Tao, et al.
(författare)
-
Understanding the behavior of in-memory computing workloads
- 2014
-
Ingår i: IISWC 2014 - IEEE International Symposium on Workload Characterization. - 9781479964536 ; , s. 22-30
-
Konferensbidrag (refereegranskat)abstract
- © 2014 IEEE. The increasing demands of big data applications have led researchers and practitioners to turn to in-memory computing to speed processing. For instance, the Apache Spark framework stores intermediate results in memory to deliver good performance on iterative machine learning and interactive data analysis tasks. To the best of our knowledge, though, little work has been done to understand Spark's architectural and microarchitectural behaviors. Furthermore, although conventional commodity processors have been well optimized for traditional desktops and HPC, their effectiveness for Spark workloads remains to be studied. To shed some light on the effectiveness of conventional generalpurpose processors on Spark workloads, we study their behavior in comparison to those of Hadoop, CloudSuite, SPEC CPU2006, TPC-C, and DesktopCloud. We evaluate the benchmarks on a 17-node Xeon cluster. Our performance results reveal that Spark workloads have significantly different characteristics from Hadoop and traditional HPC benchmarks. At the system level, Spark workloads have good memory bandwidth utilization (up to 50%), stable memory accesses, and high disk IO request frequency (200 per second). At the microarchitectural level, the cache and TLB are effective for Spark workloads, but the L2 cache miss rate is high. We hope this work yields insights for chip and datacenter system designers.
|
|
