| 1. |
- 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
|
|
| 2. |
- 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).
|
|
| 3. |
- Bickham, S., et al.
(författare)
-
Low cutoff G.657-compatible fiber for data center interconnects operating in the 1064 and 1310 nm windows
- 2020
-
Ingår i: Proceedings of SPIE - The International Society for Optical Engineering. - : SPIE. - 0277-786X .- 1996-756X. ; 11286
-
Konferensbidrag (refereegranskat)abstract
- Optical interconnects in data centers have traditionally used 850 nm GaAs-based vertical-cavity surface-emitting lasers (VCSELs) in combination with multimode fiber, having a reach up to 100 m in length. Longer links typically use standard single-mode fiber in conjunction with either InP-based edge-emitting lasers or silicon photonic transmitters operating in the 1310 nm or 1550 nm window. Single-mode GaAs-based VCSELs operating at 1064 nm offer another path for achieving longer system reach. Potential advantages of these VCSELs include better power efficiency, modulation speeds reaching 50 Gbps and large-scale fabrication volumes. The longer wavelength is also beneficial due to the lower attenuation and chromatic dispersion of optical fibers at that wavelength. However, one practical issue for single-mode transmission is that the G.657 standard for single-mode fiber requires that the 22-meter cable cutoff wavelength be less than 1260 nm, and these fibers are typically few-moded at 1064 nm. The large differences between the group velocities of the LP01 and LP11 modes can lead to degradation of the system performance due to multi-path interference if the higher order modes are present. To resolve this quandary, we have designed and validated the performance of a new optical fiber which is single-moded at wavelengths less than 1064 nm, but also has G.657-compliant mode field diameter and dispersion characteristics that enable it to be used in the 1310 nm window.
|
|
| 4. |
- Huang, Yiqian, et al.
(författare)
-
A Novel Maximum Distance Separable Code Based RIS-OFDM : Design and Optimization
- 2022
-
Ingår i: 2022 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM 2022). - : Institute of Electrical and Electronics Engineers (IEEE). ; , s. 1521-1526
-
Konferensbidrag (refereegranskat)abstract
- In this paper, we propose a novel maximum distance separable (MDS) code based and reconfigurable intelligent surface (RIS) assisted wireless communication system with orthogonal frequency division multiplexing (OFDM). Specifically, input bits are firstly divided into groups and their MDS codes are utilized to decide the amplitudes and phases of subcarriers. The introduction of the MDS code helps to increase the minimum Hamming distance between symbols and improve on the capability of error detection. Besides, the RIS is adopted to create additional paths between the radio frequency (RF) and the receiver as well as alter the signal phases with derived optimal solution. Benefiting from the strength of the RIS, the proposed system can better overcome multipath fading compared with conventional systems. Simulation results are presented to demonstrate the efficacy of the proposed system in terms of reducing bit error rate (BER) through multipath channels.
|
|
| 5. |
- Lu, Xin, et al.
(författare)
-
A generic and modularized Digital twin enabled human-robot collaboration
- 2022
-
Ingår i: Proceedings 2022 IEEE International Conference on e-Business Engineering ICEBE 2022. - : IEEE. - 9781665492447 - 9781665492454 ; , s. 66-73
-
Konferensbidrag (refereegranskat)abstract
- Recently, the manufacturing paradigm shifts from mass production to mass customization, which results in urgently demands for the development of intelligent, flexible and automatic manufacturing systems for handling complex manufacturing tasks with high efficiency. The use of collaborative robots, an essential enabling technology for developing human-robot collaboration (HRC), is on the rise for human-centric intelligent automation design. An effective virtual simulation platform, which can continuously simulate and evaluate HRC performance in different working scenarios, is lacking in developing an HRC system in a sophisticated industrial arena. This paper presents a generic and modularized digital twin enabled HRC framework based on the synergy effect of human, robotic and environment-related factors to provide a flexible, compatible, re-configurable solution to ease the implementation of HRC in the real world. The feasibility of the proposed framework is validated through the practical implementation of a food packaging job, which involves a human operator and an ABB robotic arm collaboratively working together, on an industrial shop.
|
|
| 6. |
- Wang, Zicun, et al.
(författare)
-
Intelligent Beam Training with Deep Convolutional Neural Network in mmWave Communications
- 2022
-
Ingår i: 2022 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM 2022). - : Institute of Electrical and Electronics Engineers (IEEE). ; , s. 1223-1228
-
Konferensbidrag (refereegranskat)abstract
- Highly directional beams in millimeter wave (mmWave) communications necessitate beam training or alignment between the access point (AP) and the user equipment (UE), and exhausted beam search (EBS) method is suggested in the current 3GPP standard. Nevertheless, EBS suffers from high overheads and inevitably lowers the throughput, especially when the beam space is large. In this paper, we utilize the spatial correlation among different beams as well as the strong feature extraction/representation capability of the deep convolutional neural network (CNN), and propose an intelligent beam training algorithm. With the proposed method, the AP can probe only a fixed subset of the whole beam space and identify the optimal beam intelligently. Simulation results show that, the proposed method can largely reduce the overheads for the beam training meanwhile boost the throughput performance compared with the state of the arts.
|
|
