SwePub
Sök i SwePub databas

  Utökad sökning

Träfflista för sökning "WFRF:(He Keji) "

Sökning: WFRF:(He Keji)

  • Resultat 1-2 av 2
Sortera/gruppera träfflistan
   
NumreringReferensOmslagsbildHitta
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.
  • Liu, Ziye, et al. (författare)
  • MicroInfer : An Edge Deep-Learning Inference Framework for Industry IoT
  • 2022
  • Ingår i: AIIOT 2022 - Proceedings of the 2022 1st Workshop on Digital Twin and Edge AI for Industrial IoT, Part of MobiCom 2022. - New York, NY, USA : Association for Computing Machinery (ACM). ; , s. 13-18
  • Konferensbidrag (refereegranskat)abstract
    • To address the difficult deployment, high memory overhead, and poor portability of edge deep learning frameworks in industry IoT, we propose MicroInfer which is an edge deep learning inference framework for Microprocessors. MicroInfer employs a combination of upper computer and lower computer architecture. The upper computer automatically implements model quantization, model precompilation, operator matching, and code generation, estimates in advance the memory overhead and inference acceleration scheme required on the lower computer chip, and automatically generates a customized AI plug-in. The lower computer utilize an improved memory management strategy to execute the algorithm with as little memory space as possible without affecting the inference speed. A custom XidianOS operating system for microprocessors is also designed for MicroInfer, and the AI framework is designed to support various AI inference frameworks. The proposed MicroInfer is compared with other inference frameworks, achieving significant improvements in memory usage and inference speed, accelerating the development of industry IoT.
  •  
Skapa referenser, mejla, bekava och länka
  • Resultat 1-2 av 2

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