Difference between revisions of "Resource:Previous Seminars"

From MobiNetS
Jump to: navigation, search
 
(3 intermediate revisions by 2 users not shown)
Line 1: Line 1:
=== History ===
=== History ===
====2024====
====2024====
 
{{Hist_seminar
|abstract = Video super-resolution (VSR) on mobile devices aims to restore high-resolution frames from their low-resolution counterparts, satisfying the requirements of performance, FLOPs and latency. On one hand, partial feature processing, as a classic and acknowledged strategy, is developed in current studies to reach an appropriate trade-off between FLOPs and accuracy. However, the splitting of partial feature processing strategy are usually performed in a blind manner, thereby reducing the computational efficiency and performance gains. On the other hand, current methods for mobile platforms primarily treat VSR as an extension of single-image super-resolution to reduce model calculation and inference latency. However, lacking inter-frame information interaction in current methods results in a suboptimal latency and accuracy trade-off. To this end, we propose a novel architecture, termed Feature Aggregating Network with Inter-frame Interaction (FANI), a lightweight yet considering frame-wise correlation VSR network, which could achieve real-time inference while maintaining superior performance. Our FANI accepts adjacent multi-frame low-resolution images as input and generally consists of several fully-connection-embedded modules, i.e., Multi-stage Partial Feature Distillation (MPFD) for capturing multi-level feature representations. Moreover, considering the importance of inter-frame alignment, we further employ a tiny Attention-based Frame Alignment (AFA) module to promote inter-frame information flow and aggregation efficiently. Extensive experiments on the well-known dataset and real-world mobile device demonstrate the superiority of our proposed FANI, which means that our FANI could be well adapted to mobile devices and produce visually pleasing results.
|confname = ICDM‘23
|link = https://ieeexplore.ieee.org/abstract/document/10415812
|title= Feature Aggregating Network with Inter-Frame Interaction for Efficient Video Super-Resolution
|speaker=Shuhong
|date=2024-10-25
}}
{{Hist_seminar
|abstract = The proliferation of edge devices has pushed computing from the cloud to the data sources, and video analytics is among the most promising applications of edge computing. Running video analytics is compute- and latency-sensitive, as video frames are analyzed by complex deep neural networks (DNNs) which put severe pressure on resource-constrained edge devices. To resolve the tension between inference latency and resource cost, we present Polly, a cross-camera inference system that enables co-located cameras with different but overlapping fields of views (FoVs) to share inference results between one another, thus eliminating the redundant inference work for objects in the same physical area. Polly’s design solves two basic challenges of cross-camera inference: how to identify overlapping FoVs automatically, and how to share inference results accurately across cameras. Evaluation on NVIDIA Jetson Nano with a real-world traffic surveillance dataset shows that Polly reduces the inference latency by up to 71.4% while achieving almost the same detection accuracy with state-of-the-art systems.
|confname= INFOCOM'23
|link = https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10229045
|title= Cross-Camera Inference on the Constrained Edge
|speaker=Xinyan
|date=2024-10-25
}}
{{Hist_seminar
|abstract = Smart cameras with on-device deep learning inference capabilities are enabling distributed video analytics at the data source without sending raw video data over the often unreliable and congested wireless network. However, how to unleash the full potential of the computing power of the camera network requires careful coordination among the distributed cameras, catering to the uneven workload distribution and the heterogeneous computing capabilities. This paper presents CrossVision, a distributed framework for real-time video analytics, that retains all video data on cameras while achieving low inference delay and high inference accuracy. The key idea behind CrossVision is that there is a significant information redundancy in the video content captured by cameras with overlapped Field-of-Views (FoVs), which can be exploited to reduce inference workload as well as improve inference accuracy between correlated cameras. CrossVision consists of three main components to realize its function: a Region-of-Interest (RoI) Matcher that discovers video content correlation based on a segmented FoV transformation scheme; a Workload Balancer that implements a randomized workload balancing strategy based on a bulk-queuing analysis, taking into account the cameras’ predicted future workload arrivals; an Accuracy Guard that ensures that the inference accuracy is not sacrificed as redundant information is discarded. We evaluate CrossVision in a hardware-augmented simulator and on real-world cross-camera datasets, and the results show that CrossVision is able to significantly reduce inference delay while improving the inference accuracy compared to a variety of baseline approaches.
|confname= TMC'24
|link = https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10202594
|title= CrossVision: Real-Time On-Camera Video Analysis via Common RoI Load Balancing
|speaker=Xinyan
|date=2024-10-25
}}
{{Hist_seminar
|abstract = LoRa is a promising technology that offers ubiquitous low-power IoT connectivity. With the features of multi-channel communication, orthogonal transmission, and spectrum sharing, LoRaWAN is poised to connect millions of IoT devices across thousands of logical channels. However, current LoRa gateways utilize hardwired Rx chains that cover only a small fraction (<1%) of the logical channels, limiting the potential for massive LoRa communications. This paper presents XGate, a novel gateway design that uses a single Rx chain to concurrently receive packets from all logical channels, fundamentally enabling scalable LoRa transmission and flexible network access. Unlike hardwired Rx chains in the current gateway design, XGate allocates resources including software-controlled Rx chains and demodulators based on the extracted meta information of incoming packets. XGate addresses a series of challenges to efficiently detect incoming packets without prior knowledge of their parameter configurations. Evaluations show that XGate boosts LoRa concurrent transmissions by 8.4× than state-of-the-art.
|confname=Mobicom' 24
|link = https://dl.acm.org/doi/pdf/10.1145/3636534.3649375
|title= Revolutionizing LoRa Gateway with XGate: Scalable Concurrent Transmission across Massive Logical Channels
|speaker=Chenkai
|date=2024-10-18
}}
{{Hist_seminar
|abstract = Deep learning training (DLT), e.g., large language model (LLM) training, has become one of the most important services in multitenant cloud computing. By deeply studying in-production DLT jobs, we observed that communication contention among different DLT jobs seriously influences the overall GPU computation utilization, resulting in the low efficiency of the training cluster. In this paper, we present Crux, a communication scheduler that aims to maximize GPU computation utilization by mitigating the communication contention among DLT jobs. Maximizing GPU computation utilization for DLT, nevertheless, is NP-Complete; thus, we formulate and prove a novel theorem to approach this goal by GPU intensity-aware communication scheduling. Then, we propose an approach that prioritizes the DLT flows with high GPU computation intensity, reducing potential communication contention. Our 96-GPU testbed experiments show that Crux improves 8.3% to 14.8% GPU computation utilization. The large-scale production trace-based simulation further shows that Crux increases GPU computation utilization by up to 23% compared with alternatives including Sincronia, TACCL, and CASSINI.
|confname=SIGCOMM' 24
|link = https://dl.acm.org/doi/pdf/10.1145/3651890.3672239
|title= Crux: GPU-Efficient Communication Scheduling for Deep Learning Training
|speaker=Youwei
|date=2024-10-18
}}
{{Hist_seminar
|abstract = Zero-shot object navigation is a challenging task for home-assistance robots. This task emphasizes visual grounding, commonsense inference and locomotion abilities, where the first two are inherent in foundation models. But for the locomotion part, most works still depend on map-based planning approaches. The gap between RGB space and map space makes it difficult to directly transfer the knowledge from foundation models to navigation tasks. In this work, we propose a Pixel-guided Navigation skill (PixNav), which bridges the gap between the foundation models and the embodied navigation task. It is straightforward for recent foundation models to indicate an object by pixels, and with pixels as the goal specification, our method becomes a versatile navigation policy towards all different kinds of objects. Besides, our PixNav is a pure RGB-based policy that can reduce the cost of homeassistance robots. Experiments demonstrate the robustness of the PixNav which achieves 80+% success rate in the local path-planning task. To perform long-horizon object navigation, we design an LLM-based planner to utilize the commonsense knowledge between objects and rooms to select the best waypoint. Evaluations across both photorealistic indoor simulators and real-world environments validate the effectiveness of our proposed navigation strategy.
|confname=ICRA' 24
|link = https://ieeexplore.ieee.org/document/10610499
|title= Bridging Zero-shot Object Navigation and Foundation Models through Pixel-Guided Navigation Skill
|speaker=Qinyong
|date=2024-10-11
}}
{{Hist_seminar
|abstract = Datacenter networks today provide best-effort delivery—messages may observe unpredictable queueing, delays, and drops due to switch buffer overflows within the network. Such weak guarantees reduce the set of assumptions that system designers can rely upon from the network, thus introducing inefficiency and complexity in host hardware and software. We present Harmony, a datacenter network architecture that provides powerful "congestion-free" message delivery guarantees—each message, once transmitted by the sender, observes bounded queueing at each switch in the network. Thus, network delays are bounded in failure-free scenarios, and congestion-related drops are completely eliminated. We establish, both theoretically and empirically, that Harmony provides such powerful guarantees with near-zero overheads compared to best-effort delivery networks: it incurs a tiny additive latency overhead that diminishes with message sizes, while achieving near-optimal network utilization.
|confname=NSDI' 24
|link = https://www.usenix.org/conference/nsdi24/presentation/agarwal-saksham
|title= Harmony: A Congestion-free Datacenter Architecture
|speaker=Junzhe
|date=2024-10-11
}}
{{Hist_seminar
{{Hist_seminar
|abstract = Overlapping cameras offer exciting opportunities to view a scene from different angles, allowing for more advanced, comprehensive and robust analysis. However, existing video analytics systems for multi-camera streams are mostly limited to (i) per-camera processing and aggregation and (ii) workload-agnostic centralized processing architectures. In this paper, we present Argus, a distributed video analytics system with cross-camera collaboration on smart cameras. We identify multi-camera, multi-target tracking as the primary task of multi-camera video analytics and develop a novel technique that avoids redundant, processing-heavy identification tasks by leveraging object-wise spatio-temporal association in the overlapping fields of view across multiple cameras. We further develop a set of techniques to perform these operations across distributed cameras without cloud support at low latency by (i) dynamically ordering the camera and object inspection sequence and (ii) flexibly distributing the workload across smart cameras, taking into account network transmission and heterogeneous computational capacities. Evaluation of three real-world overlapping camera datasets with two Nvidia Jetson devices shows that Argus reduces the number of object identifications and end-to-end latency by up to 7.13× and 2.19× (4.86× and 1.60× compared to the state-of-the-art), while achieving comparable tracking quality.
|abstract = Overlapping cameras offer exciting opportunities to view a scene from different angles, allowing for more advanced, comprehensive and robust analysis. However, existing video analytics systems for multi-camera streams are mostly limited to (i) per-camera processing and aggregation and (ii) workload-agnostic centralized processing architectures. In this paper, we present Argus, a distributed video analytics system with cross-camera collaboration on smart cameras. We identify multi-camera, multi-target tracking as the primary task of multi-camera video analytics and develop a novel technique that avoids redundant, processing-heavy identification tasks by leveraging object-wise spatio-temporal association in the overlapping fields of view across multiple cameras. We further develop a set of techniques to perform these operations across distributed cameras without cloud support at low latency by (i) dynamically ordering the camera and object inspection sequence and (ii) flexibly distributing the workload across smart cameras, taking into account network transmission and heterogeneous computational capacities. Evaluation of three real-world overlapping camera datasets with two Nvidia Jetson devices shows that Argus reduces the number of object identifications and end-to-end latency by up to 7.13× and 2.19× (4.86× and 1.60× compared to the state-of-the-art), while achieving comparable tracking quality.
Line 10: Line 65:
|date=2024-9-29
|date=2024-9-29
}}
}}
{{Hist_seminar
{{Hist_seminar
|abstract = We present FarfetchFusion, a fully mobile live 3D telepresence system. Enabling mobile live telepresence is a challenging problem as it requires i) realistic reconstruction of the user and ii) high responsiveness for immersive experience. We first thoroughly analyze the live 3D telepresence pipeline and identify three critical challenges: i) 3D data streaming latency and compression complexity, ii) computational complexity of volumetric fusion-based 3D reconstruction, and iii) inconsistent reconstruction quality due to sparsity of mobile 3D sensors. To tackle the challenges, we propose a disentangled fusion approach, which separates invariant regions and dynamically changing regions with our low-complexity spatio-temporal alignment technique, topology anchoring. We then design and implement an end-to-end system, which achieves realistic reconstruction quality comparable to existing server-based solutions while meeting the real-time performance requirements (<100 ms end-to-end latency, 30 fps throughput, <16 ms motion-to-photon latency) solely relying on mobile computation capability.
|abstract = We present FarfetchFusion, a fully mobile live 3D telepresence system. Enabling mobile live telepresence is a challenging problem as it requires i) realistic reconstruction of the user and ii) high responsiveness for immersive experience. We first thoroughly analyze the live 3D telepresence pipeline and identify three critical challenges: i) 3D data streaming latency and compression complexity, ii) computational complexity of volumetric fusion-based 3D reconstruction, and iii) inconsistent reconstruction quality due to sparsity of mobile 3D sensors. To tackle the challenges, we propose a disentangled fusion approach, which separates invariant regions and dynamically changing regions with our low-complexity spatio-temporal alignment technique, topology anchoring. We then design and implement an end-to-end system, which achieves realistic reconstruction quality comparable to existing server-based solutions while meeting the real-time performance requirements (<100 ms end-to-end latency, 30 fps throughput, <16 ms motion-to-photon latency) solely relying on mobile computation capability.
Line 19: Line 73:
|date=2024-9-29
|date=2024-9-29
}}
}}
{{Hist_seminar
{{Hist_seminar
|abstract = Increasing bandwidth demands of mobile video streaming pose a challenge in optimizing the Quality of Experience (QoE) for better user engagement. Multipath transmission promises to extend network capacity by utilizing multiple wireless links simultaneously. Previous studies mainly tune the packet scheduler in multipath transmission, expecting higher QoE by accelerating transmission. However, since Adaptive BitRate (ABR) algorithms overlook the impact of multipath scheduling on throughput prediction, multipath adaptive streaming can even experience lower QoE than single-path. This paper proposes Chorus, a cross-layer framework that coordinates multipath scheduling with adaptive streaming to optimize QoE jointly. Chorus establishes two-way feedback control loops between the server and the client. Furthermore, Chorus introduces Coarse-grained Decisions, which assist appropriate bitrate selection by considering the scheduling decision in throughput prediction, and Finegrained Corrections, which meet the predicted throughput by QoE-oriented multipath scheduling. Extensive emulation and real-world mobile Internet evaluations show that Chorus outperforms the state-of-the-art MPQUIC scheduler, improving average QoE by 23.5% and 65.7%, respectively.  
|abstract = Increasing bandwidth demands of mobile video streaming pose a challenge in optimizing the Quality of Experience (QoE) for better user engagement. Multipath transmission promises to extend network capacity by utilizing multiple wireless links simultaneously. Previous studies mainly tune the packet scheduler in multipath transmission, expecting higher QoE by accelerating transmission. However, since Adaptive BitRate (ABR) algorithms overlook the impact of multipath scheduling on throughput prediction, multipath adaptive streaming can even experience lower QoE than single-path. This paper proposes Chorus, a cross-layer framework that coordinates multipath scheduling with adaptive streaming to optimize QoE jointly. Chorus establishes two-way feedback control loops between the server and the client. Furthermore, Chorus introduces Coarse-grained Decisions, which assist appropriate bitrate selection by considering the scheduling decision in throughput prediction, and Finegrained Corrections, which meet the predicted throughput by QoE-oriented multipath scheduling. Extensive emulation and real-world mobile Internet evaluations show that Chorus outperforms the state-of-the-art MPQUIC scheduler, improving average QoE by 23.5% and 65.7%, respectively.  

Latest revision as of 11:46, 31 October 2024

History

2024

2023

2022

2021

2020

  • [Topic] [ The path planning algorithm for multiple mobile edge servers in EdgeGO], Rong Cong, 2020-11-18

2019

2018

2017

Instructions

请使用Latest_seminar和Hist_seminar模板更新本页信息.

    • 修改时间和地点信息
    • 将当前latest seminar部分的code复制到这个页面中
    • 将{{Latest_seminar... 修改为 {{Hist_seminar...，并增加对应的日期信息|date=
    • 填入latest seminar各字段信息
    • link请务必不要留空，如果没有link则填本页地址 https://mobinets.org/index.php?title=Resource:Seminar
  • 格式说明
    • Latest_seminar:

{{Latest_seminar
|confname=
|link=
|title=
|speaker=
}}

    • Hist_seminar

{{Hist_seminar
|confname=
|link=
|title=
|speaker=
|date=
}}

Retrieved from "http://mobinets.cn/site/index.php?title=Resource:Previous_Seminars&oldid=3213"