English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Skeleton-based Graph Convolutional Networks (GCNs) models for actionrecognition have achieved excellent prediction accuracy in the field. However,limited by large model and computation complexity, GCNs for action recognitionlike 2s-AGCN have insufficient power-efficiency and throughput on GPU. Thus,the demand of model reduction and hardware acceleration for low-power GCNsaction recognition application becomes continuously higher.  To address challenges above, this paper proposes a runtime sparse featurecompress accelerator with hybrid pruning method: RFC-HyPGCN. First, this methodskips both graph and spatial convolution workloads by reorganizing themultiplication order. Following spatial convolution workloads channel-pruningdataflow, a coarse-grained pruning method on temporal filters is designed,together with sampling-like fine-grained pruning on time dimension. Later, wecome up with an architecture where all convolutional layers are mapped on chipto pursue high throughput. To further reduce storage resource utilization,online sparse feature compress format is put forward. Features are divided andencoded into several banks according to presented format, then bank storage issplit into depth-variable mini-banks. Furthermore, this work appliesquantization, input-skipping and intra-PE dynamic data scheduling to acceleratethe model. In experiments, proposed pruning method is conducted on 2s-AGCN,acquiring 3.0x-8.4x model compression ratio and 73.20\% graph-skippingefficiency with balancing weight pruning. Implemented on Xilinx XCKU-115 FPGA,the proposed architecture has the peak performance of 1142 GOP/s and achievesup to 9.19x and 3.91x speedup over high-end GPU NVIDIA 2080Ti and NVIDIA V100,respectively. Compared with latest accelerator for action recognition GCNsmodels, our design reaches 22.9x speedup and 28.93\% improvement on DSPefficiency.

RFC-HyPGCN: A Runtime Sparse Feature Compress Accelerator for Skeleton-Based GCNs Action Recognition Model with Hybrid Pruning