How ACLNet Boosts Skeleton-Based Action Recognition with Affinity Contrastive Learning

ACLNet, an Affinity Contrastive Learning Network introduced by researchers from the Chinese Academy of Sciences, BUPT and Moonshot AI, tackles the ambiguity of skeleton‑based human activity recognition by modeling inter‑class structural similarities and intra‑class margins, achieving state‑of‑the‑art results on NTU‑RGB+D, Kinetics‑Skeleton, FineGYM and other benchmarks.

affinity contrastive learninggraph convolutional networkhuman activity analysis

0 likes · 11 min read

How ACLNet Boosts Skeleton-Based Action Recognition with Affinity Contrastive Learning

Kuaishou Tech

May 24, 2021 · Artificial Intelligence

BCNet: A Bilayer Instance Segmentation Network for Occlusion‑Aware Object Detection

The paper proposes BCNet, a lightweight bilayer instance segmentation network that explicitly models occluder and occludee relationships by treating each region of interest as two overlapping layers, achieving significant performance gains on COCO, COCOA and KINS datasets under heavy occlusion.

Computer VisionDeep Learningbilayer network

0 likes · 10 min read

BCNet: A Bilayer Instance Segmentation Network for Occlusion‑Aware Object Detection

Kuaishou Audio & Video Technology

May 21, 2021 · Artificial Intelligence

How BCNet Tackles Occlusion in Instance Segmentation with a Dual‑Layer GCN

The article introduces BCNet, a lightweight dual‑layer instance segmentation network that models images as overlapping occluder and occludee layers, enabling effective handling of heavy object occlusion and achieving significant performance gains on COCO, COCOA and KINS datasets compared to existing methods.

graph convolutional networkinstance segmentationocclusion handling

0 likes · 11 min read

How BCNet Tackles Occlusion in Instance Segmentation with a Dual‑Layer GCN

Amap Tech

Sep 24, 2020 · Artificial Intelligence

Hybrid Spatio‑Temporal Graph Convolutional Network for Precise Traffic Prediction

At the 2020 Yunqi Conference, Amap’s senior algorithm expert presented the Hybrid Spatio‑Temporal Graph Convolutional Network, which leverages massive real‑time navigation data to estimate future traffic flow, transform it into travel‑time features, and outperform prior models, enabling proactive congestion avoidance and dynamic traffic‑scheduling for millions of users.

AIHSTGCNSmart Mobility

0 likes · 11 min read

Hybrid Spatio‑Temporal Graph Convolutional Network for Precise Traffic Prediction

Amap Tech

Jun 24, 2020 · Artificial Intelligence

Hybrid Spatio-Temporal Graph Convolutional Network (H‑STGCN) for Traffic Forecasting

The Hybrid Spatio‑Temporal Graph Convolutional Network (H‑STGCN) integrates planned traffic flow from navigation data via a domain transformer and a compound adjacency matrix, enabling graph‑based spatio‑temporal modeling that consistently outperforms baselines in real‑world traffic forecasting and reduces severe ETA errors.

Deep LearningH‑STGCNSpatio-temporal modeling

0 likes · 17 min read

Hybrid Spatio-Temporal Graph Convolutional Network (H‑STGCN) for Traffic Forecasting

JD Tech

Aug 14, 2018 · Artificial Intelligence

GCN‑LSTM Image Captioning Model by JD AI Research Institute

JD AI Research Institute presented a GCN‑LSTM encoder‑decoder system that integrates object semantic and spatial relationships via graph convolutional networks to significantly improve image captioning performance on the COCO benchmark, achieving state‑of‑the‑art results.

COCO datasetImage CaptioningLSTM

0 likes · 7 min read

GCN‑LSTM Image Captioning Model by JD AI Research Institute