arXiv Computer Science @arxiv_cs@qoto.org

GPLA-12: An Acoustic Signal Dataset of Gas Pipeline Leakage. (arXiv:2106.10277v1 [eess.AS]) http://arxiv.org/abs/2106.10277

Say Their Names: Resurgence in the collective attention toward Black victims of fatal police violence following the death of George Floyd. (arXiv:2106.10281v1 [cs.SI]) http://arxiv.org/abs/2106.10281

Dependency Structure Misspecification in Multi-Source Weak Supervision Models. (arXiv:2106.10302v1 [cs.LG]) http://arxiv.org/abs/2106.10302

Multi-Task Learning for User Engagement and Adoption in Live Video Streaming Events. (arXiv:2106.10305v1 [cs.AI]) http://arxiv.org/abs/2106.10305

Deep Learning for Intelligent Wireless MAC: Exploiting Real Data Sampled on 2.4GHz Frequency Band. (arXiv:2106.10307v1 [cs.IT]) http://arxiv.org/abs/2106.10307

Towards Single Stage Weakly Supervised Semantic Segmentation. (arXiv:2106.10309v1 [cs.CV]) http://arxiv.org/abs/2106.10309

Verifying Safe Transitions between Dynamic Motion Primitives on Legged Robots. (arXiv:2106.10310v1 [cs.RO]) http://arxiv.org/abs/2106.10310

Universal Rate-Distortion-Perception Representations for Lossy Compression. (arXiv:2106.10311v1 [cs.IT]) http://arxiv.org/abs/2106.10311

Differentiable Particle Filtering without Modifying the Forward Pass. (arXiv:2106.10314v1 [stat.ML]) http://arxiv.org/abs/2106.10314

Machining Cycle Time Prediction: Data-driven Modelling of Machine Tool Feedrate Behavior with Neural Networks. (arXiv:2106.09719v1 [cs.LG]) http://arxiv.org/abs/2106.09719

DeepLab2: A TensorFlow Library for Deep Labeling. (arXiv:2106.09748v1 [cs.CV]) http://arxiv.org/abs/2106.09748

Optimizing robotic swarm based construction tasks. (arXiv:2106.09749v1 [cs.RO]) http://arxiv.org/abs/2106.09749

Towards Real-Time Routing Optimization with Deep Reinforcement Learning: Open Challenges. (arXiv:2106.09754v1 [cs.NI]) http://arxiv.org/abs/2106.09754

PyKale: Knowledge-Aware Machine Learning from Multiple Sources in Python. (arXiv:2106.09756v1 [cs.LG]) http://arxiv.org/abs/2106.09756

CIRA Guide to Custom Loss Functions for Neural Networks in Environmental Sciences -- Version 1. (arXiv:2106.09757v1 [cs.LG]) http://arxiv.org/abs/2106.09757

Discovering Relationships between Object Categories via Universal Canonical Maps. (arXiv:2106.09758v1 [cs.CV]) http://arxiv.org/abs/2106.09758

Synthetic COVID-19 Chest X-ray Dataset for Computer-Aided Diagnosis. (arXiv:2106.09759v1 [eess.IV]) http://arxiv.org/abs/2106.09759

Multi-mode Transformer Transducer with Stochastic Future Context. (arXiv:2106.09760v1 [eess.AS]) http://arxiv.org/abs/2106.09760

Unsupervised Resource Allocation with Graph Neural Networks. (arXiv:2106.09761v1 [cs.LG]) http://arxiv.org/abs/2106.09761

On the training of sparse and dense deep neural networks: less parameters, same performance. (arXiv:2106.09021v1 [cs.LG]) http://arxiv.org/abs/2106.09021