AI Research Papers
Novel papers are one of the ways Qualcomm Technologies contributes impactful research to the larger community of AI research. Below are papers that Qualcomm AI Research has written or co-authored.
Computer vision
ActionBytes: Learning from Trimmed Videos to Localize Actions | CVPR 2020
End-to-End Lane Marker Detection via Row-wise Classification | CVPR 2020
Recognizing Compressed Videos: Challenges and Promises | ICCV 2019
Weakly-supervised Degree of Eye-Closeness Estimation | ICCV 2019
A Compact Deep Learning Model for Robust Facial Expression Recognition | CVPR 2018
Video2vec Embeddings Recognize Events when Examples are Scarce | IEEE 2017
Data compression and generative modeling
Lossy Compression with Distortion Constrained Optimization | CVPR 2020
Adversarial Distortion for Learned Video Compression | CVPR 2020
Feedback Recurrent Autoencoder | ICASSP 2020
Video Compression With Rate-Distortion Autoencoders | ICCV 2019
Recognizing Compressed Videos: Challenges and Promises | ICCV 2019
Machine learning fundamentals
Natural Graph Networks | NeurIPS 2020
Conditional Channel Gated Networks for Task-Aware Continual Learning | CVPR 2020
Gauge Equivariant Convolutional Networks and the Icosahedral CNN | ICML 2019
Batch-Shaping for Learning Conditional Channel Gated Networks | ICLR 2020
A General Theory of Equivariant CNNs on Homogeneous Spaces | NeurIPS 2019
3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data | NeurIPS 2018
Optimization and reinforcement learning
Power efficiency
Structured Convolutions for Efficient Neural Network Design | NeurIPS 2020
Bayesian Bits: Unifying Quantization and Pruning | NeurIPS 2020
A Data and Compute Efficient Design for Limited-Resources Deep Learning | ICLR 2020
LSQ+: Improving low-bit quantization through learnable offsets and better initialization | CVPR 2020
Conditional Channel Gated Networks for Task-Aware Continual Learning | CVPR 2020
Gradient l1 Regularization for Quantization Robustness | ICLR 2020
Batch-Shaping for Learning Conditional Channel Gated Networks | ICLR 2020
Data-Free Quantization through Weight Equalization and Bias Correction | ICCV 2019
Up or Down? Adaptive Rounding for Post-Training Quantization | ICML 2020
Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets | ICLR 2019
DAC: Data-free Automatic Acceleration of Convolutional Networks | WACV 2019
Relaxed Quantization for Discretized Neural Networks | ICLR 2019
Blended Coarse Gradient Descent for Full Quantization of Deep Neural Networks | RMS
A Quantization-Friendly Separable Convolution for MobileNets | EMC^2 2018
©2021 Qualcomm Technologies, Inc. and/or its affiliated companies.