Representation Learning

Sparse Deep Learning: A New Framework Immune to Local Traps and Miscalibration NeurIPS 2021 Sparse encoding for more-interpretable feature-selecting representations in probabilistic matrix factorization ICLR 2021 Sparsely Changing Latent States for Prediction and Planning in Partially Observable Domains NeurIPS 2021 Sparse R-CNN: End-to-End Object Detection With Learnable Proposals CVPR 2021 Spatial Assembly Networks for Image Representation Learning CVPR 2021 Spatially-Invariant Style-Codes Controlled Makeup Transfer CVPR 2021 Spatial-Temporal Sequential Hypergraph Network for Crime Prediction with Dynamic Multiplex Relation Learning IJCAI 2021 Spatial-Temporal Transformer for Dynamic Scene Graph Generation ICCV 2021 Spatio-Temporal Dynamic Inference Network for Group Activity Recognition ICCV 2021 Spatiotemporal Graph Neural Network based Mask Reconstruction for Video Object Segmentation AAAI 2021 Spatio-Temporal Representation Factorization for Video-Based Person Re-Identification ICCV 2021 Spatio-Temporal Self-Supervised Representation Learning for 3D Point Clouds ICCV 2021 Speaker Embeddings by Modeling Channel-Wise Correlations Interspeech 2021 Speaker Normalization Using Joint Variational Autoencoder Interspeech 2021 SpecRec: An Alternative Solution for Improving End-to-End Speech-to-Text Translation via Spectrogram Reconstruction Interspeech 2021 Spectro-Temporal Deep Features for Disordered Speech Assessment and Recognition Interspeech 2021 Speech2Talking-Face: Inferring and Driving a Face with Synchronized Audio-Visual Representation IJCAI 2021 Speechformer: Reducing Information Loss in Direct Speech Translation EMNLP 2021 Speech Separation Using an Asynchronous Fully Recurrent Convolutional Neural Network NeurIPS 2021 SpellBERT: A Lightweight Pretrained Model for Chinese Spelling Check EMNLP 2021 Spine2Net: SpineNet with Res2Net and Time-Squeeze-and-Excitation Blocks for Speaker Recognition Interspeech 2021 SPIN: Structure-Preserving Inner Offset Network for Scene Text Recognition AAAI 2021 Split then Refine: Stacked Attention-guided ResUNets for Blind Single Image Visible Watermark Removal AAAI 2021 Spot the Difference: Detection of Topological Changes via Geometric Alignment NeurIPS 2021 SSMF: Shifting Seasonal Matrix Factorization NeurIPS 2021