Techniques

DocQueryNet: Value Retrieval with Arbitrary Queries for Form-like Documents COLING 2022 Do Current Multi-Task Optimization Methods in Deep Learning Even Help? NeurIPS 2022 Do Deep Neural Nets Display Human-like Attention in Short Answer Scoring? NAACL 2022 Domain Adaptation for Time Series Forecasting via Attention Sharing ICML 2022 Domain Generalization with Relaxed Instance Frequency-wise Normalization for Multi-device Acoustic Scene Classification Interspeech 2022 Don't Pour Cereal into Coffee: Differentiable Temporal Logic for Temporal Action Segmentation NeurIPS 2022 Do We Need Anisotropic Graph Neural Networks? ICLR 2022 DRAGONN: Distributed Randomized Approximate Gradients of Neural Networks ICML 2022 DropCov: A Simple yet Effective Method for Improving Deep Architectures NeurIPS 2022 DropMix: A Textual Data Augmentation Combining Dropout with Mixup EMNLP 2022 Dual Attention Networks for Few-Shot Fine-Grained Recognition AAAI 2022 Dual Decomposition of Convex Optimization Layers for Consistent Attention in Medical Images ICML 2022 Dynamic Dual-Output Diffusion Models CVPR 2022 Dynamic Iterative Refinement for Efficient 3D Hand Pose Estimation WACV 2022 Dynamic Nonlinear Mixup with Distance-based Sample Selection COLING 2022 Dynamic Scene Graph Generation via Anticipatory Pre-Training CVPR 2022 Dynamic Spatial Propagation Network for Depth Completion AAAI 2022 DynamicTOC: Persona-based Table of Contents for Consumption of Long Documents NAACL 2022 Dynamic Token Normalization improves Vision Transformers ICLR 2022 E2EC: An End-to-End Contour-Based Method for High-Quality High-Speed Instance Segmentation CVPR 2022 Early-Bird GCNs: Graph-Network Co-optimization towards More Efficient GCN Training and Inference via Drawing Early-Bird Lottery Tickets AAAI 2022 Easy-First Bottom-Up Discourse Parsing via Sequence Labelling COLING 2022 EcoFormer: Energy-Saving Attention with Linear Complexity NeurIPS 2022 EdgeFormer: A Parameter-Efficient Transformer for On-Device Seq2seq Generation EMNLP 2022 EENAS: An Efficient Evolutionary Algorithm for Neural Architecture Search ACML 2022