| Rethinking Visual Geo-localization for Large-Scale Applications | Apr 5, 2022 | Contrastive Learninggeo-localization | CodeCode Available | 2 |
| iSDF: Real-Time Neural Signed Distance Fields for Robot Perception | Apr 5, 2022 | Continual LearningDenoising | CodeCode Available | 2 |
| Region Rebalance for Long-Tailed Semantic Segmentation | Apr 5, 2022 | SegmentationSemantic Segmentation | CodeCode Available | 2 |
| Text2LIVE: Text-Driven Layered Image and Video Editing | Apr 5, 2022 | Video Editing | CodeCode Available | 2 |
| From implicit learning to explicit representations | Apr 5, 2022 | | CodeCode Available | 2 |
| BatchFormerV2: Exploring Sample Relationships for Dense Representation Learning | Apr 4, 2022 | image-classificationImage Classification | CodeCode Available | 2 |
| Do As I Can, Not As I Say: Grounding Language in Robotic Affordances | Apr 4, 2022 | Decision MakingLanguage Modeling | CodeCode Available | 2 |
| MultiMAE: Multi-modal Multi-task Masked Autoencoders | Apr 4, 2022 | Depth Estimationimage-classification | CodeCode Available | 2 |
| BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimation | Apr 3, 2022 | DecoderDepth Estimation | CodeCode Available | 2 |
| Data Cards: Purposeful and Transparent Dataset Documentation for Responsible AI | Apr 3, 2022 | | CodeCode Available | 2 |
| AdaFace: Quality Adaptive Margin for Face Recognition | Apr 3, 2022 | Face RecognitionFace Recognition (Closed-Set) | CodeCode Available | 2 |
| Style-Based Global Appearance Flow for Virtual Try-On | Apr 3, 2022 | Virtual Try-on | CodeCode Available | 2 |
| SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image | Apr 2, 2022 | NeRFNovel View Synthesis | CodeCode Available | 2 |
| Distributional Gradient Boosting Machines | Apr 2, 2022 | Prediction Intervalsregression | CodeCode Available | 2 |
| Multi-Class Road User Detection With 3+1D Radar in the View-of-Delft Dataset | Apr 1, 2022 | 3D Object DetectionBenchmarking | CodeCode Available | 2 |
| Interpretable RNA Foundation Model from Unannotated Data for Highly Accurate RNA Structure and Function Predictions | Apr 1, 2022 | Self-Supervised Learning | CodeCode Available | 2 |
| VQF: Highly Accurate IMU Orientation Estimation with Bias Estimation and Magnetic Disturbance Rejection | Mar 31, 2022 | | CodeCode Available | 2 |
| Scaling Up Models and Data with t5x and seqio | Mar 31, 2022 | Decoder | CodeCode Available | 2 |
| Bringing Old Films Back to Life | Mar 31, 2022 | Analog Video Restoration | CodeCode Available | 2 |
| SELFIES and the future of molecular string representations | Mar 31, 2022 | valid | CodeCode Available | 2 |
| Exploring Visual Prompts for Adapting Large-Scale Models | Mar 31, 2022 | Visual Prompting | CodeCode Available | 2 |
| BRIO: Bringing Order to Abstractive Summarization | Mar 31, 2022 | Abstractive Text SummarizationText Summarization | CodeCode Available | 2 |
| Equivariant Diffusion for Molecule Generation in 3D | Mar 31, 2022 | Unconditional Molecule Generation | CodeCode Available | 2 |
| FlowFormer: A Transformer Architecture for Optical Flow | Mar 30, 2022 | DecoderOptical Flow Estimation | CodeCode Available | 2 |
| Large-Scale Pre-training for Person Re-identification with Noisy Labels | Mar 30, 2022 | Contrastive LearningMulti-Object Tracking | CodeCode Available | 2 |
| AdaMixer: A Fast-Converging Query-Based Object Detector | Mar 30, 2022 | ObjectObject Detection | CodeCode Available | 2 |
| Exploring Plain Vision Transformer Backbones for Object Detection | Mar 30, 2022 | Cross-Domain Few-Shot Object DetectionInstance Segmentation | CodeCode Available | 2 |
| Vakyansh: ASR Toolkit for Low Resource Indic languages | Mar 30, 2022 | Punctuation Restorationspeech-recognition | CodeCode Available | 2 |
| Balanced MSE for Imbalanced Visual Regression | Mar 30, 2022 | Age EstimationFairness | CodeCode Available | 2 |
| PerfectDou: Dominating DouDizhu with Perfect Information Distillation | Mar 30, 2022 | | CodeCode Available | 2 |
| Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Data | Mar 30, 2022 | 3D Object Detection3D Semantic Segmentation | CodeCode Available | 2 |
| Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection | Mar 30, 2022 | 2D Object DetectionBilevel Optimization | CodeCode Available | 2 |
| PromptDet: Towards Open-vocabulary Detection using Uncurated Images | Mar 30, 2022 | Language ModelingLanguage Modelling | CodeCode Available | 2 |
| MatteFormer: Transformer-Based Image Matting via Prior-Tokens | Mar 29, 2022 | Image Matting | CodeCode Available | 2 |
| Self-Supervised Learning for Recommender Systems: A Survey | Mar 29, 2022 | Recommendation SystemsSelf-Supervised Learning | CodeCode Available | 2 |
| 4-bit Conformer with Native Quantization Aware Training for Speech Recognition | Mar 29, 2022 | Automatic Speech RecognitionAutomatic Speech Recognition (ASR) | CodeCode Available | 2 |
| PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision | Mar 29, 2022 | 3D Human Pose EstimationHallucination | CodeCode Available | 2 |
| MAT: Mask-Aware Transformer for Large Hole Image Inpainting | Mar 29, 2022 | DiversityImage Inpainting | CodeCode Available | 2 |
| Nix-TTS: Lightweight and End-to-End Text-to-Speech via Module-wise Distillation | Mar 29, 2022 | CPUDecoder | CodeCode Available | 2 |
| Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation | Mar 29, 2022 | Instance SegmentationNeRF | CodeCode Available | 2 |
| LinkBERT: Pretraining Language Models with Document Links | Mar 29, 2022 | Document ClassificationLanguage Modeling | CodeCode Available | 2 |
| Balanced Multimodal Learning via On-the-fly Gradient Modulation | Mar 29, 2022 | | CodeCode Available | 2 |
| Towards End-to-End Unified Scene Text Detection and Layout Analysis | Mar 28, 2022 | Document Layout AnalysisScene Text Detection | CodeCode Available | 2 |
| REGTR: End-to-end Point Cloud Correspondences with Transformers | Mar 28, 2022 | Point Cloud RegistrationPose Estimation | CodeCode Available | 2 |
| STaR: Bootstrapping Reasoning With Reasoning | Mar 28, 2022 | Common Sense ReasoningLanguage Modeling | CodeCode Available | 2 |
| Stratified Transformer for 3D Point Cloud Segmentation | Mar 28, 2022 | Point Cloud SegmentationPosition | CodeCode Available | 2 |
| TGL: A General Framework for Temporal GNN Training on Billion-Scale Graphs | Mar 28, 2022 | CPUGPU | CodeCode Available | 2 |
| Rethinking Semantic Segmentation: A Prototype View | Mar 28, 2022 | SegmentationSemantic Segmentation | CodeCode Available | 2 |
| CMGAN: Conformer-based Metric GAN for Speech Enhancement | Mar 28, 2022 | Automatic Speech RecognitionAutomatic Speech Recognition (ASR) | CodeCode Available | 2 |
| LiDAR Snowfall Simulation for Robust 3D Object Detection | Mar 28, 2022 | 3D Object DetectionAutonomous Driving | CodeCode Available | 2 |