| TransTab: Learning Transferable Tabular Transformers Across Tables | May 19, 2022 | Incremental LearningTransfer Learning | CodeCode Available | 2 |
| Towards Unified Keyframe Propagation Models | May 19, 2022 | Image InpaintingVideo Editing | CodeCode Available | 2 |
| Torchhd: An Open Source Python Library to Support Research on Hyperdimensional Computing and Vector Symbolic Architectures | May 18, 2022 | | CodeCode Available | 2 |
| "I'm sorry to hear that": Finding New Biases in Language Models with a Holistic Descriptor Dataset | May 18, 2022 | Sentence | CodeCode Available | 2 |
| Masked Autoencoders As Spatiotemporal Learners | May 18, 2022 | Inductive BiasRepresentation Learning | CodeCode Available | 2 |
| BBDM: Image-to-image Translation with Brownian Bridge Diffusion Models | May 16, 2022 | Image GenerationImage-to-Image Translation | CodeCode Available | 2 |
| Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization | May 16, 2022 | graph partitioningSegmentation | CodeCode Available | 2 |
| A New Outlier Removal Strategy Based on Reliability of Correspondence Graph for Fast Point Cloud Registration | May 16, 2022 | Point Cloud Registration | CodeCode Available | 2 |
| PillarNet: Real-Time and High-Performance Pillar-based 3D Object Detection | May 16, 2022 | 3D Object DetectionAutonomous Driving | CodeCode Available | 2 |
| Diffusion Models for Adversarial Purification | May 16, 2022 | Adversarial Purification | CodeCode Available | 2 |
| Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pockets | May 15, 2022 | Drug DesignGraph Neural Network | CodeCode Available | 2 |
| Learning Lip-Based Audio-Visual Speaker Embeddings with AV-HuBERT | May 15, 2022 | Representation LearningSpeaker Verification | CodeCode Available | 2 |
| GenerSpeech: Towards Style Transfer for Generalizable Out-Of-Domain Text-to-Speech | May 15, 2022 | Speech SynthesisStyle Transfer | CodeCode Available | 2 |
| Neural-Fly Enables Rapid Learning for Agile Flight in Strong Winds | May 13, 2022 | Meta-Learning | CodeCode Available | 2 |
| VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder | May 13, 2022 | Blind Face RestorationDecoder | CodeCode Available | 2 |
| A Generalist Agent | May 12, 2022 | Language ModelingLanguage Modelling | CodeCode Available | 2 |
| Robot Cooking with Stir-fry: Bimanual Non-prehensile Manipulation of Semi-fluid Objects | May 12, 2022 | Deformable Object Manipulation | CodeCode Available | 2 |
| READ: Large-Scale Neural Scene Rendering for Autonomous Driving | May 11, 2022 | 3D Scene ReconstructionAutonomous Driving | CodeCode Available | 2 |
| RITA: a Study on Scaling Up Generative Protein Sequence Models | May 11, 2022 | PredictionProtein Design | CodeCode Available | 2 |
| Secure & Private Federated Neuroimaging | May 11, 2022 | Federated Learning | CodeCode Available | 2 |
| Surface Representation for Point Clouds | May 11, 2022 | 3D Object Detection3D Point Cloud Classification | CodeCode Available | 2 |
| Arbitrary Shape Text Detection via Boundary Transformer | May 11, 2022 | DecoderText Detection | CodeCode Available | 2 |
| KeypointNeRF: Generalizing Image-based Volumetric Avatars using Relative Spatial Encoding of Keypoints | May 10, 2022 | 3D Face Reconstruction3D Human Reconstruction | CodeCode Available | 2 |
| Symphony Generation with Permutation Invariant Language Model | May 10, 2022 | Audio GenerationDecoder | CodeCode Available | 2 |
| NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality | May 9, 2022 | SentenceSpeech Synthesis | CodeCode Available | 2 |
| ConvMAE: Masked Convolution Meets Masked Autoencoders | May 8, 2022 | Computational Efficiencyimage-classification | CodeCode Available | 2 |
| Decoupled-and-Coupled Networks: Self-Supervised Hyperspectral Image Super-Resolution with Subpixel Fusion | May 7, 2022 | Hyperspectral Image Super-ResolutionImage Super-Resolution | CodeCode Available | 2 |
| Machine Learning-Friendly Biomedical Datasets for Equivalence and Subsumption Ontology Matching | May 6, 2022 | Ontology Matching | CodeCode Available | 2 |
| CLIP-CLOP: CLIP-Guided Collage and Photomontage | May 6, 2022 | Prompt Engineering | CodeCode Available | 2 |
| Aksharantar: Open Indic-language Transliteration datasets and models for the Next Billion Users | May 6, 2022 | Transliteration | CodeCode Available | 2 |
| Language Models Can See: Plugging Visual Controls in Text Generation | May 5, 2022 | Image CaptioningImage-text matching | CodeCode Available | 2 |
| Approximate Convex Decomposition for 3D Meshes with Collision-Aware Concavity and Tree Search | May 5, 2022 | | CodeCode Available | 2 |
| GANimator: Neural Motion Synthesis from a Single Sequence | May 5, 2022 | Motion SynthesisStyle Transfer | CodeCode Available | 2 |
| Neural 3D Scene Reconstruction with the Manhattan-world Assumption | May 5, 2022 | 2D Semantic Segmentation3D Reconstruction | CodeCode Available | 2 |
| EmoBank: Studying the Impact of Annotation Perspective and Representation Format on Dimensional Emotion Analysis | May 4, 2022 | Emotion Recognition | CodeCode Available | 2 |
| Hybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completion | May 4, 2022 | Information RetrievalKnowledge Graph Completion | CodeCode Available | 2 |
| pyRDF2Vec: A Python Implementation and Extension of RDF2Vec | May 4, 2022 | | CodeCode Available | 2 |
| Masked Generative Distillation | May 3, 2022 | image-classificationImage Classification | CodeCode Available | 2 |
| Self-focusing virtual screening with active design space pruning | May 3, 2022 | | CodeCode Available | 2 |
| Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation | May 3, 2022 | 2D Human Pose EstimationMulti-Person Pose Estimation | CodeCode Available | 2 |
| MemSeg: A semi-supervised method for image surface defect detection using differences and commonalities | May 2, 2022 | Anomaly DetectionDefect Detection | CodeCode Available | 2 |
| MUTR3D: A Multi-camera Tracking Framework via 3D-to-2D Queries | May 2, 2022 | Autonomous DrivingDepth Estimation | CodeCode Available | 2 |
| Learning Multi-dimensional Edge Feature-based AU Relation Graph for Facial Action Unit Recognition | May 2, 2022 | Facial Action Unit DetectionRelation | CodeCode Available | 2 |
| DoTAT: A Domain-oriented Text Annotation Tool | May 1, 2022 | text annotation | CodeCode Available | 2 |
| BMInf: An Efficient Toolkit for Big Model Inference and Tuning | May 1, 2022 | CPUGPU | CodeCode Available | 2 |
| Deep PCB To COCO Convertor | May 1, 2022 | ClassificationData Augmentation | CodeCode Available | 2 |
| ONCE-3DLanes: Building Monocular 3D Lane Detection | Apr 30, 2022 | 3D Lane DetectionAutonomous Driving | CodeCode Available | 2 |
| Deep Learning-Enabled Semantic Communication Systems with Task-Unaware Transmitter and Dynamic Data | Apr 30, 2022 | Domain AdaptationSemantic Communication | CodeCode Available | 2 |
| AdaInt: Learning Adaptive Intervals for 3D Lookup Tables on Real-time Image Enhancement | Apr 29, 2022 | Image EnhancementPhoto Retouching | CodeCode Available | 2 |
| An Extensive Data Processing Pipeline for MIMIC-IV | Apr 29, 2022 | modelTime Series Analysis | CodeCode Available | 2 |