| Task | Area | Papers | Results |
|---|---|---|---|
| Graph Matching Graph Matching is the problem of finding correspondences bet… | Graphs & Structured Data | 477 | 83 |
| Action Detection Action Detection aims to find both where and when an action … | Computer Vision | 817 | 81 |
| Multiple Object Tracking Multiple Object Tracking is the problem of automatically ide… | Computer Vision | 318 | 81 |
| 3D Instance Segmentation Image: [OccuSeg](https://arxiv.org/pdf/2003.06537v3.pdf) | Computer Vision | 153 | 79 |
| Semantic Parsing Semantic Parsing is the task of transducing natural language… | Language & Reasoning | 1,202 | 78 |
| Retinal Vessel Segmentation Retinal vessel segmentation is the task of segmenting vessel… | Medical & Scientific | 139 | 78 |
| Text Simplification Text Simplification is the task of reducing the complexity o… | Language & Reasoning | 468 | 77 |
| 3D Multi-Person Pose Estimation This task aims to solve root-relative 3D multi-person pose e… | Computer Vision | 62 | 77 |
| Formation Energy On the QM9 dataset the numbers reported in the table are the… | Medical & Scientific | 54 | 77 |
| Cross-Domain Few-Shot | Foundations & Efficiency | 141 | 76 |
| AMR Parsing Each AMR is a single rooted, directed graph. AMRs include Pr… | Graphs & Structured Data | 117 | 76 |
| Grammatical Error Correction Grammatical Error Correction (GEC) is the task of correcting… | Language & Reasoning | 415 | 75 |
| Intent Detection Intent Detection is a task of determining the underlying pur… | Language & Reasoning | 330 | 75 |
| Conditional Image Generation Conditional image generation is the task of generating new i… | Generative Models | 286 | 75 |
| Entity Resolution Entity resolution (also known as entity matching, record lin… | Language & Reasoning | 184 | 75 |
| Interactive Segmentation | Computer Vision | 255 | 74 |
| Image Deblurring file:///var/mobile/Library/SMS/Attachments/cb/11/8A26E2FC-74… | Generative Models | 396 | 73 |
| Object Counting The goal of Object Counting task is to count the number of o… | Computer Vision | 158 | 69 |
| Vehicle Re-Identification Vehicle re-identification is the task of identifying the sam… | Computer Vision | 150 | 68 |
| Discourse Parsing | Language & Reasoning | 189 | 66 |
| Density Estimation The goal of Density Estimation is to give an accurate descri… | Foundations & Efficiency | 1,394 | 65 |
| Logical Reasoning | Language & Reasoning | 747 | 65 |
| Video Anomaly Detection | Time Series & Forecasting | 262 | 64 |
| Open Vocabulary Object Detection Open-vocabulary detection (OVD) aims to generalize beyond th… | Computer Vision | 145 | 64 |
| Shadow Removal Image Shadow Removal | Generative Models | 127 | 64 |
| Automated Theorem Proving The goal of Automated Theorem Proving is to automatically ge… | Language & Reasoning | 288 | 63 |
| Linguistic Acceptability Linguistic Acceptability is the task of determining whether … | Language & Reasoning | 72 | 63 |
| Birds Eye View Object Detection KITTI birds eye view detection task | Reinforcement Learning & Robotics | 8 | 63 |
| Multi-modal Entity Alignment | Multimodal & Vision-Language | 19 | 62 |
| Federated Learning Federated Learning is a machine learning approach that allow… | Foundations & Efficiency | 6,771 | 61 |
| Hand Pose Estimation Hand pose estimation is the task of finding the joints of th… | Computer Vision | 260 | 61 |
| Entity Disambiguation Entity Disambiguation is the task of linking mentions of amb… | Language & Reasoning | 156 | 61 |
| Robot Manipulation | Reinforcement Learning & Robotics | 430 | 60 |
| Camouflaged Object Segmentation Camouflaged object segmentation (COS) or Camouflaged object … | Computer Vision | 47 | 60 |
| 3D Semantic Scene Completion This task was introduced in "Semantic Scene Completion from … | Computer Vision | 65 | 59 |
| Handwritten Mathmatical Expression Recognition Offline Handwritten mathematical Expression Recognition aims… | Language & Reasoning | 16 | 59 |
| Depth Estimation Depth Estimation is the task of measuring the distance of ea… | Computer Vision | 2,454 | 58 |
| 2D Object Detection | Computer Vision | 210 | 57 |
| Moment Retrieval Moment retrieval can de defined as the task of "localizing m… | Multimodal & Vision-Language | 132 | 57 |
| KG-to-Text Generation Knowledge-graph-to-text (KG-to-text) generation aims to gene… | Language & Reasoning | 22 | 57 |
| LIDAR Semantic Segmentation | Computer Vision | 129 | 56 |
| Sleep Stage Detection Human Sleep Staging into W-N1-N2-N3-REM classes from multipl… | Medical & Scientific | 34 | 55 |
| Text Generation Text Generation is the task of generating text with the goal… | Language & Reasoning | 5,335 | 54 |
| Dependency Parsing Dependency parsing is the task of extracting a dependency pa… | Language & Reasoning | 1,407 | 54 |
| Unsupervised Object Segmentation Image credit: [ClevrTex: A Texture-Rich Benchmark for Unsupe… | Computer Vision | 39 | 53 |
| Few-Shot Learning Few-Shot Learning is an example of meta-learning, where a le… | Foundations & Efficiency | 2,964 | 52 |
| Code Documentation Generation Code Documentation Generation is a supervised task where a c… | Language & Reasoning | 8 | 52 |
| Document Classification Document Classification is a procedure of assigning one or m… | Language & Reasoning | 641 | 51 |
| Object Localization Object Localization is the task of locating an instance of a… | Computer Vision | 617 | 51 |
| Universal Domain Adaptation | Foundations & Efficiency | 55 | 51 |