| Unconstrained Lip-synchronization Given a video of an arbitrary person, and an arbitrary drivi… | 4 | 0 |
| Underwater 3D Scene Reconstruction | 4 | 0 |
| Video Individual Counting | 4 | 0 |
| Video Story QA MCQ about clips from movies/tvshows/etc | 4 | 0 |
| Visibility Tracking | 4 | 0 |
| Visu | 4 | 0 |
| Visual Crowd Analysis | 4 | 0 |
| Weakly Supervised 3D Point Cloud Segmentation | 4 | 0 |
| Weakly-Supervised Action Recognition Action recognition with single-point annotations in time (th… | 4 | 0 |
| Weakly-supervised panoptic segmentation | 4 | 0 |
| Zero-Shot Learning + Domain Generalization | 4 | 0 |
| 2D Semantic Segmentation task 2 (17 classes) | 3 | 0 |
| 3D Canonicalization 3D Canonicalization is the process of estimating a transform… | 3 | 0 |
| 3D Semantic Scene Completion from a single 2D image | 3 | 0 |
| Action Triplet Detection Detecting and localizing bounding boxes of tools and anatomi… | 3 | 0 |
| Age/Unbiased | 3 | 0 |
| Anomaly Instance Segmentation | 3 | 0 |
| Articulated Object modelling | 3 | 0 |
| Artist classification Classification of the artist for artistic images | 3 | 0 |
| Artistic style classification Classify the artistic style of an artwork image | 3 | 0 |
| Atom3D benchmark | 3 | 0 |
| A-VB High The A-VB High track, explores a high-dimensional emotion spa… | 3 | 0 |
| Burst Image Reconstruction | 3 | 0 |
| CAPTCHA Detection | 3 | 0 |
| Clothes Landmark Detection | 3 | 0 |
| Composed Video Retrieval (CoVR) | 3 | 0 |
| Concave shapes | 3 | 0 |
| Constrained Diffeomorphic Image Registration | 3 | 0 |
| Continual Panoptic Segmentation | 3 | 0 |
| cow identification cattle/cow identification | 3 | 0 |
| Damaged Building Detection | 3 | 0 |
| Dark Humor Detection | 3 | 0 |
| Depth Aleatoric Uncertainty Estimation | 3 | 0 |
| Depth Image Estimation | 3 | 0 |
| Disguised Face Verification | 3 | 0 |
| Few-shot 3D semantic segmentation | 3 | 0 |
| Field Boundary Delineation | 3 | 0 |
| Flooded Building Segmentation | 3 | 0 |
| Forgery Image Detection Detecting Forgery Images Generated By LLMs | 3 | 0 |
| Generalized Zero Shot skeletal action recognition Generalized Zero Shot Learning for 3d Skeleton-Based Action … | 3 | 0 |
| Hallucination Pair-wise Detection (1-ref) | 3 | 0 |
| Human Fitting | 3 | 0 |
| Human-Human Interaction Recognition | 3 | 0 |
| Human-Object Relationship Detection | 3 | 0 |
| Hyperspectral Image-Based Fruit Ripeness Prediction Fruit ripeness prediction (FRP) is a classification-based ag… | 3 | 0 |
| Hyperspectral Image Inpainting | 3 | 0 |
| Hypertension detection Detection of hypertension (high blood pressure) using vital … | 3 | 0 |
| Image Compression Artifact Reduction | 3 | 0 |
| Image Deep Networks | 3 | 0 |
| image-sentence alignment Predict the alignment (score) between an image and a sentenc… | 3 | 0 |
