Computer Vision

Occlusion Resistant Network for 3D Face Reconstruction WACV 2022 Occlusion-Robust Face Alignment Using a Viewpoint-Invariant Hierarchical Network Architecture CVPR 2022 OCR Improves Machine Translation for Low-Resource Languages ACL 2022 OCSampler: Compressing Videos to One Clip With Single-Step Sampling CVPR 2022 OctAttention: Octree-Based Large-Scale Contexts Model for Point Cloud Compression AAAI 2022 OGC: Unsupervised 3D Object Segmentation from Rigid Dynamics of Point Clouds NeurIPS 2022 OLALA: Object-Level Active Learning for Efficient Document Layout Annotation EMNLP 2022 OLIVES Dataset: Ophthalmic Labels for Investigating Visual Eye Semantics NeurIPS 2022 Omni-DETR: Omni-Supervised Object Detection With Transformers CVPR 2022 Omni-Dimensional Dynamic Convolution ICLR 2022 OmniFusion: 360 Monocular Depth Estimation via Geometry-Aware Fusion CVPR 2022 OmniVL: One Foundation Model for Image-Language and Video-Language Tasks NeurIPS 2022 Omnivore: A Single Model for Many Visual Modalities CVPR 2022 On Advances in Text Generation from Images Beyond Captioning: A Case Study in Self-Rationalization EMNLP 2022 On Aliased Resizing and Surprising Subtleties in GAN Evaluation CVPR 2022 On Analyzing Generative and Denoising Capabilities of Diffusion-based Deep Generative Models NeurIPS 2022 On Black-Box Explanation for Face Verification WACV 2022 ONCE-3DLanes: Building Monocular 3D Lane Detection CVPR 2022 One-Class Learned Encoder-Decoder Network With Adversarial Context Masking for Novelty Detection WACV 2022 One-Inlier is First: Towards Efficient Position Encoding for Point Cloud Registration NeurIPS 2022 One Loss for Quantization: Deep Hashing With Discrete Wasserstein Distributional Matching CVPR 2022 One Model to Edit Them All: Free-Form Text-Driven Image Manipulation with Semantic Modulations NeurIPS 2022 One More Check: Making “Fake Background” Be Tracked Again AAAI 2022 OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Models NeurIPS 2022 OnePose: One-Shot Object Pose Estimation Without CAD Models CVPR 2022