DFNet: Enhance Absolute Pose Regression with Direct Feature Matching.- Cornerformer: Purifying Instances for Corner-Based Detectors.- Robust Object Detection with Inaccurate Bounding Boxes.- Efficient Decoder-Free Object Detection with Transformers.- Cross-Modality Knowledge Distillation Network for Monocular 3D Object Detection.- ReAct: Temporal Action Detection with Relational Queries.- Towards Accurate Active Camera Localization.- Camera Pose Auto-Encoders for Improving Pose Regression.- Improving the Intra-Class Long-Tail in 3D Detection via Rare Example Mining.- Bagging Regional Classification Activation Maps for Weakly Supervised Object Localization.- UC-OWOD: Unknown-Classified Open World Object Detection.- RayTran: 3D Pose Estimation and Shape Reconstruction of Multiple
Objects from Videos with Ray-Traced Transformers.- GTCaR: Graph Transformer for Camera Re-Localization.- 3D Object Detection with aSelf-Supervised Lidar Scene Flow Backbone.- Open Vocabulary Object Detection with Pseudo Bounding-Box Labels.- Few-Shot Object Detection by Knowledge Distillation Using Bag-of-Visual-Words Representations.- SALISA: Saliency-Based Input Sampling for Efficient Video Object
Detection.- ECO-TR: Efficient Correspondences Finding via Coarse-to-Fine
Refinement.- Vote from the Center: 6 DoF Pose Estimation in RGB-D Images by
Radial Keypoint Voting.- Long-Tailed Instance Segmentation Using Gumbel Optimized Loss.- DetMatch: Two Teachers Are Better than One for Joint 2D and 3D
Semi-Supervised Object Detection.- ObjectBox: From Centers to Boxes for Anchor-Free Object Detection.- Is Geometry Enough for Matching in Visual Localization?.- SWFormer: Sparse Window Transformer for 3D Object Detection in Point Clouds.- PCR-CG: Point Cloud Registration via Deep Explicit Color and Geometry.- GLAMD:Global and Local Attention Mask Distillation for Object Detectors.- FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection.- Video Anomaly Detection by Solving Decoupled Spatio-Temporal
Jigsaw Puzzles.- Class-Agnostic Object Detection with Multi-modal Transformer.- Enhancing Multi-modal Features Using Local Self-Attention for 3D
Object Detection.- Object Detection As Probabilistic Set Prediction.- Weakly-Supervised Temporal Action Detection for Fine-Grained Videos with Hierarchical Atomic Actions.- Neural Correspondence Field for Object Pose Estimation.- On Label Granularity and Object Localization.- OIMNet++: Prototypical Normalization and Localization-Aware
Learning for Person Search.- Out-of-Distribution Identification: Let Detector Tell Which I Am Not Sure.- Learning with Free Object Segments for Long-Tailed Instance
Segmentation.- Autoregressive Uncertainty Modelingfor 3D Bounding Box Prediction.- 3D Random Occlusion and Multi-layer Projection for Deep Multi-Camera Pedestrian Localization.- A Simple Single-Scale Vision Transformer for Object Detection and
Instance Segmentation.- Simple Open-Vocabulary Object Detection with Vision Transformers
