研究介绍 出于隐私和安全考虑，如今变得越来越明显的是，需要从 […]
Large-Scale Object Detection in the Wild with Imbalanced Data Distribution, and Multi-Labels (TPAMI 2024)
研究介绍： 使用更多数据进行训练一直是深度学习时代提升性能最 […]
RCL: Reliable Continual Learning for Unified Failure Detection (CVPR 2024)
研究介绍： 深度神经网络往往对未知输入过于自信，给实际应用带 […]
Fully Sparse Fusion for 3D Object Detection (TPAMI 2024)
目前流行的多模态3D检测方法通常依赖于密集检测器，这些检测器 […]
Fully Data-Driven Pseudo Label Estimation for Pointly-Supervised Panoptic Segmentation (AAAI 2024)
点监督全景分割的核心是从稀疏点标签中准确估计密集的伪标签，以 […]
Learnable Graph Matching: A Practical Paradigm for Data Association (TPAMI 2024)
数据关联是许多计算机视觉任务的核心，例如多目标跟踪、图像匹配 […]
MixSup: Mixed-grained Supervision for Label-efficient LiDAR-based 3D Object Detection, International Conference on Learning Representations (ICLR 2024)
目前基于激光雷达的三维目标检测高效标注训练主要由弱监督和半监 […]
HardMo: A Large-Scale Hardcase Dataset for Motion Capture (CVPR 2024)
研究介绍 本文介绍了一个大规模的难例动作捕捉数据集——Har […]
Monocular Occupancy Prediction for Scalable Indoor Scenes (ECCV 2024)
研究介绍： 基于摄像头的3D占用预测最近在户外驾驶场景中引起 […]
OneTrack: Demystifying the Conflict Between Detection and Tracking in End-to-End 3D Trackers (ECCV 2024)
研究介绍： 本文提出了一种解决视觉3D感知中端到端多目标追踪 […]
