논문 리뷰17 [논문 요약] Cross-modal Prompts: Adapting Large Pre-trained Models for Audio-Visual Downstream Tasks [논문 요약] Cross-modal Prompts: Adapting Large Pre-trained Models for Audio-Visual Downstream Tasks 2023 NeurIPShttps://arxiv.org/abs/2311.05152 Cross-modal Prompts: Adapting Large Pre-trained Models for Audio-Visual Downstream TasksIn recent years, the deployment of large-scale pre-trained models in audio-visual downstream tasks has yielded remarkable outcomes. However, these models, primarily tra.. 2025. 3. 4. [논문 요약] Robust Real-time LiDAR-inertial Initialization [논문 요약] Robust Real-time LiDAR-inertial Initialization 2022 IROS 논문.요즘 라이다-IMU Calibaration 하고 있어서 중심 내용만 짧게 정리한다.SLAM 돌리는데 calibration이나 다른 초기값들이 너무 중요한듯.. 이 값들에 의해 알고리즘 결과가 천차만별. https://arxiv.org/abs/2202.11006 Robust Real-time LiDAR-inertial InitializationFor most LiDAR-inertial odometry, accurate initial states, including temporal offset and extrinsic transformation between LiDAR and 6-axis.. 2025. 1. 24. [논문 정리] Barlow Twins: Self-Supervised Learning via Redundancy Reduction [논문 정리] Barlow Twins: Self-Supervised Learning via Redundancy Reduction2021, SSL 관련 논문https://arxiv.org/abs/2103.03230 Barlow Twins: Self-Supervised Learning via Redundancy ReductionSelf-supervised learning (SSL) is rapidly closing the gap with supervised methods on large computer vision benchmarks. A successful approach to SSL is to learn embeddings which are invariant to distortions of the inp.. 2025. 1. 17. [논문 요약] EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning [논문 요약] EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning ICML 2024 paperhttps://arxiv.org/abs/2403.09502 EquiAV: Leveraging Equivariance for Audio-Visual Contrastive LearningRecent advancements in self-supervised audio-visual representation learning have demonstrated its potential to capture rich and comprehensive representations. However, despite the advantages of data augm.. 2024. 12. 11. [논문 정리] LIO-SAM: Tightly-coupled Lidar Inertial Odometry via Smoothing and Mapping [논문정리] LIO-SAM: Tightly-coupled Lidar Inertial Odometry viaSmoothing and Mapping https://arxiv.org/abs/2007.00258 LIO-SAM: Tightly-coupled Lidar Inertial Odometry via Smoothing and MappingWe propose a framework for tightly-coupled lidar inertial odometry via smoothing and mapping, LIO-SAM, that achieves highly accurate, real-time mobile robot trajectory estimation and map-building. LIO-SAM formu.. 2024. 12. 4. [논문 리뷰] AVFF: Audio-Visual Feature Fusion for Video Deepfake Detection [논문 리뷰] AVFF: Audio-Visual Feature Fusion for Video Deepfake Detection CVPR 2024 Accepted paper. https://arxiv.org/abs/2406.02951 AVFF: Audio-Visual Feature Fusion for Video Deepfake DetectionWith the rapid growth in deepfake video content, we require improved and generalizable methods to detect them. Most existing detection methods either use uni-modal cues or rely on supervised training to cap.. 2024. 11. 21. 이전 1 2 3 다음
