https://github.com/asterisci/language-assisted-3d
공식 코드Language-Assisted 3D Feature Learning for Semantic Scene Understanding
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Language-Assisted 3D Feature Learning for Semantic Scene Understanding
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast
All for One and One for All: Improving Music Separation by Bridging Networks
All for One and One for All: Improving Music Separation by Bridging Networks
Large Language Models on Wikipedia-Style Survey Generation: an Evaluation in NLP Concepts
SciBERTSUM: Extractive Summarization for Scientific Documents
A Dataset for Plain Language Adaptation of Biomedical Abstracts
Context Autoencoder for Self-Supervised Representation Learning
On the Connection between Local Attention and Dynamic Depth-wise Convolution
Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment
LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection
AraBERT: Transformer-based Model for Arabic Language Understanding
Robust 6DoF Pose Estimation Against Depth Noise and a Comprehensive Evaluation on a Mobile Dataset
Robust 6DoF Pose Estimation Against Depth Noise and a Comprehensive Evaluation on a Mobile Dataset
Unsupervised Speech Decomposition via Triple Information Bottleneck
Misaligned Over-The-Air Computation of Multi-Sensor Data with Wiener-Denoiser Network
Gompertz Linear Units: Leveraging Asymmetry for Enhanced Learning Dynamics
GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields
GOOD: Exploring Geometric Cues for Detecting Objects in an Open World
Multi-Modal Fusion Transformer for End-to-End Autonomous Driving
VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids
R-TOD: Real-Time Object Detector with Minimized End-to-End Delay for Autonomous Driving
Phantom Sponges: Exploiting Non-Maximum Suppression to Attack Deep Object Detectors
Formal Verification of Deep Neural Networks for Object Detection
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.