[ICCV'23] Cascade-DETR: Delving into High-Quality Universal Object Detection

[ECCV 2024] A Simple and Effective 3D DETR in Point Clouds

[ICLR 2022] Official implementation of the paper "DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR"

Deformable DETR: Deformable Transformers for End-to-End Object Detection.

[ICLR 2026] TriC-Motion: Tri-Domain Causal Modeling Grounded Text-to-Motion Generation

Enhancing 3D Object Detection with 2D Detection-Guided Query Anchors, CVPR 2024

AI agents running research on single-GPU nanochat training automatically

[CVPR 2026] SPAN: Spatial-Projection Alignment for Monocular 3D Object Detection

[ECCV2024 Oral] Official implementation of the paper "Relation DETR: Exploring Explicit Position Relation Prior for Object Detection"

🔍大模型应用开发实战一：RAG 技术全栈指南，在线阅读地址：https://datawhalechina.github.io/all-in-rag/

软院研究生经验分享

Awesome Monocular 3D detection

assistant tools for attention visualization in deep learning

Unbalanced Optimal Transport: A Unified Framework for Object Detection

A paper list of some recent Transformer-based CV works.

[ AAAI 2026 ] The official implementation of 'MonoCLUE: Object-Aware Clustering Enhances Monocular 3D Object Detection'

A simple, elegant web tool that allows you to create custom RSS feeds for arXiv search queries. Stay up-to-date with the latest research papers in your field by subscribing to precisely crafted sea…

Learning to Rank in PyTorch

Fast Differentiable Sorting and Ranking

Enforce the output format (JSON Schema, Regex etc) of a language model

PyTorch code and models for the DINOv2 self-supervised learning method.

[CVPR 2025 🔥] MI-DETR: An Object Detection Model with Multi-time Inquiries Mechanism

Processed / Cleaned Data for Paper Copilot

[CVPR 2024] MonoCD: Monocular 3D Object Detection with Complementary Depths

[CVPR 2025] The offical implementation of 'MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors'

Official implementation of the 3DV 2024 paper MonoLSS: Learnable Sample Selection For Monocular 3D Detection

使用open3d显示kitti数据的3D视角和BEV视角