Official implementation of paper "GAPrompt: Geometry-Aware Point Cloud Prompt for 3D Vision Model", ICML 2025

(AAAI2024) Point-PEFT: Parameter-Efficient Fine-Tuning for 3D Pre-trained Models

[ECCV 2024] ShapeLLM: Universal 3D Object Understanding for Embodied Interaction

The official code repository of "HIS-GPT: Towards 3D Human-In-Scene Multimodal Understanding"

[ICML 2024] A Touch, Vision, and Language Dataset for Multimodal Alignment

A list of Human-Object Interaction Learning.

本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）

[CVPR 2024 Accepted] TaskWeave: Decoupling and Inter-Task Feedback for Joint Moment Retrieval and Highlight Detection

The official code for Relational Context Learning for Human-Object Interaction Detection, CVPR2023.

[ICCV'23] Official PyTorch implementation for paper "Exploring Predicate Visual Context in Detecting Human-Object Interactions"

[EMNLP2024 Demo], [ICASSP 2025] A user-friendly library for reproducible video moment retrieval and highlight detection. It also supports audio moment retrieval.

code for sound event detection transformer (SEDT) and self-supervised pre-training SEDT (SP-SEDT)

Code for the Interspeech 2021 paper "AST: Audio Spectrogram Transformer".

Code for one-stage adaptive set-based HOI detector AS-Net.

Code for "Mining the Benefits of Two-stage and One-stage HOI Detection"

Repo for CVPR2021 paper "QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information"

Disentangled Pre-training for Human-Object Interaction Detection

This is the code for HOI Transformer

Official repository for HOTR: End-to-End Human-Object Interaction Detection with Transformers (CVPR'21, Oral Presentation)

(TGRS 2024) OrientedFormer: An End-to-End Transformer-Based Oriented Object Detector in Remote Sensing Images

[CVPR 2025] Official code repository for "MaSS13K: A Matting-level Semantic Segmentation Benchmark"

ScratchFormer: Remote Sensing Change Detection With Transformers Trained from Scratch

Official Pytorch Implementation of "Remote Sensing Image Change Detection with Transformers"

The official implementation for "Spherical Transformer for LiDAR-based 3D Recognition" (CVPR 2023).

This is the official implementation of "LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels" (Accepted at CVPR 2024).

[WACV 2025] WeedsGalore dataset and code for segmentation of weeds in maize fields.

Code for running baseline models/experiments with the Fields of The World dataset