The code of the paper "NExT-Chat: An LMM for Chat, Detection and Segmentation".

System for AI Education Resource.

🤠 Agent-as-a-Judge and DevAI dataset

This is the public repository for the Poster Abstract: Realistic Multiuser, Multimodal (IMU, Acoustic) HAR Data Generation through Single User Data Augmentation accepted in ACM/IEEE IPSN 2022.

3-layer-CNN and ResNet with OPPORTUNITY dataset, PAMAP2 dataset, UCI-HAR dataset, UniMiB-SHAR dataset, USC-HAD dataset, and WISDM dataset.

GTP engine and self-play learning in Go

Meta-Transformer for Unified Multimodal Learning

[CVPR 2024] OneLLM: One Framework to Align All Modalities with Language

Official repository for the NuScenes-MQA. This paper is accepted by LLVA-AD Workshop at WACV 2024.

high Building Throw Det

[ICCV 2023] GeoMIM: towards better 3d knowledge transfer via masked image modeling for multi-view 3d understanding

[ICLR 2024 & ECCV 2024] The All-Seeing Projects: Towards Panoptic Visual Recognition&Understanding and General Relation Comprehension of the Open World"

The official Talk2Car dataset repo

MixMIM: Mixed and Masked Image Modeling for Efficient Visual Representation Learning

[AAAI 2024] NuScenes-QA: A Multi-modal Visual Question Answering Benchmark for Autonomous Driving Scenario.

Official PyTorch implementation of FocalFormer3D [ICCV 2023]

Project Page for "LISA: Reasoning Segmentation via Large Language Model"

[ICCV 2023] Code for NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

[ICCV 2023] Temporal Enhanced Training of Multi-view 3D Object Detector via Historical Object Prediction

Official code base of the BEVDet series .

The official implementation of ICLR2021 paper "Improve Object Detection with Feature-based Knowledge Distillation: Towards Accurate and Efficient Detectors".

Official code for BEVDepth.

Codes for VPGTrans: Transfer Visual Prompt Generator across LLMs. VL-LLaMA, VL-Vicuna.

Segment Any RGBD

Code release for "Masked-attention Mask Transformer for Universal Image Segmentation"

[CVPR 2023 Highlight] InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions

This is the official code for MobileSAM project that makes SAM lightweight for mobile applications and beyond!