Refine high-quality datasets and visual AI models

Sequential model-based optimization with a `scipy.optimize` interface

Official implementation of PVT series

An implementation of CycleGan using TensorFlow

Official PyTorch implementation of ODISE: Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models [CVPR 2023 Highlight]

Mask Transfiner for High-Quality Instance Segmentation, CVPR 2022

Autonomous Navigation of UAV using Reinforcement Learning algorithms.

[ICRA 2024 Oral] Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation

CEDNet: A Cascade Encoder-Decoder Network for Dense Prediction (Pattern Recognition 2024)

Generate videos that interpolate between two given images

AIOZ-GDANCE: a large-scale dataset & baseline for music-driven group dance generation. (CVPR 2023)

[ISBI 2024] An implementation of SAM3D which adapts Segment Anything Model for Volumetric Medical Image Segmentation

[CVPR 2025] h-Edit: Effective and Flexible Diffusion-Based Editing via Doob’s h-Transform

[Remote Sensing] AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation

IAM dataset

[CVPR 2023] This is the official PyTorch implementation for "Dynamic Focus-aware Positional Queries for Semantic Segmentation".

Qualia is a deep learning framework deeply integrated with automatic differentiation and dynamic graphing with CUDA acceleration. Qualia was built from scratch.

[IEEE BHI 2022] Multimodality Multi-Lead ECG Arrhythmia Classification using Self-Supervised Learning

Warmup learning rate wrapper for Pytorch Scheduler

[CVPR'22] DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition

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

[IJCV] AOE-Net: Entities Interactions Modeling with Adaptive Attention Mechanism for Temporal Action Proposals Generation

OBEYED-VLA: Clutter-Resistant Vision-Language-Action Models through Object-Centric and Geometry Grounding

[BMVC 2021 Oral] AEI: Actors-Environment Interaction with Adaptive Attention for Temporal Action Proposal Generation