BitBIRCH-Lean, a memory-efficient implementation of BitBIRCH designed for high-throughput clustering of huge molecular libraries

Social Chemistry 101: Learning to Reason about Social and Moral Norms

Agent S: an open agentic framework that uses computers like a human

Machine Learning In Production (MLOps)

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

[ECCV 2024] OpenPSG: Open-set Panoptic Scene Graph Generation via Large Multimodal Models

The repository provides code for training/fine tune the Meta Segment Anything Model 2 (SAM 2)

Adapting Meta AI's Segment Anything to Downstream Tasks with Adapters and Prompts

ME-GraphAU on Video

llama3 implementation one matrix multiplication at a time

Segment Anything for Microscopy

[ICCV'25 Best Paper Finalist] ReCamMaster: Camera-Controlled Generative Rendering from A Single Video

Official repo for VGGHeads: 3D Multi Head Alignment with a Large-Scale Synthetic Dataset..

pytorch-hair-segmentation

docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.

This material is based on the System Design Masterclass (2025) course available on Udemy. You can find the course here: System Design Masterclass. You can also find many free resources related to t…

[FG 2025] official implementation for the paper 'Representation Learning and Identity Adversarial Training for Facial Behavior Understanding'

Norface: Improving Facial Expression Analysis by Identity Normalization, ECCV 2024

AI models trained by Google to classify species in images from motion-triggered wildlife cameras.

Face recognition with deep neural networks.

Multi-label Co-regularization for Semi-supervised Facial Action Unit Recognition (NeurIPS 2019)

PyTorch implementation of JAA-Net including both ECCV version and IJCV version

[AAAI 2020] Facial Action Unit Intensity Estimation via Semantic Correspondence Learning with Dynamic Graph Convolution

Self-supervised Representation Learning from Videos for Facial Action Unit Detection

[IJCAI 2022] Learning Multi-dimensional Edge Feature-based AU Relation Graph for Facial Action Unit Recognition, Pytorch code

Pytorch implementation of Multi-View Dynamic Facial Action Unit Detection, Image and Vision Computing (2018)

This is an official implementation of our CVPR 2023 paper "Human Pose as Compositional Tokens" (https://arxiv.org/pdf/2303.11638.pdf)

Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"