Frederic Zhang

upt. [CVPR'22] Official PyTorch implementation for paper "Efficient Two-Stage Detection of Human–Object Interactions with a Novel Unary–Pairwise Transformer"

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

spatially-conditioned-graphs. [ICCV'21] Official PyTorch implementation for paper "Spatially Conditioned Graphs for Detecting Human–Object Interactions"

hicodet. Utilities for the human-object interaction detection dataset HICO-DET

pocket. A deep learning library to enable rapid prototyping

atlas. [NeurIPS'24] Official PyTorch implementation for paper "Knowledge Composition using Task Vectors with Learned Anisotropic Scaling"

SIFT-MATLAB. Extract and match features using SIFT descriptors

5-point-algorithm-MATLAB. 5-point algorithm based on David Nister solution

Normalized-Eight-Point-Algorithm. CAUTION! This implementation returns inaccurate results on noisy data from real images albeit working perfectly on synthetic data. It is purposed to help understand the algorithm but not encouraged to be used in large projects..

vcoco. Utilities for the dataset V-COCO in Python3

Camera-Calibration. Camera calibration program using 3d grid in Matlab

fredzzhang.github.io. SCSS