This repo is the official implementation of the paper titled "Generating Hashtags for Short-form Videos with Guided Signals" (ACL 2023).
Code for the paper Self-Supervised Learning of Split Invariant Equivariant Representations
Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive architecture."
A public release of TimelineBuilder for building personal digital data timelines.
Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectories
projectaria_tools provide the open-source toolkit in C++ and Python to interact with data from Project Aria
[CVPR 2023] Official code for "Learning Procedure-aware Video Representation from Instructional Videos and Their Narrations"
This is a PyTorch implementation of the paperViP A Differentially Private Foundation Model for Computer Vision
Code for Novel View Acoustic Synthesis paper
An algorithm for reconstructing the radiance field of a dynamic scene from a casually-captured video.
Learning Compiler Pass Orders using Coreset and Normalized Value Prediction. (ICML 2023)
Repo for ICML'23 paper SurCo Learning Linear Surrogates For Combinatorial Nonlinear Optimization Problems
Code repo for ICML'23 Searching Large Neighborhoods for Integer Linear Programs with Contrastive Learning
eSSIM is an evolution of SSIM which improves correlation with subjective scores and reduces complexity by employing box filters, striding, and Minkowski pooling
Code and pre-trained model release for the ICASSP 2023 Paper "NORD NON-MATCHING REFERENCE BASED RELATIVE DEPTH ESTIMATION FROM BINAURAL AUDIO"
CoTracker is a model for tracking any point (pixel) on a video.
