Open-source alternatives to ViFi CLIP

by Mutian Xu, Runyu Ding, Hengshuang Zhao, and Xiaojuan Qi.

:construction: WIP :construction:

This is the author code of "Learnable Dynamic Temporal Pooling for Time Series Classification" (AAAI 2021). - We employ (and customize) the fast CUDA implementation of soft-dtw (based on pytorch), publicly available at https://github.com/Maghoumi/pytorch-softdtw-cuda. - For more details of…

Code for Generative Time-series Modeling with Fourier Flows.

This code provides a PyTorch implementation and pretrained models for DepthContrast, as described in the paper Self-Supervised Pretraining of 3D Features on any Point-Cloud.

This repository contains the official PyTorch implementation of the following paper:

Kronecker Time-Varying Graphical Lasso (KTVGL) implementation.

ICCV 2021- Oral Official PyTorch implementation for Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers, a novel method to visualize any Transformer-based network. Including examples for DETR, VQA.

Voice2Series: Reprogramming / Prompting Acoustic Models for Time Series Classification

This repo contains the source code of our ECCV 2022 paper MS-CLIP:

Neural Rough Differential Equations for Long Time Series (ICML 2021) arXiv

Authors: Jinsung Yoon, Daniel Jarrett, Mihaela van der Schaar

Prathyush Parvatharaju, Ramesh Doddaiah, Tom Hartvigsen, Elke Rundensteiner

This repository contains a Pytorch implementation of the paper:

The implementation of SubdivNet in our paper, Subdivion-based Mesh Convolutional Networks

open review | arXiv | Primary contact: Xu Ma

This is the official PyTorch implementation of RegionCLIP (CVPR 2022).

Swin-Transformer is a deep learning framework designed for training and deploying hierarchical vision transformer models. It serves as a research library and toolkit for computer vision tasks, providing the infrastructure to build models that replace standard convolution operations with sliding window self-attention mechanisms. By utilizing a multi-scale feature hierarchy, the framework enables the processing of visual data at varying resolutions and spatial scales. The project distinguishes itself through its implementation of shifted window partitioning, which facilitates global information

TimeMAE: Self-supervised Representation of Time Series with Decoupled Masked Autoencoders (ACM WSDM2026, Accepted)

Byeongho Heo, Sangdoo Yun, Dongyoon Han, Sanghyuk Chun, Junsuk Choe, Seong Joon Oh | Paper

Chinese-CLIP is a multimodal framework and vision-language model designed for cross-modal retrieval and representation generation using Chinese text and images. It employs a contrastive learning architecture to map visual and textual data into a shared vector space for similarity calculations. The system enables bidirectional search, allowing for text-to-image and image-to-text retrieval. It also provides zero-shot image classification, which identifies objects within images without requiring task-specific training. The project includes tools for fine-tuning pre-trained models on specialized