Towhee is a framework that is dedicated to making neural data processing...
Video Foundation Models & Data for Multimodal Understanding
Video embeddings for retrieval with natural language queries
[NeurIPS 2021] Moment-DETR code and QVHighlights dataset
Authors official PyTorch implementation of the "ViSiL: Fine-grained Spat...
[ECCV 2020] PyTorch code for XML on TVRetrieval dataset - TVR: A Large-S...
A PyTorch implementation of VIOLET
Authors official Tensorflow implementation of the "Near-Duplicate Video ...
Authors official PyTorch implementation of the "DnS: Distill-and-Select ...
Video-aided Unsupervised Grammar Induction, NAACL‘21 [best long paper]
Near Duplicate Video Retrieval