6 results found Sort:
- Filter by Primary Language:
- Python (4)
- Jupyter Notebook (2)
- +
A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.
Created
2021-01-18
434 commits to main branch, last one about a year ago
[ECCV2024] Video Foundation Models & Data for Multimodal Understanding
benchmark
multimodal
video-clip
video-data
video-dataset
self-supervised
video-retrieval
foundation-models
action-recognition
instruction-tuning
masked-autoencoder
vision-transformer
video-understanding
zero-shot-retrieval
contrastive-learning
open-set-recognition
video-question-answering
zero-shot-classification
temporal-action-localization
spatio-temporal-action-localization
Created
2022-11-23
229 commits to main branch, last one 10 days ago
official code of “OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding”
Created
2023-05-18
26 commits to master branch, last one 11 months ago
Reproducible scaling laws for contrastive language-image learning (https://arxiv.org/abs/2212.07143)
Created
2022-12-13
54 commits to master branch, last one about a year ago
[EMNLP 2022] This is the code repo for our EMNLP‘22 paper "COCO-DR: Combating Distribution Shifts in Zero-Shot Dense Retrieval with Contrastive and Distributionally Robust Learning".
Created
2022-10-26
30 commits to main branch, last one about a year ago
Evaluate custom and HuggingFace text-to-image/zero-shot-image-classification models like CLIP, SigLIP, DFN5B, and EVA-CLIP. Metrics include Zero-shot accuracy, Linear Probe, Image retrieval, and KNN ...
Created
2024-02-09
89 commits to main branch, last one 4 months ago