amazon-science / gluonmm
A library of transformer models for computer vision and multi-modality research
☆49Updated 3 years ago
Related projects ⓘ
Alternatives and complementary repositories for gluonmm
- Learning Representational Invariances for Data-Efficient Action Recognition☆32Updated 3 years ago
- ☆31Updated 3 years ago
- Video Noise Contrastive Estimation☆65Updated 11 months ago
- Video Representation Learning by Recognizing Temporal Transformations. In ECCV, 2020.☆48Updated 3 years ago
- PyTorch Implementation of Region Similarity Representation Learning (ReSim)☆86Updated 3 years ago
- support Large Vocabulary Instance Segmentation (LVIS) dataset for mmdetection☆16Updated 4 years ago
- ☆34Updated 2 years ago
- ☆74Updated 2 years ago
- [arXiv 2020] Video Representation Learning with Visual Tempo Consistency☆24Updated 4 years ago
- Implementation of momentum^2 teacher☆120Updated 3 years ago
- code for our ECCV-2020 paper: Self-supervised Video Representation Learning by Pace Prediction☆99Updated 3 years ago
- PIC Challenge Baseline☆19Updated 5 years ago
- (CVPR 2020) This repo contains code for "PADS: Policy-Adapted Sampling for Visual Similarity Learning", which proposes learnable triplet …☆60Updated 4 years ago
- The 1st place solution of 2022 Ego4d Natural Language Queries.☆32Updated 2 years ago
- A ShuffleBatchNorm layer to shuffle BatchNorm statistics across multiple GPUs☆56Updated 2 years ago
- Pytorch code for Towards Backward-Compatible Representation Learning [CVPR 2020 Oral]☆54Updated 3 years ago
- Code for reproducing experiments in "How Useful is Self-Supervised Pretraining for Visual Tasks?"☆60Updated 3 months ago
- ☆16Updated 4 years ago
- This repository contains the annotations used for evaluating Unsupervised Domain Adaptation on EPIC Kitchens, with individual kitchens us…☆12Updated 4 years ago
- [ECCV 2020] Boundary-Aware Cascade Networks for Temporal Action Segmentation☆84Updated 3 years ago
- code base for vision transformers☆35Updated 2 years ago
- ☆40Updated 2 years ago
- ☆34Updated 2 years ago
- [ECCV2022] New benchmark for evaluating pre-trained model; New supervised contrastive learning framework.☆106Updated 11 months ago
- Contrastive Object-level Pre-training with Spatial Noise Curriculum Learning☆20Updated 2 years ago
- We present a framework for training multi-modal deep learning models on unlabelled video data by forcing the network to learn invariances…☆44Updated 3 years ago
- 1st Place Solution to ECCV-TAO-2020: Detect and Represent Any Object for Tracking☆80Updated 3 years ago
- SoT: Delving Deeper into Classification Head for Transformer☆47Updated 2 years ago