yekeren Goto Github PK

ads-kb

Implementation of the WACV21 paper "Breaking Shortcuts by Masking for Robust Visual Reasoning"

advise-image_ads_understanding

ADVISE model for the Automatic Understanding of Visual Advertisements challenge. Please refer to our ECCV paper "ADVISE: Symbolism and External Knowledge for Decoding Advertisements".

bert

TensorFlow code and pre-trained models for BERT

best_checkpoint_copier

Tensorflow Exporter that copies the best checkpoints

c2-action-detection

Evaluation measures for the EPIC-KITCHENS-100 Action Detection challenge

cap2det

Implementation of our ICCV 2019 paper "Cap2Det: Learning to AmplifyWeak Caption Supervision for Object Detection"

covid-19-open-data

Datasets of daily time-series data related to COVID-19 for over 20,000 distinct locations around the world.

cs2510_minigoogle

cs2510_rpc

A RPC library implemented in C++. We implemented a stub generator for automatically generating client stub and server stub codes.

ovr-cnn

A new framework for open-vocabulary object detection, based on maskrcnn-benchmark

story-video_ads_understanding

LSTM/BOF model to encode Videos. Implementation of our BMVC paper "Story Understanding in Video Advertisements".

swinir

SwinIR: Image Restoration Using Swin Transformer (official repository)

tensorflow

Computation using data flow graphs for scalable machine learning

tensorflow_models

Models and examples built with TensorFlow

textzoom

A super-resolution dataset of paired LR-HR scene text images

vcr

vcr-shortcut-effects-study

Code and data of our AAAI2021 paper "A Case Study of the Shortcut Effects in Visual Commonsense Reasoning"

video_ads_understanding

ws-ek100

wsod

wssgg

A weakly-supervised scene graph generation codebase. The implementation of our CVPR2021 paper ``Linguistic Structures as Weak Supervision for Visual Scene Graph Generation''