Per-Clip Video Object Segmentation

Progressive matching mechanism for efficient information-passing within a clip.

Github: https://github.com/pkyong95/PCVOS

Paper: https://arxiv.org/abs/2208.01924v1

Dataset: https://paperswithcode.com/dataset/davis

Video: https://youtu.be/6QATHDwrUx0

👉 @bigdata_1

Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers

Github: https://github.com/lkeab/BCNet

Paper: https://arxiv.org/abs/2208.04438v1

Dataset: https://paperswithcode.com/dataset/bdd100k

Video: https://www.youtube.com/watch?v=iHlGJppJGiQ

👉 @bigdata_1

LAMDA-SSL: Semi-Supervised Learning in Python


Github: https://github.com/ygzwqzd/lamda-ssl

Paper: https://arxiv.org/pdf/2208.04610.pdf

Docs: https://ygzwqzd.github.io/LAMDA-SSL

👉 @bigdata_1

ROC: A New Paradigm for Lyric-to-Melody Generation

Muzic is a research project on AI music that empowers music understanding and generation with deep learning and artificial intelligence.

Github: https://github.com/microsoft/muzic

Paper: https://arxiv.org/abs/2208.05697v1

Project: https://www.microsoft.com/en-us/research/project/ai-music/

👉 @bigdata_1

Speech Enhancement and Dereverberation with Diffusion-based Generative Models

Github: https://github.com/sp-uhh/sgmse

Paper: https://arxiv.org/abs/2208.05830v1

Pretrained checkpoints: https://drive.google.com/drive/folders/1CSnkhUSoiv3RG0xg7WEcVapyLuwDaLbe?usp=sharing

👉 @bigdata_1

StyleFaceV - Official PyTorch Implementation

StyleFaceV produces high-fidelity identity-preserving face videos with vivid movements

Github: https://github.com/arthur-qiu/stylefacev

Project: http://haonanqiu.com/projects/StyleFaceV.html

Video: https://youtu.be/BZNLcD04-Fc

Paper: https://arxiv.org/abs/2208.07862v1

Dataset: https://paperswithcode.com/dataset/faceforensics-1

👉 @bigdata_1

Unifying Visual Perception by Dispersible Points Learning

Conceptually simple, flexible, and universal visual perception head for variant visual task

Github: https://github.com/sense-x/unihead

Paper: https://arxiv.org/abs/2208.08630v1

Model: https://drive.google.com/file/d/1TwFCog_PMd1HWA7s-s9pN2F_fgyMyR3x/view

Datasets: https://paperswithcode.com/dataset/imagenet

👉 @bigdata_1

Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise

Github: https://github.com/arpitbansal297/cold-diffusion-models

Paper: https://arxiv.org/abs/2208.09392v1

Cold-Diffusion: https://arxiv.org/abs/2208.09392

Datasets: https://paperswithcode.com/dataset/celeba

👉 @bigdata_1

Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks

Masked "language" modeling on images (Imglish), texts (English), and image-text pairs ("parallel sentences") in a unified manner.

Github: https://github.com/microsoft/unilm/tree/master/beit

Paper: https://arxiv.org/abs/2208.10442v1

Datasets: https://paperswithcode.com/dataset/visual-genome

👉 @bigdata_1

Awesome-Dataset-Distillation

Github: https://github.com/Guang000/Awesome-Dataset-Distillation

Awesome Computer Vision: https://github.com/jbhuang0604/awesome-computer-vision

Paper: https://arxiv.org/abs/2208.11311v1

Datasets: https://paperswithcode.com/dataset/cifar-10

👉 @bigdata_1

YOLOX-PAI: An Improved YOLOX Version by PAI

Github: https://github.com/alibaba/EasyCV

Paper: https://arxiv.org/abs/2208.13040v1

Datasets: https://paperswithcode.com/dataset/coco

👉 @bigdata_1

Self-Supervised Pyramid Representation Learning
for Multi-Label Visual Analysis and Beyond

Github: https://github.com/wesleyhsieh0806/ss-prl

Paper: https://arxiv.org/abs/2208.14439v1

Datasets: https://github.com/wesleyhsieh0806/ss-prl#books-prepare-dataset

Downstream: http://host.robots.ox.ac.uk/pascal/VOC/

👉 @bigdata_1

PyTorch Image Quality (PIQ) is a collection of measures and metrics for image quality assessment.

$ pip install piq

Github: https://github.com/photosynthesis-team/piq

Paper: https://arxiv.org/abs/2208.14818v1

Docs: https://piq.readthedocs.io.

Datasets: https://paperswithcode.com/dataset/kadid-10k

👉 @bigdata_1

2BiVQA: Double Bi-LSTM based Video Quality Assessment of UGC Videos

Github: https://github.com/atelili/2bivqa

Paper: https://arxiv.org/abs/2208.14774v1

Dataset: https://paperswithcode.com/dataset/live-vqc

Tasks: https://paperswithcode.com/task/video-quality-assessment

👉 @bigdata_1

Map-free Visual Relocalization: Metric Pose Relative to a Single Image

⚙️Github: https://github.com/nianticlabs/map-free-reloc

📄Paper: https://arxiv.org/abs/2210.05494v1

Project: https://research.nianticlabs.com/mapfree-reloc-benchmark

🗒Dataset: https://paperswithcode.com/dataset/kitti

👉 @bigdata_1

Bayesian Optimisation & Reinforcement Learning Research

pip install HEBO

Github: https://github.com/huawei-noah/HEBO

🗒 Docs: https://hebo.readthedocs.io/en/latest/

T-LBO: https://github.com/huawei-noah/HEBO/blob/master/T-LBO

Reinforcement Learning Research : https://github.com/huawei-noah/HEBO/tree/master/SAUTE

👉 @bigdata_1

PDEBENCH: An Extensive Benchmark for Scientific Machine Learning

Github: https://github.com/pdebench/pdebench

🗒 Paper: https://arxiv.org/abs/2210.07182v1

Dataset https://darus.uni-stuttgart.de/dataset.xhtml?persistentId=doi:10.18419/darus-2986

Pre-Trained Models : https://darus.uni-stuttgart.de/dataset.xhtml?persistentId=doi:10.18419/darus-2987

👉 @bigdata_1

Benchmarking ML for MD simulation

Molecular dynamics simulation with machine learning force fields.

Github: https://github.com/kyonofx/mdsim

🗒 Paper: https://arxiv.org/abs/2210.07237v1

Guide: https://github.com/kyonofx/mdsim#install-other-dependencies

Dataset: https://paperswithcode.com/dataset/md17

👉 @bigdata_1

LAVIS - A Library for Language-Vision Intelligence

LAVIS is a Python deep learning library for LAnguage-and-VISion intelligence research and applications.

git clone https://github.com/salesforce/LAVIS.git
cd LAVIS
pip install .

Github: https://github.com/salesforce/lavis

🗒 Paper: https://arxiv.org/abs/2210.08773v1

Models: https://github.com/salesforce/LAVIS/tree/main/examples

Docs: https://opensource.salesforce.com/LAVIS//latest/index.html

Dataset: https://paperswithcode.com/dataset/ok-vqa

👉 @bigdata_1

Towards Realistic Low-resource Relation Extraction: A Benchmark with Empirical Baseline Study

conda create -n knowprompt python=3.8

conda activate knowprompt

Github: https://github.com/zjunlp/KnowPrompt

🗒 Paper: https://arxiv.org/abs/2210.10678v1

Dataset: https://github.com/zjunlp/KnowPrompt/blob/master/dataset/semeval

👉 @bigdata_1

MetaFormer Baselines for Vision

Github: https://github.com/sail-sg/metaformer

🗒 Paper: https://arxiv.org/abs/2210.13452v1

Dataset: https://paperswithcode.com/dataset/imagenet

👉 @bigdata_1