UniverseNet

UniverseNet is the state-of-the-art detector that can be trained in 24 epochs.

Github: https://github.com/shinya7y/UniverseNet

Paper: https://arxiv.org/abs/2103.14027v1

👉 @bigdata_1

TransT - Transformer Tracking

Github: https://github.com/chenxin-dlut/TransT

Paper: https://arxiv.org/abs/2103.15436

Model: https://drive.google.com/drive/folders/1GVQV1GoW-ttDJRRqaVAtLUtubtgLhWCE

👉 @bigdata_1

Animesion

DAF:RE: A CHALLENGING, CROWD-SOURCED, LARGE-SCALE, LONG-TAILED
DATASET FOR ANIME CHARACTER RECOGNITION

Code:https://github.com/arkel23/animesion

Paper: https://arxiv.org/abs/2101.08674v1

👉 @bigdata_1

Hyperbolic Graph Convolutional Auto-Encoders

Github: https://github.com/junhocho/HGCAE

Paper: https://arxiv.org/abs/2103.16046

👉 @bigdata_1

Self-Adaptive Training

Github: https://github.com/LayneH/self-adaptive-training

Paper: https://arxiv.org/abs/2101.08732v1

👉 @bigdata_1

⚡️ NeX: Real-time View Synthesis with Neural Basis Expansion

Github: https://github.com/nex-mpi/nex-code

Real-time View Synthesis with Python Code: https://analyticsindiamag.com/what-is-nex-guide-to-real-time-view-synthesis-with-python-code/

Project: https://nex-mpi.github.io/

Paper: https://arxiv.org/pdf/2103.05606.pdf

Video: https://www.youtube.com/watch?v=HyfkF7Z-ddA&ab_channel=SupasornSuwajanakorn

👉 @bigdata_1

The Ultimate Scikit-Learn Machine Learning Cheatsheet

https://www.kdnuggets.com/2021/01/ultimate-scikit-learn-machine-learning-cheatsheet.html

👉 @bigdata_1

EasyMocap is an open-source toolbox for markerless human motion capture from RGB videos

Github: https://github.com/zju3dv/EasyMocap

Paper: https://arxiv.org/abs/2104.00340v1

👉 @bigdata_1

👁 Learning Spatio-Temporal Transformer for Visual Tracking

Github: https://github.com/researchmm/Stark

Paper: https://arxiv.org/abs/2103.17154v1

👉 @bigdata_1

Audio-Visual Event Localization in Unconstrained Videos

https://sites.google.com/view/audiovisualresearch

Github: https://github.com/YapengTian/AVE-ECCV18

Paper: https://arxiv.org/abs/1803.08842

👉 @bigdata_1

Regularizing Generative Adversarial Networks under Limited Data

Github: https://github.com/google/lecam-gan

Paper: https://arxiv.org/abs/2104.03310

https://hytseng0509.github.io/lecam-gan/

👉 @bigdata_1

🦏 DoubleML - Double Machine Learning in Python

Github: https://github.com/DoubleML/doubleml-for-py

Paper: https://arxiv.org/abs/2104.03220v1

Docs: https://docs.doubleml.org/stable/index.html


👉 @bigdata_1

Summarising Historical Text in Modern Languages

Github: https://github.com/Pzoom522/HistSumm

Paper: https://arxiv.org/abs/2101.10759v2

👉 @bigdata_1

💬 New Facebook's Casual Conversations Dataset over 45,000 videos

Dataset: https://ai.facebook.com/datasets/casual-conversations-dataset/

Paper: https://ai.facebook.com/blog/shedding-light-on-fairness-in-ai-with-a-new-data-set/

👉 @bigdata_1

Generalising via Meta-Examples for Continual Learning in the Wild

Github: https://github.com/alessiabertugli/FUSION

Article: https://arxiv.org/abs/2101.12081v1

👉 @bigdata_1

Implicit Neural Representations with Periodic Activation Functions

Github: https://github.com/lucidrains/siren-pytorch

Paper: https://arxiv.org/abs/2006.09661

👉 @bigdata_1

Playable Video Generation

Github: https://github.com/willi-menapace/PlayableVideoGeneration

Paper: https://arxiv.org/abs/2101.12195

👉 @bigdata_1

PaddleGAN provides developers with high-performance implementation of classic and SOTA Generative Adversarial Networks

Github: https://github.com/PaddlePaddle/PaddleGAN

Paper: https://arxiv.org/abs/2104.05376v1

👉 @bigdata_1

Hands-on Guide to OpenAI’s CLIP – Connecting Text To Images

https://analyticsindiamag.com/hands-on-guide-to-openais-clip-connecting-text-to-images/

👉 @bigdata_1

🧠 Lite-HRNet: A Lightweight High-Resolution Network

Github: https://github.com/HRNet/Lite-HRNet

Paper: https://arxiv.org/abs/2104.06403

👉 @bigdata_1