/qingsongedu/ Transformers in Time Series: A Survey
https://github.com/qingsongedu/time-series-transformers-review
To the best of our knowledge, this paper is the first work to comprehensively and systematically summarize the recent advances of Transformers for modeling time series data. Code: https://github.com/qingsongedu/time-series-transformers-review
/deepmind/ From data to functa: Your data point is a function and you can treat it like one
https://github.com/deepmind/functa
A powerful continuous alternative is then to represent these measurements using an implicit neural representation, a neural function trained to output the appropriate measurement value for any input spatial location. Code: https://github.com/deepmind/functa
/western-oc2-lab/ IoT Data Analytics in Dynamic Environments: From An Automated Machine Learning Perspective
https://github.com/western-oc2-lab/automl-implementation-for-static-and-dynamic-data-analytics
Machine Learning (ML) approaches have shown their capacity for IoT data analytics. Code: https://github.com/western-oc2-lab/automl-implementation-for-static-and-dynamic-data-analytics
/huggingface/ Efficient Few-Shot Learning Without Prompts
https://github.com/huggingface/setfit
This simple framework requires no prompts or verbalizers, and achieves high accuracy with orders of magnitude less parameters than existing techniques. Code: https://github.com/huggingface/setfit
/newbeeer/ Poisson Flow Generative Models
https://github.com/newbeeer/poisson_flow
We interpret the data points as electrical charges on the $z=0$ hyperplane in a space augmented with an additional dimension $z$, generating a high-dimensional electric field (the gradient of the solution to Poisson equation). Code: https://github.com/newbeeer/poisson_flow
/williamyang1991/ VToonify: Controllable High-Resolution Portrait Video Style Transfer
https://github.com/williamyang1991/vtoonify
Although a series of successful portrait image toonification models built upon the powerful StyleGAN have been proposed, these image-oriented methods have obvious limitations when applied to videos, such as the fixed frame size, the requirement of face alignment, missing non-facial details and temporal inconsistency. Code: https://github.com/williamyang1991/vtoonify
/minqi824/ ADBench: Anomaly Detection Benchmark
https://github.com/minqi824/adbench
Given a long list of anomaly detection algorithms developed in the last few decades, how do they perform with regard to (i) varying levels of supervision, (ii) different types of anomalies, and (iii) noisy and corrupted data? Code: https://github.com/minqi824/adbench
/megvii-basedetection/ BEVStereo: Enhancing Depth Estimation in Multi-view 3D Object Detection with Dynamic Temporal Stereo
https://github.com/megvii-basedetection/bevstereo
To this end, we introduce an effective temporal stereo method to dynamically select the scale of matching candidates, enable to significantly reduce computation overhead. Code: https://github.com/megvii-basedetection/bevstereo
/huoxiangzuo/ HiFuse: Hierarchical Multi-Scale Feature Fusion Network for Medical Image Classification
https://github.com/huoxiangzuo/HiFuse
A parallel hierarchy of local and global feature blocks is designed to efficiently extract local features and global representations at various semantic scales, with the flexibility to model at different scales and linear computational complexity relevant to image size. Code: https://github.com/huoxiangzuo/HiFuse
/smplbody/ Benchmarking and Analyzing 3D Human Pose and Shape Estimation Beyond Algorithms
https://github.com/smplbody/hmr-benchmarks
Experiments with 10 backbones, ranging from CNNs to transformers, show the knowledge learnt from a proximity task is readily transferable to human mesh recovery. Code: https://github.com/smplbody/hmr-benchmarks
/IDEA-Research/ DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
https://github.com/IDEA-Research/detrex
Compared to other models on the leaderboard, DINO significantly reduces its model size and pre-training data size while achieving better results. Code: https://github.com/IDEA-Research/detrex
/openai/ Robust Speech Recognition via Large-Scale Weak Supervision
https://github.com/openai/whisper
We study the capabilities of speech processing systems trained simply to predict large amounts of transcripts of audio on the internet. Code: https://github.com/openai/whisper
/frozenburning/ Text2Light: Zero-Shot Text-Driven HDR Panorama Generation
https://github.com/frozenburning/text2light
To achieve super-resolution inverse tone mapping, we derive a continuous representation of 360-degree imaging from the LDR panorama as a set of structured latent codes anchored to the sphere. Code: https://github.com/frozenburning/text2light
/kakaobrain/ Plenoxels: Radiance Fields without Neural Networks
https://github.com/kakaobrain/NeRF-Factory
We introduce Plenoxels (plenoptic voxels), a system for photorealistic view synthesis. Code: https://github.com/kakaobrain/NeRF-Factory
/timojl/ Image Segmentation Using Text and Image Prompts
https://github.com/timojl/clipseg
After training on an extended version of the PhraseCut dataset, our system generates a binary segmentation map for an image based on a free-text prompt or on an additional image expressing the query. Code: https://github.com/timojl/clipseg
/jeff-sjtu/ D&D: Learning Human Dynamics from Dynamic Camera
https://github.com/jeff-sjtu/dnd
In this work, we present D&D (Learning Human Dynamics from Dynamic Camera), which leverages the laws of physics to reconstruct 3D human motion from the in-the-wild videos with a moving camera. Code: https://github.com/jeff-sjtu/dnd
/visual-attention-network/ SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation
https://github.com/visual-attention-network/segnext
Notably, SegNeXt outperforms EfficientNet-L2 w/ NAS-FPN and achieves 90. 6% mIoU on the Pascal VOC 2012 test leaderboard using only 1/10 parameters of it. Code: https://github.com/visual-attention-network/segnext
/salesforce/ LAVIS: A Library for Language-Vision Intelligence
https://github.com/salesforce/lavis
We introduce LAVIS, an open-source deep learning library for LAnguage-VISion research and applications. Code: https://github.com/salesforce/lavis
/bgu-cs-vil/ A Deep Moving-camera Background Model
https://github.com/bgu-cs-vil/deepmcbm
Moreover, existing MCBMs usually model the background either on the domain of a typically-large panoramic image or in an online fashion. Code: https://github.com/bgu-cs-vil/deepmcbm
/wilsonjr/ HUMAP: Hierarchical Uniform Manifold Approximation and Projection
https://github.com/wilsonjr/humap
Dimensionality reduction (DR) techniques help analysts to understand patterns in high-dimensional spaces. Code: https://github.com/wilsonjr/humap
/compvis/ High-Resolution Image Synthesis with Latent Diffusion Models
https://github.com/compvis/stable-diffusion
By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. Code: https://github.com/compvis/stable-diffusion
/neuralmagic/ How Well Do Sparse Imagenet Models Transfer?
https://github.com/neuralmagic/deepsparse
Transfer learning is a classic paradigm by which models pretrained on large "upstream" datasets are adapted to yield good results on "downstream" specialized datasets. Code: https://github.com/neuralmagic/deepsparse
/label-sleuth/ Label Sleuth: From Unlabeled Text to a Classifier in a Few Hours
https://github.com/label-sleuth/label-sleuth
Text classification can be useful in many real-world scenarios, saving a lot of time for end users. Code: https://github.com/label-sleuth/label-sleuth
/dauparas/ Robust deep learning based protein sequence design using ProteinMPNN
https://github.com/dauparas/ProteinMPNN
While deep learning has revolutionized protein structure prediction, almost all experimentally characterized de novo protein designs have been generated using physically based approaches such as Rosetta. Code: https://github.com/dauparas/ProteinMPNN
/chenwu98/ Generative Visual Prompt: Unifying Distributional Control of Pre-Trained Generative Models
https://github.com/chenwu98/generative-visual-prompt
We demonstrate how PromptGen can control several generative models (e. g., StyleGAN2, StyleNeRF, diffusion autoencoder, and NVAE) using various off-the-shelf models: (1) with the CLIP model, PromptGen can sample images guided by text, (2) with image classifiers, PromptGen can de-bias generative models across a set of attributes, and (3) with inverse graphics models, PromptGen can sample images of the same identity in different poses. Code: https://github.com/chenwu98/generative-visual-prompt
/Westlake-AI/ OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learning
https://github.com/Westlake-AI/openmixup
With the remarkable progress of deep neural networks in computer vision, data mixing augmentation techniques are widely studied to alleviate problems of degraded generalization when the amount of training data is limited. Code: https://github.com/Westlake-AI/openmixup
/microsoft/ GLIPv2: Unifying Localization and Vision-Language Understanding
https://github.com/microsoft/GLIP
We present GLIPv2, a grounded VL understanding model, that serves both localization tasks (e. g., object detection, instance segmentation) and Vision-Language (VL) understanding tasks (e. g., VQA, image captioning). Code: https://github.com/microsoft/GLIP
/shengyu-meng/ Zero-Shot Text-Guided Object Generation with Dream Fields
https://github.com/shengyu-meng/dreamfields-3D
Our method, Dream Fields, can generate the geometry and color of a wide range of objects without 3D supervision. Code: https://github.com/shengyu-meng/dreamfields-3D
/samuela/ Git Re-Basin: Merging Models modulo Permutation Symmetries
https://github.com/samuela/git-re-basin
Experimentally, we demonstrate the single basin phenomenon across a variety of model architectures and datasets, including the first (to our knowledge) demonstration of zero-barrier linear mode connectivity between independently trained ResNet models on CIFAR-10 and CIFAR-100. Code: https://github.com/samuela/git-re-basin
/MetaSLAM/ General Place Recognition Survey: Towards the Real-world Autonomy Age
https://github.com/MetaSLAM/GPRS
A summary of this work and our datasets and evaluation API is publicly available to the robotics community at: https://github. com/MetaSLAM/GPRS. Code: https://github.com/MetaSLAM/GPRS
/PKU-TANGENT/ Neural Architectures for Named Entity Recognition
https://github.com/PKU-TANGENT/nlp-tutorial
State-of-the-art named entity recognition systems rely heavily on hand-crafted features and domain-specific knowledge in order to learn effectively from the small, supervised training corpora that are available. Code: https://github.com/PKU-TANGENT/nlp-tutorial
/PaddlePaddle/ Parameter-Free Style Projection for Arbitrary Style Transfer
https://github.com/PaddlePaddle/PaddleHub
This paper further presents a real-time feed-forward model to leverage Style Projection for arbitrary image style transfer, which includes a regularization term for matching the semantics between input contents and stylized outputs. Code: https://github.com/PaddlePaddle/PaddleHub
/HybridRobotics/ GenLoco: Generalized Locomotion Controllers for Quadrupedal Robots
https://github.com/HybridRobotics/GenLoco
In this work, we introduce a framework for training generalized locomotion (GenLoco) controllers for quadrupedal robots. Code: https://github.com/HybridRobotics/GenLoco
/adymaharana/ StoryDALL-E: Adapting Pretrained Text-to-Image Transformers for Story Continuation
https://github.com/adymaharana/storydalle
Hence, we first propose the task of story continuation, where the generated visual story is conditioned on a source image, allowing for better generalization to narratives with new characters. Code: https://github.com/adymaharana/storydalle
/tusimple/ CenterFormer: Center-based Transformer for 3D Object Detection
https://github.com/tusimple/centerformer
It then uses the feature of the center candidate as the query embedding in the transformer. Code: https://github.com/tusimple/centerformer
/wyhsirius/ Latent Image Animator: Learning to animate image via latent space navigation
https://github.com/wyhsirius/LIA
Deviating from such models, we here introduce Latent Image Animator (LIA), a self-supervised auto-encoder that evades need for structure representation. Code: https://github.com/wyhsirius/LIA
/athn-nik/ TEACH: Temporal Action Composition for 3D Humans
https://github.com/athn-nik/teach
In particular, our goal is to enable the synthesis of a series of actions, which we refer to as temporal action composition. Code: https://github.com/athn-nik/teach
/YangLing0818/ Diffusion Models: A Comprehensive Survey of Methods and Applications
https://github.com/YangLing0818/Diffusion-Models-Papers-Survey-Taxonomy
Diffusion models are a class of deep generative models that have shown impressive results on various tasks with dense theoretical founding. Code: https://github.com/YangLing0818/Diffusion-Models-Papers-Survey-Taxonomy
/Felix-Petersen/ Monotonic Differentiable Sorting Networks
https://github.com/Felix-Petersen/diffsort
We introduce a family of sigmoid functions and prove that they produce differentiable sorting networks that are monotonic. Code: https://github.com/Felix-Petersen/diffsort
/BoyanJIANG/ LoRD: Local 4D Implicit Representation for High-Fidelity Dynamic Human Modeling
https://github.com/BoyanJIANG/LoRD
Recent progress in 4D implicit representation focuses on globally controlling the shape and motion with low dimensional latent vectors, which is prone to missing surface details and accumulating tracking error. Code: https://github.com/BoyanJIANG/LoRD
/hancyran/ Surface Representation for Point Clouds
https://github.com/hancyran/RepSurf
Based on a simple baseline of PointNet++ (SSG version), Umbrella RepSurf surpasses the previous state-of-the-art by a large margin for classification, segmentation and detection on various benchmarks in terms of performance and efficiency. Code: https://github.com/hancyran/RepSurf
/taichi-dev/ DiffTaichi: Differentiable Programming for Physical Simulation
https://github.com/taichi-dev/taichi
We present DiffTaichi, a new differentiable programming language tailored for building high-performance differentiable physical simulators. Code: https://github.com/taichi-dev/taichi
/aharley/ Particle Video Revisited: Tracking Through Occlusions Using Point Trajectories
https://github.com/aharley/pips
In this paper, we revisit Sand and Teller's "particle video" approach, and study pixel tracking as a long-range motion estimation problem, where every pixel is described with a trajectory that locates it in multiple future frames. Code: https://github.com/aharley/pips
/zju-vipa/ A Survey of Neural Trees
https://github.com/zju-vipa/awesome-neural-trees
This survey aims to present a comprehensive review of NTs and attempts to identify how they enhance the model interpretability. Code: https://github.com/zju-vipa/awesome-neural-trees
/FedML-AI/ FedML: A Research Library and Benchmark for Federated Machine Learning
https://github.com/FedML-AI/FedML
Federated learning (FL) is a rapidly growing research field in machine learning. Code: https://github.com/FedML-AI/FedML
/coqui-ai/ YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone
https://github.com/coqui-ai/TTS
YourTTS brings the power of a multilingual approach to the task of zero-shot multi-speaker TTS. Code: https://github.com/coqui-ai/TTS
/duxiaodan/ Text-Free Learning of a Natural Language Interface for Pretrained Face Generators
https://github.com/duxiaodan/fast_text2stylegan
We propose Fast text2StyleGAN, a natural language interface that adapts pre-trained GANs for text-guided human face synthesis. Code: https://github.com/duxiaodan/fast_text2stylegan
/hkunlp/ Selective Annotation Makes Language Models Better Few-Shot Learners
https://github.com/hkunlp/icl-selective-annotation
Departing from recent in-context learning methods, we formulate an annotation-efficient, two-step framework: selective annotation that chooses a pool of examples to annotate from unlabeled data in advance, followed by prompt retrieval that retrieves task examples from the annotated pool at test time. Code: https://github.com/hkunlp/icl-selective-annotation
/BehaviorTree/ Behavior Trees in Robotics and AI: An Introduction
https://github.com/BehaviorTree/BehaviorTree.CPP
A Behavior Tree (BT) is a way to structure the switching between different tasks in an autonomous agent, such as a robot or a virtual entity in a computer game. Code: https://github.com/BehaviorTree/BehaviorTree.CPP
/aangelopoulos/ A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification
https://github.com/aangelopoulos/conformal-prediction
Conformal prediction is a user-friendly paradigm for creating statistically rigorous uncertainty sets/intervals for the predictions of such models. Code: https://github.com/aangelopoulos/conformal-prediction