ALBench: A Framework for Evaluating Active Learning in Object Detection

An active learning benchmark framework named as ALBench for evaluating active learning in object detection.

Github: https://github.com/industryessentials/ymir

Paper: https://arxiv.org/abs/2207.13339v1

Projects: https://github.com/IndustryEssentials/ymir/projects

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

👉 @bigdata_1

Deep Deformable 3D Caricature with Learned Shape Control (DD3C)

Github: https://github.com/ycjungsubhuman/deepdeformable3dcaricatures

Paper: https://arxiv.org/abs/2207.14593v1

Project: https://ycjungsubhuman.github.io/DeepDeformable3DCaricatures

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

Video: https://youtu.be/WLMPEaK6E4M

👉 @bigdata_1

CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation

Github: https://github.com/huawei-noah/noah-research/tree/master/CLIFF

Paper: https://arxiv.org/abs/2208.00571v1

Pretrained checkpoints : https://drive.google.com/drive/folders/1EmSZwaDULhT9m1VvH7YOpCXwBWgYrgwP

Dataset: https://paperswithcode.com/dataset/human3-6m

👉 @bigdata_1

Expanding Language-Image Pretrained Models for General Video Recognition by Microsoft.

Video-specific prompting scheme, which leverages video content information for generating discriminative textual prompts.

Github: https://github.com/microsoft/VideoX/tree/master/X-CLIP

Paper: https://arxiv.org/abs/2208.02816v1

Dataset: https://paperswithcode.com/dataset/ucf101

👉 @bigdata_1

Prompt Tuning for Generative Multimodal Pretrained Models

Github: https://github.com/ofa-sys/ofa

Paper: https://arxiv.org/abs/2208.02532v1

Dataset: https://paperswithcode.com/dataset/snli-ve

Demo: https://huggingface.co/spaces/OFA-Sys/OFA-Generic_Interface

👉 @bigdata_1

P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Prompting

Github: https://github.com/wangzy22/P2P

Paper: https://arxiv.org/abs/2208.02812v1

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

Model: https://shapenet.cs.stanford.edu/media/modelnet40_normal_resampled.zip

👉 @bigdata_1

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