JoeHEZHAO

beyond-confidence-atypicality

Repository for the NeurIPS 2023 paper "Beyond Confidence: Reliable Models Should Also Consider Atypicality"

lamp

PyTorch implementation of the paper "Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning", NeurIPS 2023

Track-Anything

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

awesome-self-supervised-multimodal-learning

A curated list of self-supervised multimodal learning resources.

videowalk

Repository for "Space-Time Correspondence as a Contrastive Random Walk" (NeurIPS 2020)

day-to-night

class-balanced-loss

Class-Balanced Loss Based on Effective Number of Samples. CVPR 2019

BDQ_PrivacyAR

vpa

Towards a Visual Privacy Advisor: Understanding and Predicting Risks in Images, ICCV '17

PA-HMDB51

[TPAMI 2020] "Privacy-Preserving Deep Action Recognition: An Adversarial Learning Framework and A New Dataset" by Zhenyu Wu, Haotao Wang, Zhaowen Wang, Hailin Jin, and Zhangyang Wang

Privacy-AdversarialLearning

[ECCV 2018] Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Study

alm-dnn

Constrained Optimization to Train Neural Networks on Critical and Under-Represented Classes [NeurIPS2021]

LibAUC

LibAUC: A Deep Learning Library for X-Risk Optimization

noise_flow

Noise Flow: Noise Modeling with Conditional Normalizing Flows

DEAR

[ICCV 2021 Oral] Deep Evidential Action Recognition

Importance_Weighted_Autoencoders

A PyTorch Implementation of the Importance Weighted Autoencoders

progressive-action-prediction

[CVPR 2023] Code for action prediction from videos

EgoProceL-egocentric-procedure-learning

Code implementation for our ECCV, 2022 paper titled "My View is the Best View: Procedure Learning from Egocentric Videos"

igr

AppearanceFreeActionRecognition

[ECCV 2022] Is Appearance Free Action Recognition Possible?

SPAct

Official code repository for SPAct: Self-supervised Privacy Preservation for Action Recognition [CVPR-2022]

ReferFormer

[CVPR2022] Official Implementation of ReferFormer

CVAE-GAN-zoos-PyTorch-Beginner

For beginner, this will be the best start for VAEs, GANs, and CVAE-GAN. This contains AE, DAE, VAE, GAN, CGAN, DCGAN, WGAN, WGAN-GP, VAE-GAN, CVAE-GAN. All use PyTorch.

CVPR22-POC

Official Repo for CVPR 2022 Paper "Set-Supervised Action Learning in Procedural Videos via Pairwise Order Consistency"

VT-TWINS

Video-Text Representation Learning via Differentiable Weak Temporal Alignment (PyTorch implementation for the CVPR 2022 paper)

EasyOCR

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

NSVA

The official implementation of our paper "Sports Video Analysis on Large-scale Data" (https://arxiv.org/abs/2208.04897)

LMC-Memory

Official PyTorch implementation of "Video Prediction Recalling Long-term Motion Context via Memory Alignment Learning" (CVPR 2021 Oral)

FUTR

Future Transformer for Long-term Action Anticipation (CVPR 2022)

FC-Net

The official pytorch implementation of the MICCAI 2021 paper "Distinguishing Differences Matters: Focal Contrastive Network for Peripheral Anterior Synechiae Recognition"