Tencent YouTu Research's repositories
AnomalyDetection-SoftPatch
Code for NeurIPS 2022 paper "SoftKernel: Unsupervised Anomaly Detection with Noisy Data"
CrowdCounting-P2PNet
The official codes for the ICCV2021 Oral presentation "Rethinking Counting and Localization in Crowds: A Purely Point-Based Framework"
OpenWorld-DeepFakeAttribution
Code for ICCV 2023 paper "Contrastive Pseudo Learning for Open-World DeepFake Attribution"
PersonRetrieval-IVT
Code for ECCV 2022 Workshop paper "See Finer, See More: Implicit Modality Alignment for Text-based Person Retrieval"
AnomalyDetection-M3DM
Code for CVPR 2023 paper "Multimodal Industrial Anomaly Detection via Hybrid Fusion"
AdaMatcher
Code for CVPR2023 paper:Adaptive Assignment for Geometry Aware Local Feature Matching
HighlightDetection-CLC
Code for CVPR2023 paper "Collaborative Noisy Label Cleaner: Learning Scene-aware Trailers for Multi-modal Highlight Detection in Movies"
SceneSegmentation-SCRL
Code for CVPR 2022 paper "Scene Consistency Representation Learning for Video Scene Segmentation"
ImageColorization-ColorFormer
Code for ECCV 2022 paper "ColorFormer: Image Colorization via Color Memory assisted Hybrid-attention Transformer"
FaceRestoration-sgpn
Code for CVPR 2022 paper "Blind Face Restoration via Integrating Face Shape and Generative Priors"
FewShotLearning-tSF
Code for ECCV 2022 paper "tSF: Transformer-based Semantic Filter for Few-Shot Learning"
HeadSynthesis-HifiHead
Code for IJCAI-22 paper "HifiHead: One-Shot High Fidelity Neural Head Synthesis with 3D Control"
Classification-SemiCLS
Code for CVPR 2022 paper “Class-Aware Contrastive Semi-Supervised Learning”
Adv-Makeup
This project is an implementation of our IJCAI 2021 paper "Adv-Makeup: A New Imperceptible and Transferable Attack on Face Recognition", we propose a novel attacking form for the face recognition to synthesize the transferable and imperceptible adversarial examples.
PersonReID-ACT
Code for AAAI 2020 paper "Asymmetric Co-Teaching for Unsupervised Cross Domain Person Re-Identification"
ActionDetection-LSTC
LSTC: Boosting Atomic Action Detection with Long-Short-Term Context
VPLOW_CLEAR22
Code for CVPR 2022 CLEAR Challenge "This repository is the CLEAR Challenge 1st place methods for CVPR 2022 Workshop on Visual Perception and Learning in an Open World"
EventExtraction-RAAT
Code for NAACL 2022 paper (Main Track) "RAAT: Relation-Augmented Attention Transformer for Relation Modeling in Document-Level Event Extraction"
MultiLabel-HML
Code for ECCV 2022 paper "Hyperspherical Learning in Multi-Label Classification"
ImageMatching-OETR
This is the official implementation in PyTorch for AAAI2022 paperGuide Local Feature Matching by Overlap Estimation and also contain a image matching toolbox.
VisualRecognition-NomMer
Code for CVPR 2022 paper "NomMer: Nominate Synergistic Context in Vision Transformer for Visual Recognition"
BaseArchitecture-EAT
Official pytorch implementation of the paper "Analogous to Evolutionary Algorithm: Designing a Unified Sequence Model, NeurIPS'21".
ActiveLearning-SDM
Implementation of CVPR 2022 paper "Learning Distinctive Margin toward Active Domain Adaptation”
HIG-GraphClassification
Code of Heterogeneous interpolation on graph, which is a solution for OGB challenge
ActionDetection-AFSD
Code for CVPR2021 paper "Learning Salient Boundary Feature for Anchor-free Temporal Action Localization"
CrowdCounting-UEPNet
The official codes for the ICCV2021 presentation "Uniformity in Heterogeneity: Diving Deep into Count Interval Partition for Crowd Counting"