cgh's repositories
CAFNet
IEEE Transactions on Affective Computing 2023
causal-impact-index
This is the repo for our work on "Causal Impact Index" as a better metric than citations.
CLIP4STR
An implementation of "CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model".
Contrastive-Hierarchical-Clustering
This is the official code for the paper Contrastive Hierarchical Clustering (ECML PKDD 2023)
DeepSolo
The official repo for [CVPR'23] "DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting" & [ArXiv'23] "DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Text Spotting"
DFER-CLIP
[BMVC'23] Prompting Visual-Language Models for Dynamic Facial Expression Recognition
DPText-DETR
[AAAI 2023 Oral] DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer
EmoNeXt
Code for the paper: "EmoNeXt: an Adapted ConvNeXt for Facial Emotion Recognition"
FacialMMT
Code for paper "A Facial Expression-Aware Multimodal Multi-task Learning Framework for Emotion Recognition in Multi-party Conversations"
gpt4v-emotion
GPT-4V with Emotion
MARCONet
Learning Generative Structure Prior for Blind Text Image Super-resolution [CVPR 2023]
MixPro
🔥MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision Transformer [Official, ICLR 2023]
SEAM
Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation, CVPR 2020 (Oral)
SEQ_HGNN
Seq-HGNN: Learning Sequential Node Representation on Heterogeneous Graph
SSR_BMVC2022
SSR: An Efficient and Robust Framework for Learning with Unknown Label Noise (BMVC2022)
SwinTextSpotter
Pytorch re-implementation of Paper: SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition (CVPR 2022)
TCL
Twin Contrastive Learning with Noisy Labels (CVPR 2023)
TCM
Turning a CLIP Model into a Scene Text Detector (CVPR2023)
TextPMs
Arbitrary Shape Text Detection via Segmentation with Probability Maps; accepted by TPAMI2022
TPGSR
Code for Text Prior Guided Scene Text Image Super-Resolution (TIP 2023)
Union14M
[ICCV 2023] Code base for Revisiting Scene Text Recognition: A Data Perspective
visprog
Official code for VisProg (CVPR 2023 Best Paper!)