Cross-modal_Retrieval_Tutorial

The tutorial of Cross-Modal Matching will be constantly updated for Preliminary Insight !

Logupdate

Section Updating

【2021.12.11】 A new section named [Video-Text Learning] has been added.
【2021.11.17】 A new section named [RSTPReid] has been added.
【2021.08.24】 A new section named [ICFG-PEDES] has been added.
【2021.07.10】 A new section named [Vision-Language Pretraining] has been added.

Paper Updating

【2022.04.15】 Pretrained works UniT, ViT-BERT, Frozen, PromptFuse, GLUE, CMKT, VLKD, X-VLM, LoopITR, DemoVLP, ViSTA, CoCo-BERT, X-Pool and Conventional works RELAX, SVSEN, GraDual, CMCAN, ALGCN, DAGNN, DAQN, DLMLG, UARDA, CGMN, TSHSR, VRACR, VSRN++ and Datasets & Surveys ECCVCaption, CxC, Survey have been added.
【2021.12.11】 Pretrained works ActBERT, DeCLIP, TAGS, FILIP, LiT, Florence, OATransformer, RegionLearner and Conventional works MEMBER, MRL, NCR, LESS, SwAMP, ISERI have been added.
【2021.11.17】 Pretrained works TDMR, VLDeformer, CAMoE, MURAL, KD-VLP, DistillVLM, VLMO, ALBEF, SimVLM, CLIP2Video, CLIP2TV and Conventional works WCGL, LapsCore, AACH, CSCC, Meta-SPN, DSSL, SAM, SSAMT, IMRL have been added.
【2021.08.24】 Pretrained works ClipBERT, UC2, LightingDOT, GilBERT, SOHO and Conventional works OLVSEM, SSP, HEI, SSAN, MGEL, SMFEA, HAN, CAEMCL, A-GANet, CMAAM have been added.

Catalogue

• Peformance Comparison

  • Flickr8K
  • Flickr30K
  • MSCOCO1K
  • MSCOCO5K
  • RSTPReid
  • CUHK-PEDES
  • ICFG-PEDES
  • CUB-Flowers

• Methods Summary

  • Vision-Language Pretraining
  • Generic-Feature Extraction
  • Cross-Modal Interaction
  • Similarity Measurement
  • Commonsense Learning
  • Adversarial Learning
  • Loss Function
  • Un-/Semi-Supervised
  • Zero-/Fewer-Shot
  • Identification Learning
  • Video-Text Learning
  • Scene-Text Learning
  • Related Works
  • Posted in

• Other Resources

  • Multimodal Learning
  • Graph Learning
  • Fewshot Learning

License

MIT license. If any questions, please contact me at [email protected].