SOTAVerified

Image Retrieval with Multi-Modal Query

The problem of retrieving images from a database based on a multi-modal (image- text) query. Specifically, the query text prompts some modification in the query image and the task is to retrieve images with the desired modifications.

Papers

Showing 110 of 10 papers

TitleStatusHype
Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty RegularizationCode1
Compositional Learning of Image-Text Query for Image RetrievalCode1
Composing Text and Image for Image Retrieval - An Empirical OdysseyCode1
FiLM: Visual Reasoning with a General Conditioning LayerCode1
Automatic Spatially-aware Fashion Concept DiscoveryCode1
Show and Tell: A Neural Image Caption GeneratorCode1
Collaborative Group: Composed Image Retrieval via Consensus Learning from Noisy Annotations0
Attributes as Operators: Factorizing Unseen Attribute-Object CompositionsCode0
A simple neural network module for relational reasoningCode0
Image Question Answering using Convolutional Neural Network with Dynamic Parameter PredictionCode0
Show:102550

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Css-NetRecall@123.4Unverified
2ComposeAERecall@122.8Unverified
3Multi-grained Uncertainty Regularization(MUR)Recall@121.8Unverified
4TIRGRecall@114.1Unverified
5RelationshipRecall@113Unverified
6Show and TellRecall@112.3Unverified
7Param HashingRecall@112.2Unverified
8FashionConceptRecall@16.3Unverified
#ModelMetricClaimedVerifiedStatus
1ComposeAERecall@113.9Unverified
2TIRGRecall@112.2Unverified
3Show and TellRecall@111.9Unverified
4FiLMRecall@110.1Unverified
5Attribute as OperatorRecall@18.8Unverified
#ModelMetricClaimedVerifiedStatus
1ComposeAERecall@1011.8Unverified
2TIRGRecall@103.34Unverified