Browse SoTA > Computer Vision > Image Retrieval > Text-Image Retrieval

Text-Image Retrieval

5 papers with code · Computer Vision
Subtask of Image Retrieval

It include two tasks: (1) Image as Query and Text as Targets; (2) Text as Query and Image as Targets.

Benchmarks

Greatest papers with code

Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks

ECCV 2020 microsoft/Oscar

Large-scale pre-training methods of learning cross-modal representations on image-text pairs are becoming popular for vision-language tasks.

IMAGE CAPTIONING TEXT-IMAGE RETRIEVAL VISUAL QUESTION ANSWERING

SoDeep: a Sorting Deep net to learn ranking loss surrogates

CVPR 2019 technicolor-research/sodeep

Our approach is based on a deep architecture that approximates the sorting of arbitrary sets of scores.

IMAGE CLASSIFICATION TEXT-IMAGE RETRIEVAL

Deep Visual-Semantic Alignments for Generating Image Descriptions

CVPR 2015 VinitSR7/Image-Caption-Generation

Our approach leverages datasets of images and their sentence descriptions to learn about the inter-modal correspondences between language and visual data.

IMAGE CAPTIONING TEXT-IMAGE RETRIEVAL