118 papers with code • 2 benchmarks • 1 datasets

This task has no description! Would you like to contribute one?


Use these libraries to find Re-Ranking models and implementations


Most implemented papers

Learning Discriminative Features with Multiple Granularities for Person Re-Identification

seathiefwang/MGN-pytorch 4 Apr 2018

Instead of learning on semantic regions, we uniformly partition the images into several stripes, and vary the number of parts in different local branches to obtain local feature representations with multiple granularities.

Particular object retrieval with integral max-pooling of CNN activations

almazan/deep-image-retrieval 18 Nov 2015

Recently, image representation built upon Convolutional Neural Network (CNN) has been shown to provide effective descriptors for image search, outperforming pre-CNN features as short-vector representations.

Passage Re-ranking with BERT

nyu-dl/dl4marco-bert 13 Jan 2019

Recently, neural models pretrained on a language modeling task, such as ELMo (Peters et al., 2017), OpenAI GPT (Radford et al., 2018), and BERT (Devlin et al., 2018), have achieved impressive results on various natural language processing tasks such as question-answering and natural language inference.

Document Expansion by Query Prediction

nyu-dl/dl4ir-doc2query 17 Apr 2019

One technique to improve the retrieval effectiveness of a search engine is to expand documents with terms that are related or representative of the documents' content. From the perspective of a question answering system, this might comprise questions the document can potentially answer.

Visual Re-ranking with Natural Language Understanding for Text Spotting

ahmedssabir/Visual-Semantic-Relatedness-with-Word-Embedding 29 Oct 2018

We propose a post-processing approach to improve scene text recognition accuracy by using occurrence probabilities of words (unigram language model), and the semantic correlation between scene and text.

ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT

stanford-futuredata/ColBERT 27 Apr 2020

ColBERT introduces a late interaction architecture that independently encodes the query and the document using BERT and then employs a cheap yet powerful interaction step that models their fine-grained similarity.

Class-Weighted Convolutional Features for Visual Instance Search

imatge-upc/retrieval-2017-cam 9 Jul 2017

In this paper, we go beyond this spatial information and propose a local-aware encoding of convolutional features based on semantic information predicted in the target image.

A Pose-Sensitive Embedding for Person Re-Identification with Expanded Cross Neighborhood Re-Ranking

pse-ecn/pose-sensitive-embedding CVPR 2018

In contrast to the recent direction of explicitly modeling body parts or correcting for misalignment based on these, we show that a rather straightforward inclusion of acquired camera view and/or the detected joint locations into a convolutional neural network helps to learn a very effective representation.

SphereReID: Deep Hypersphere Manifold Embedding for Person Re-Identification

layumi/Person_reID_baseline_pytorch 2 Jul 2018

In this paper, we use a modified softmax function, termed Sphere Softmax, to solve the classification problem and learn a hypersphere manifold embedding simultaneously.