Search Results for author: Jiangbo Yuan

Found 6 papers, 2 papers with code

eProduct: A Million-Scale Visual Search Benchmark to Address Product Recognition Challenges

no code implementations13 Jul 2021 Jiangbo Yuan, An-Ti Chiang, Wen Tang, Antonio Haro

This motivated creation of eProduct, a dataset consisting of 2. 5 million product images towards accelerating development in the areas of self-supervised learning, weakly-supervised learning, and multimodal learning, for fine-grained recognition.

Self-Supervised Learning

Instance-level Image Retrieval using Reranking Transformers

1 code implementation ICCV 2021 Fuwen Tan, Jiangbo Yuan, Vicente Ordonez

Instance-level image retrieval is the task of searching in a large database for images that match an object in a query image.

Image Retrieval

Learning Tuple Compatibility for Conditional OutfitRecommendation

no code implementations18 Aug 2020 Xuewen Yang, Dongliang Xie, Xin Wang, Jiangbo Yuan, Wanying Ding, Pengyun Yan

Our contributions include: 1) Designing a Mixed Category Attention Net (MCAN) which integrates both fine-grained and coarse category information into recommendation and learns the compatibility among fashion tuples.

Recommendation Systems

Adversarial Code Learning for Image Generation

no code implementations30 Jan 2020 Jiangbo Yuan, Bing Wu, Wanying Ding, Qing Ping, Zhendong Yu

We conduct the learning in an adversarial learning process, which bears a close resemblance to the original GAN but again shifts the learning from image spaces to prior and latent code spaces.

Image Generation

Fashion-AttGAN: Attribute-Aware Fashion Editing with Multi-Objective GAN

2 code implementations16 Apr 2019 Qing Ping, Bing Wu, Wanying Ding, Jiangbo Yuan

In this paper, we introduce attribute-aware fashion-editing, a novel task, to the fashion domain.

Transformed Residual Quantization for Approximate Nearest Neighbor Search

no code implementations22 Dec 2015 Jiangbo Yuan, Xiuwen Liu

The success of product quantization (PQ) for fast nearest neighbor search depends on the exponentially reduced complexities of both storage and computation with respect to the codebook size.


Cannot find the paper you are looking for? You can Submit a new open access paper.