activity
20142023
most citedSeeing the Big Picture: Deep Embedding with Contextual Evidences

16 citations · 28 across the 7 of their papers we have counts for

collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2022

Portrait Interpretation and a Benchmark

Yixuan Fan, Zhaopeng Dou, Yali Li +1

We propose a task we name Portrait Interpretation and construct a dataset named Portrait250K for it. Current researches on portraits such as human attribute recognition and person…

cs.CV20218 cited

Adaptive Affinity for Associations in Multi-Target Multi-Camera Tracking

Yunzhong Hou, Zhongdao Wang, Shengjin Wang +1

Data associations in multi-target multi-camera tracking (MTMCT) usually estimate affinity directly from re-identification (re-ID) feature distances. However, we argue that it might…

cs.CV2021

Delving into Probabilistic Uncertainty for Unsupervised Domain Adaptive Person Re-Identification

Jian Han, Ya-Li li, Shengjin Wang

Clustering-based unsupervised domain adaptive (UDA) person re-identification (ReID) reduces exhaustive annotations. However, owing to unsatisfactory feature embedding and imperfect…

cs.CV2014

Visual Reranking with Improved Image Graph

Ziqiong Liu, Shengjin Wang, Liang Zheng +1

This paper introduces an improved reranking method for the Bag-of-Words (BoW) based image search. Built on [1], a directed image graph robust to outlier distraction is proposed. In…

cs.CV201416 cited

Seeing the Big Picture: Deep Embedding with Contextual Evidences

Liang Zheng, Shengjin Wang, Fei He +1

In the Bag-of-Words (BoW) model based image retrieval task, the precision of visual matching plays a critical role in improving retrieval performance. Conventionally, local cues of…

cs.CV2014

Bayes Merging of Multiple Vocabularies for Scalable Image Retrieval

Liang Zheng, Shengjin Wang, Wengang Zhou +1

The Bag-of-Words (BoW) representation is well applied to recent state-of-the-art image retrieval works. Typically, multiple vocabularies are generated to correct quantization artif…