activity
20152021
most citedRGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature Alignment

59 citations · 187 across the 17 of their papers we have counts for

collaborators
Showing 2020 · cs.CVShow all

6 papers · 2 filters

cs.CV2020

Confidence-aware Non-repetitive Multimodal Transformers for TextCaps

Zhaokai Wang, Renda Bao, Qi Wu +1

When describing an image, reading text in the visual scene is crucial to understand the key information. Recent work explores the TextCaps task, i.e. image captioning with reading…

cs.CV2020

Human-centric Spatio-Temporal Video Grounding With Visual Transformers

Zongheng Tang, Yue Liao, Si Liu +5

In this work, we introduce a novel task - Humancentric Spatio-Temporal Video Grounding (HC-STVG). Unlike the existing referring expression tasks in images or videos, by focusing on…

cs.CV2020★ 10 cited

Linguistic Structure Guided Context Modeling for Referring Image Segmentation

Tianrui Hui, Si Liu, Shaofei Huang +4

Referring image segmentation aims to predict the foreground mask of the object referred by a natural language sentence. Multimodal context of the sentence is crucial to distinguish…

cs.CV2020★ 3 cited

Referring Image Segmentation via Cross-Modal Progressive Comprehension

Shaofei Huang, Tianrui Hui, Si Liu +5

Referring image segmentation aims at segmenting the foreground masks of the entities that can well match the description given in the natural language expression. Previous approach…

cs.CV2020★ 7 cited

Recapture as You Want

Chen Gao, Si Liu, Ran He +2

With the increasing prevalence and more powerful camera systems of mobile devices, people can conveniently take photos in their daily life, which naturally brings the demand for mo…

cs.CV2020★ 3 cited

Tree-Structured Policy based Progressive Reinforcement Learning for Temporally Language Grounding in Video

Jie Wu, Guanbin Li, Si Liu +1

Temporally language grounding in untrimmed videos is a newly-raised task in video understanding. Most of the existing methods suffer from inferior efficiency, lacking interpretabil…