Search Results for author: Zhengzheng Tu

Found 8 papers, 5 papers with code

TriTransNet: RGB-D Salient Object Detection with a Triplet Transformer Embedding Network

1 code implementation9 Aug 2021 Zhengyi Liu, YuAn Wang, Zhengzheng Tu, Yun Xiao, Bin Tang

In view of the more contribution of high-level features for the performance, we propose a triplet transformer embedding module to enhance them by learning long-range dependencies across layers.

object-detection RGB-D Salient Object Detection +1

Multi-interactive Encoder-decoder Network for RGBT Salient Object Detection

2 code implementations5 Jun 2020 Zhengzheng Tu, Zhun Li, Chenglong Li, Yang Lang, Jin Tang

RGBT salient object detection (SOD) aims to segment the common prominent regions of visible and thermal infrared images.

object-detection Object Detection +1

Multi-interactive Dual-decoder for RGB-thermal Salient Object Detection

2 code implementations5 May 2020 Zhengzheng Tu, Zhun Li, Chenglong Li, Yang Lang, Jin Tang

Then, we design a novel dual-decoder to conduct the interactions of multi-level features, two modalities and global contexts.

object-detection RGB Salient Object Detection +1

M$^5$L: Multi-Modal Multi-Margin Metric Learning for RGBT Tracking

no code implementations17 Mar 2020 Zhengzheng Tu, Chun Lin, Chenglong Li, Jin Tang, Bin Luo

Classifying the confusing samples in the course of RGBT tracking is a quite challenging problem, which hasn't got satisfied solution.

Metric Learning

Edge-guided Non-local Fully Convolutional Network for Salient Object Detection

no code implementations7 Aug 2019 Zhengzheng Tu, Yan Ma, Chenglong Li, Jin Tang, Bin Luo

To maintain the clear edge structure of salient objects, we propose a novel Edge-guided Non-local FCN (ENFNet) to perform edge guided feature learning for accurate salient object detection.

object-detection RGB Salient Object Detection +1

Multi-Adapter RGBT Tracking

no code implementations17 Jul 2019 Chenglong Li, Andong Lu, Aihua Zheng, Zhengzheng Tu, Jin Tang

In a specific, the generality adapter is to extract shared object representations, the modality adapter aims at encoding modality-specific information to deploy their complementary advantages, and the instance adapter is to model the appearance properties and temporal variations of a certain object.

Visual Tracking

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