254 citations · 649 across the 20 of their papers we have counts for
20 papers
Adversarial Reconstruction Feedback for Robust Fine-grained Generalization
Shijie Wang, Jian Shi, Haojie Li
Existing fine-grained image retrieval (FGIR) methods predominantly rely on supervision from predefined categories to learn discriminative representations for retrieving fine-graine…
Similarity Guided Multimodal Fusion Transformer for Semantic Location Prediction in Social Media
Zhizhen Zhang, Ning Wang, Haojie Li +1
Semantic location prediction aims to derive meaningful location insights from multimodal social media posts, offering a more contextual understanding of daily activities than using…
Towards Fair and Comprehensive Comparisons for Image-Based 3D Object Detection
Xinzhu Ma, Yongtao Wang, Yinmin Zhang +5
In this work, we build a modular-designed codebase, formulate strong training recipes, design an error diagnosis toolbox, and discuss current methods for image-based 3D object dete…
TRUST: An Accurate and End-to-End Table structure Recognizer Using Splitting-based Transformers
Zengyuan Guo, Yuechen Yu, Pengyuan Lv +6
Table structure recognition is a crucial part of document image analysis domain. Its difficulty lies in the need to parse the physical coordinates and logical indices of each cell…
Fine-grained Retrieval Prompt Tuning
Shijie Wang, Jianlong Chang, Zhihui Wang +3
Fine-grained object retrieval aims to learn discriminative representation to retrieve visually similar objects. However, existing top-performing works usually impose pairwise simil…
MonoDistill: Learning Spatial Features for Monocular 3D Object Detection
Zhiyu Chong, Xinzhu Ma, Hong Zhang +4
3D object detection is a fundamental and challenging task for 3D scene understanding, and the monocular-based methods can serve as an economical alternative to the stereo-based or…
An Underwater Image Semantic Segmentation Method Focusing on Boundaries and a Real Underwater Scene Semantic Segmentation Dataset
Zhiwei Ma, Haojie Li, Zhihui Wang +5
With the development of underwater object grabbing technology, underwater object recognition and segmentation of high accuracy has become a challenge. The existing underwater objec…
A Dataset And Benchmark Of Underwater Object Detection For Robot Picking
Chongwei Liu, Haojie Li, Shuchang Wang +4
Underwater object detection for robot picking has attracted a lot of interest. However, it is still an unsolved problem due to several challenges. We take steps towards making it m…
Delving into Localization Errors for Monocular 3D Object Detection
Xinzhu Ma, Yinmin Zhang, Dan Xu +4
Estimating 3D bounding boxes from monocular images is an essential component in autonomous driving, while accurate 3D object detection from this kind of data is very challenging. I…
A Unified Joint Maximum Mean Discrepancy for Domain Adaptation
Wei Wang, Baopu Li, Shuhui Yang +6
Domain adaptation has received a lot of attention in recent years, and many algorithms have been proposed with impressive progress. However, it is still not fully explored concerni…
Full Matching on Low Resolution for Disparity Estimation
Hong Zhang, Shenglun Chen, Zhihui Wang +2
A Multistage Full Matching disparity estimation scheme (MFM) is proposed in this work. We demonstrate that decouple all similarity scores directly from the low-resolution 4D volume…
Direct Depth Learning Network for Stereo Matching
Hong Zhang, Haojie Li, Shenglun Chen +4
Being a crucial task of autonomous driving, Stereo matching has made great progress in recent years. Existing stereo matching methods estimate disparity instead of depth. They trea…
Rethink Maximum Mean Discrepancy for Domain Adaptation
Wei Wang, Haojie Li, Zhengming Ding +1
Existing domain adaptation methods aim to reduce the distributional difference between the source and target domains and respect their specific discriminative information, by estab…
Location-Aware Feature Selection Text Detection Network
Zengyuan Guo, Zilin Wang, Zhihui Wang +3
Regression-based text detection methods have already achieved promising performances with simple network structure and high efficiency. However, they are behind in accuracy compari…
Sparsely-Labeled Source Assisted Domain Adaptation
Wei Wang, Zhihui Wang, Yuankai Xiang +4
Domain Adaptation (DA) aims to generalize the classifier learned from the source domain to the target domain. Existing DA methods usually assume that rich labels could be available…
A New Dataset, Poisson GAN and AquaNet for Underwater Object Grabbing
Chongwei Liu, Zhihui Wang, Shijie Wang +6
To boost the object grabbing capability of underwater robots for open-sea farming, we propose a new dataset (UDD) consisting of three categories (seacucumber, seaurchin, and scallo…
Importance Filtered Cross-Domain Adaptation
Wei Wang, Haojie Li, Zhihui Wang +3
In Domain Adaptation (DA), the category-relevant losses usually occupy a dominant position, while they are usually built with hard or soft labels in existing models. We observed th…
Accurate Monocular Object Detection via Color-Embedded 3D Reconstruction for Autonomous Driving
Xinzhu Ma, Zhihui Wang, Haojie Li +3
In this paper, we propose a monocular 3D object detection framework in the domain of autonomous driving. Unlike previous image-based methods which focus on RGB feature extracted fr…
User-Guided Deep Anime Line Art Colorization with Conditional Adversarial Networks
Yuanzheng Ci, Xinzhu Ma, Zhihui Wang +2
Scribble colors based line art colorization is a challenging computer vision problem since neither greyscale values nor semantic information is presented in line arts, and the lack…
A Single Shot Text Detector with Scale-adaptive Anchors
Qi Yuan, Bingwang Zhang, Haojie Li +2
Currently, most top-performing text detection networks tend to employ fixed-size anchor boxes to guide the search for text instances. They usually rely on a large amount of anchors…