1k citations · 7k across the 61 of their papers we have counts for
58 papers · 1 filter
PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences
Hehe Fan, Xin Yu, Yuhang Ding +2
Point cloud sequences are irregular and unordered in the spatial dimension while exhibiting regularities and order in the temporal dimension. Therefore, existing grid based convolu…
Weakly Supervised Person Search with Region Siamese Networks
Chuchu Han, Kai Su, Dongdong Yu +5
Supervised learning is dominant in person search, but it requires elaborate labeling of bounding boxes and identities. Large-scale labeled training data is often difficult to colle…
Generating Superpixels for High-resolution Images with Decoupled Patch Calibration
Yaxiong Wang, Yunchao Wei, Xueming Qian +2
Superpixel segmentation has recently seen important progress benefiting from the advances in differentiable deep learning. However, the very high-resolution superpixel segmentation…
PR-RRN: Pairwise-Regularized Residual-Recursive Networks for Non-rigid Structure-from-Motion
Haitian Zeng, Yuchao Dai, Xin Yu +2
We propose PR-RRN, a novel neural-network based method for Non-rigid Structure-from-Motion (NRSfM). PR-RRN consists of Residual-Recursive Networks (RRN) and two extra regularizatio…
ReGO: Reference-Guided Outpainting for Scenery Image
Yaxiong Wang, Yunchao Wei, Xueming Qian +2
We aim to tackle the challenging yet practical scenery image outpainting task in this work. Recently, generative adversarial learning has significantly advanced the image outpainti…
Associating Objects with Transformers for Video Object Segmentation
Zongxin Yang, Yunchao Wei, Yi Yang
This paper investigates how to realize better and more efficient embedding learning to tackle the semi-supervised video object segmentation under challenging multi-object scenarios…
Few-Shot Segmentation via Cycle-Consistent Transformer
Gengwei Zhang, Guoliang Kang, Yi Yang +1
Few-shot segmentation aims to train a segmentation model that can fast adapt to novel classes with few exemplars. The conventional training paradigm is to learn to make predictions…
Prior-Enhanced Few-Shot Segmentation with Meta-Prototypes
Jian-Wei Zhang, Lei Lv, Yawei Luo +3
Few-shot segmentation~(FSS) performance has been extensively promoted by introducing episodic training and class-wise prototypes. However, the FSS problem remains challenging due t…
VidFace: A Full-Transformer Solver for Video FaceHallucination with Unaligned Tiny Snapshots
Yuan Gan, Yawei Luo, Xin Yu +2
In this paper, we investigate the task of hallucinating an authentic high-resolution (HR) human face from multiple low-resolution (LR) video snapshots. We propose a pure transforme…
Connecting Language and Vision for Natural Language-Based Vehicle Retrieval
Shuai Bai, Zhedong Zheng, Xiaohan Wang +5
Vehicle search is one basic task for the efficient traffic management in terms of the AI City. Most existing practices focus on the image-based vehicle matching, including vehicle…
DSC-PoseNet: Learning 6DoF Object Pose Estimation via Dual-scale Consistency
Zongxin Yang, Xin Yu, Yi Yang
Compared to 2D object bounding-box labeling, it is very difficult for humans to annotate 3D object poses, especially when depth images of scenes are unavailable. This paper investi…
Improving Weakly-supervised Object Localization via Causal Intervention
Feifei Shao, Yawei Luo, Li Zhang +4
The recent emerged weakly supervised object localization (WSOL) methods can learn to localize an object in the image only using image-level labels. Previous works endeavor to perce…
Decoupled Spatial Temporal Graphs for Generic Visual Grounding
Qianyu Feng, Yunchao Wei, Mingming Cheng +1
Visual grounding is a long-lasting problem in vision-language understanding due to its diversity and complexity. Current practices concentrate mostly on performing visual grounding…
Adaptive Boosting for Domain Adaptation: Towards Robust Predictions in Scene Segmentation
Zhedong Zheng, Yi Yang
Domain adaptation is to transfer the shared knowledge learned from the source domain to a new environment, i.e., target domain. One common practice is to train the model on both la…
Super-Resolving Cross-Domain Face Miniatures by Peeking at One-Shot Exemplar
Peike Li, Xin Yu, Yi Yang
Conventional face super-resolution methods usually assume testing low-resolution (LR) images lie in the same domain as the training ones. Due to different lighting conditions and i…
Decoupled and Memory-Reinforced Networks: Towards Effective Feature Learning for One-Step Person Search
Chuchu Han, Zhedong Zheng, Changxin Gao +2
The goal of person search is to localize and match query persons from scene images. For high efficiency, one-step methods have been developed to jointly handle the pedestrian detec…
AINet+: Advancing Superpixel Segmentation via Cascaded Association Implantation
Yaxiong Wang, Yunchao Wei, Yujiao Wu +3
Superpixel segmentation has seen significant progress benefiting from the deep convolutional networks. The typical approach entails initial division of the image into grids, follow…
Understanding Image Retrieval Re-Ranking: A Graph Neural Network Perspective
Xuanmeng Zhang, Minyue Jiang, Zhedong Zheng +3
The re-ranking approach leverages high-confidence retrieved samples to refine retrieval results, which have been widely adopted as a post-processing tool for image retrieval tasks.…
Pixel-Level Cycle Association: A New Perspective for Domain Adaptive Semantic Segmentation
Guoliang Kang, Yunchao Wei, Yi Yang +2
Domain adaptive semantic segmentation aims to train a model performing satisfactory pixel-level predictions on the target with only out-of-domain (source) annotations. The conventi…
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration
Zongxin Yang, Yunchao Wei, Yi Yang
This paper investigates the principles of embedding learning to tackle the challenging semi-supervised video object segmentation. Unlike previous practices that focus on exploring…
Inter-Image Communication for Weakly Supervised Localization
Xiaolin Zhang, Yunchao Wei, Yi Yang
Weakly supervised localization aims at finding target object regions using only image-level supervision. However, localization maps extracted from classification networks are often…
Each Part Matters: Local Patterns Facilitate Cross-view Geo-localization
Tingyu Wang, Zhedong Zheng, Chenggang Yan +4
Cross-view geo-localization is to spot images of the same geographic target from different platforms, e.g., drone-view cameras and satellites. It is challenging in the large visual…
Point Adversarial Self Mining: A Simple Method for Facial Expression Recognition
Ping Liu, Yuewei Lin, Zibo Meng +4
In this paper, we propose a simple yet effective approach, named Point Adversarial Self Mining (PASM), to improve the recognition accuracy in facial expression recognition. Unlike…
Rethinking Localization Map: Towards Accurate Object Perception with Self-Enhancement Maps
Xiaolin Zhang, Yunchao Wei, Yi Yang +1
Recently, remarkable progress has been made in weakly supervised object localization (WSOL) to promote object localization maps. The common practice of evaluating these maps applie…