1.3k citations · 1.4k across the 32 of their papers we have counts for
21 papers · 1 filter
PVUW 2025 Challenge Report: Advances in Pixel-level Understanding of Complex Videos in the Wild
Henghui Ding, Chang Liu, Nikhila Ravi +33
This report provides a comprehensive overview of the 4th Pixel-level Video Understanding in the Wild (PVUW) Challenge, held in conjunction with CVPR 2025. It summarizes the challen…
STSeg-Complex Video Object Segmentation: The 1st Solution for 4th PVUW MOSE Challenge
Kehuan Song, Xinglin Xie, Kexin Zhang +3
Segmentation of video objects in complex scenarios is highly challenging, and the MOSE dataset has significantly contributed to the development of this field. This technical report…
SoccerNet 2024 Challenges Results
Anthony Cioppa, Silvio Giancola, Vladimir Somers +81
The SoccerNet 2024 challenges represent the fourth annual video understanding challenges organized by the SoccerNet team. These challenges aim to advance research across multiple t…
Renormalized Connection for Scale-preferred Object Detection in Satellite Imagery
Fan Zhang, Lingling Li, Licheng Jiao +4
Satellite imagery, due to its long-range imaging, brings with it a variety of scale-preferred tasks, such as the detection of tiny/small objects, making the precise localization an…
Technique Report of CVPR 2024 PBDL Challenges
Ying Fu, Yu Li, Shaodi You +96
The intersection of physics-based vision and deep learning presents an exciting frontier for advancing computer vision technologies. By leveraging the principles of physics to info…
Fast and Efficient: Mask Neural Fields for 3D Scene Segmentation
Zihan Gao, Lingling Li, Licheng Jiao +5
Understanding 3D scenes is a crucial challenge in computer vision research with applications spanning multiple domains. Recent advancements in distilling 2D vision-language foundat…
PVUW 2024 Challenge on Complex Video Understanding: Methods and Results
Henghui Ding, Chang Liu, Yunchao Wei +34
Pixel-level Video Understanding in the Wild Challenge (PVUW) focus on complex video understanding. In this CVPR 2024 workshop, we add two new tracks, Complex Video Object Segmentat…
3rd Place Solution for MOSE Track in CVPR 2024 PVUW workshop: Complex Video Object Segmentation
Xinyu Liu, Jing Zhang, Kexin Zhang +3
Video Object Segmentation (VOS) is a vital task in computer vision, focusing on distinguishing foreground objects from the background across video frames. Our work draws inspiratio…
Edit-Your-Motion: Space-Time Diffusion Decoupling Learning for Video Motion Editing
Yi Zuo, Lingling Li, Licheng Jiao +5
Existing diffusion-based methods have achieved impressive results in human motion editing. However, these methods often exhibit significant ghosting and body distortion in unseen i…
Exploring Beyond Logits: Hierarchical Dynamic Labeling Based on Embeddings for Semi-Supervised Classification
Yanbiao Ma, Licheng Jiao, Fang Liu +3
In semi-supervised learning, methods that rely on confidence learning to generate pseudo-labels have been widely proposed. However, increasing research finds that when faced with n…
Unveiling and Mitigating Generalized Biases of DNNs through the Intrinsic Dimensions of Perceptual Manifolds
Yanbiao Ma, Licheng Jiao, Fang Liu +5
Building fair deep neural networks (DNNs) is a crucial step towards achieving trustworthy artificial intelligence. Delving into deeper factors that affect the fairness of DNNs is p…
Heterogeneous Network Based Contrastive Learning Method for PolSAR Land Cover Classification
Jianfeng Cai, Yue Ma, Zhixi Feng +1
Polarimetric synthetic aperture radar (PolSAR) image interpretation is widely used in various fields. Recently, deep learning has made significant progress in PolSAR image classifi…
Geometric Prior Guided Feature Representation Learning for Long-Tailed Classification
Yanbiao Ma, Licheng Jiao, Fang Liu +3
Real-world data are long-tailed, the lack of tail samples leads to a significant limitation in the generalization ability of the model. Although numerous approaches of class re-bal…
Data-Centric Long-Tailed Image Recognition
Yanbiao Ma, Licheng Jiao, Fang Liu +3
In the context of the long-tail scenario, models exhibit a strong demand for high-quality data. Data-centric approaches aim to enhance both the quantity and quality of data to impr…
Changes-Aware Transformer: Learning Generalized Changes Representation
Dan Wang, Licheng Jiao, Jie Chen +2
Difference features obtained by comparing the images of two periods play an indispensable role in the change detection (CD) task. However, a pair of bi-temporal images can exhibit…
Predicting and Enhancing the Fairness of DNNs with the Curvature of Perceptual Manifolds
Yanbiao Ma, Licheng Jiao, Fang Liu +6
To address the challenges of long-tailed classification, researchers have proposed several approaches to reduce model bias, most of which assume that classes with few samples are w…
Delving into Semantic Scale Imbalance
Yanbiao Ma, Licheng Jiao, Fang Liu +3
Model bias triggered by long-tailed data has been widely studied. However, measure based on the number of samples cannot explicate three phenomena simultaneously: (1) Given enough…
Transformers Meet Visual Learning Understanding: A Comprehensive Review
Yuting Yang, Licheng Jiao, Xu Liu +4
Dynamic attention mechanism and global modeling ability make Transformer show strong feature learning ability. In recent years, Transformer has become comparable to CNNs methods in…
A Survey of Deep Learning-based Object Detection
Licheng Jiao, Fan Zhang, Fang Liu +4
Object detection is one of the most important and challenging branches of computer vision, which has been widely applied in peoples life, such as monitoring security, autonomous dr…
Modified Diversity of Class Probability Estimation Co-training for Hyperspectral Image Classification
Yan Ju, Lingling Li, Licheng Jiao +3
Due to the limited amount and imbalanced classes of labeled training data, the conventional supervised learning can not ensure the discrimination of the learned feature for hypersp…
Polarimetric Hierarchical Semantic Model and Scattering Mechanism Based PolSAR Image Classification
Fang Liu, Junfei Shi, Licheng Jiao +5
For polarimetric SAR (PolSAR) image classification, it is a challenge to classify the aggregated terrain types, such as the urban area, into semantic homogenous regions due to shar…