Congyan Lang
YOU?
Author Swipe
View article: A computer vision system for recognition and defect detection for reusable containers
A computer vision system for recognition and defect detection for reusable containers Open
Small load carriers (SLCs) are standardized reusable containers used to transport and protect customer goods in many manufacturers. Throughout the life cycle of the SLCs, they will be collected, manually checked for defects (wear, cracks, …
View article: Knowledge Transfer and Domain Adaptation for Fine-Grained Remote Sensing Image Segmentation
Knowledge Transfer and Domain Adaptation for Fine-Grained Remote Sensing Image Segmentation Open
Fine-grained remote sensing image segmentation is essential for accurately identifying detailed objects in remote sensing images. Recently, vision transformer models (VTMs) pre-trained on large-scale datasets have demonstrated strong zero-…
View article: Adapting Vision Foundation Models for Robust Cloud Segmentation in Remote Sensing Images
Adapting Vision Foundation Models for Robust Cloud Segmentation in Remote Sensing Images Open
Cloud segmentation is a critical challenge in remote sensing image interpretation, as its accuracy directly impacts the effectiveness of subsequent data processing and analysis. Recently, vision foundation models (VFM) have demonstrated po…
View article: GrassNet: State Space Model Meets Graph Neural Network
GrassNet: State Space Model Meets Graph Neural Network Open
Designing spectral convolutional networks is a formidable task in graph learning. In traditional spectral graph neural networks (GNNs), polynomial-based methods are commonly used to design filters via the Laplacian matrix. In practical app…
View article: DFA-GNN: Forward Learning of Graph Neural Networks by Direct Feedback Alignment
DFA-GNN: Forward Learning of Graph Neural Networks by Direct Feedback Alignment Open
Graph neural networks are recognized for their strong performance across various applications, with the backpropagation algorithm playing a central role in the development of most GNN models. However, despite its effectiveness, BP has limi…
View article: RL-SeqISP: Reinforcement Learning-Based Sequential Optimization for Image Signal Processing
RL-SeqISP: Reinforcement Learning-Based Sequential Optimization for Image Signal Processing Open
Hardware image signal processing (ISP), aiming at converting RAW inputs to RGB images, consists of a series of processing blocks, each with multiple parameters. Traditionally, ISP parameters are manually tuned in isolation by imaging exper…
View article: The Cascaded Forward Algorithm for Neural Network Training
The Cascaded Forward Algorithm for Neural Network Training Open
View article: Biphenyl or Naphthalene-Modified Fluorene Fluorogenic Molecules with Different Solid-State Emission and Mechanofluorochromic Behaviors
Biphenyl or Naphthalene-Modified Fluorene Fluorogenic Molecules with Different Solid-State Emission and Mechanofluorochromic Behaviors Open
View article: Global Relation Mining for Compositional Zero-Shot Learning
Global Relation Mining for Compositional Zero-Shot Learning Open
View article: Unagi: Unified Neighbor-Aware Graph Neural Network for Multi-View Clustering
Unagi: Unified Neighbor-Aware Graph Neural Network for Multi-View Clustering Open
View article: The Cascaded Forward Algorithm for Neural Network Training
The Cascaded Forward Algorithm for Neural Network Training Open
Backpropagation algorithm has been widely used as a mainstream learning procedure for neural networks in the past decade, and has played a significant role in the development of deep learning. However, there exist some limitations associat…
View article: Collaborative Perception in Autonomous Driving: Methods, Datasets and Challenges
Collaborative Perception in Autonomous Driving: Methods, Datasets and Challenges Open
Collaborative perception is essential to address occlusion and sensor failure issues in autonomous driving. In recent years, theoretical and experimental investigations of novel works for collaborative perception have increased tremendousl…
View article: GLAN: A Graph-based Linear Assignment Network
GLAN: A Graph-based Linear Assignment Network Open
Differentiable solvers for the linear assignment problem (LAP) have attracted much research attention in recent years, which are usually embedded into learning frameworks as components. However, previous algorithms, with or without learnin…
View article: Deep Probabilistic Graph Matching
Deep Probabilistic Graph Matching Open
Most previous learning-based graph matching algorithms solve the \textit{quadratic assignment problem} (QAP) by dropping one or more of the matching constraints and adopting a relaxed assignment solver to obtain sub-optimal correspondences…
View article: Clicking Matters:Towards Interactive Human Parsing
Clicking Matters:Towards Interactive Human Parsing Open
In this work, we focus on Interactive Human Parsing (IHP), which aims to segment a human image into multiple human body parts with guidance from users' interactions. This new task inherits the class-aware property of human parsing, which c…
View article: MSO: Multi-Feature Space Joint Optimization Network for RGB-Infrared Person Re-Identification
MSO: Multi-Feature Space Joint Optimization Network for RGB-Infrared Person Re-Identification Open
The RGB-infrared cross-modality person re-identification (ReID) task aims to recognize the images of the same identity between the visible modality and the infrared modality. Existing methods mainly use a two-stream architecture to elimina…
View article: Joint Graph Learning and Matching for Semantic Feature Correspondence
Joint Graph Learning and Matching for Semantic Feature Correspondence Open
In recent years, powered by the learned discriminative representation via graph neural network (GNN) models, deep graph matching methods have made great progresses in the task of matching semantic features. However, these methods usually r…
View article: A Universal Model for Cross Modality Mapping by Relational Reasoning
A Universal Model for Cross Modality Mapping by Relational Reasoning Open
With the aim of matching a pair of instances from two different modalities, cross modality mapping has attracted growing attention in the computer vision community. Existing methods usually formulate the mapping function as the similarity …
View article: Partial Multi-Label Learning by Low-Rank and Sparse Decomposition
Partial Multi-Label Learning by Low-Rank and Sparse Decomposition Open
Multi-Label Learning (MLL) aims to learn from the training data where each example is represented by a single instance while associated with a set of candidate labels. Most existing MLL methods are typically designed to handle the problem …
View article: HERA: Partial Label Learning by Combining Heterogeneous Loss with Sparse and Low-Rank Regularization
HERA: Partial Label Learning by Combining Heterogeneous Loss with Sparse and Low-Rank Regularization Open
Partial Label Learning (PLL) aims to learn from the data where each training instance is associated with a set of candidate labels, among which only one is correct. Most existing methods deal with such problem by either treating each candi…
View article: Deep Reasoning with Multi-Scale Context for Salient Object Detection
Deep Reasoning with Multi-Scale Context for Salient Object Detection Open
To detect salient objects accurately, existing methods usually design complex backbone network architectures to learn and fuse powerful features. However, the saliency inference module that performs saliency prediction from the fused featu…
View article: GM-PLL: Graph Matching based Partial Label Learning
GM-PLL: Graph Matching based Partial Label Learning Open
Partial Label Learning (PLL) aims to learn from the data where each training example is associated with a set of candidate labels, among which only one is correct. The key to deal with such problem is to disambiguate the candidate label se…
View article: Saliency Aggregation: Multifeature and Neighbor Based Salient Region Detection for Social Images
Saliency Aggregation: Multifeature and Neighbor Based Salient Region Detection for Social Images Open
The popularity of social networks has brought the rapid growth of social images which have become an increasingly important image type. One of the most obvious attributes of social images is the tag. However, the sate-of-the-art methods fa…
View article: Multiple-Human Parsing in the Wild
Multiple-Human Parsing in the Wild Open
Human parsing is attracting increasing research attention. In this work, we aim to push the frontier of human parsing by introducing the problem of multi-human parsing in the wild. Existing works on human parsing mainly tackle single-perso…
View article: Guest Editorial: Learning Multimedia for Real World Applications
Guest Editorial: Learning Multimedia for Real World Applications Open