Search Results for author:
Found 72 papers, 24 papers with code
On Structural Explanation of Bias in Graph Neural Networks
The low transparency on how the structure of the input network influences the bias in GNN outcome largely limits the safe adoption of GNNs in various decision-critical scenarios.
Task-Adaptive Few-shot Node Classification
Then we transfer such knowledge to the classes with limited labeled nodes via our proposed task-adaptive modules.
FAITH: Few-Shot Graph Classification with Hierarchical Task Graphs
Specifically, these works propose to accumulate meta-knowledge across diverse meta-training tasks, and then generalize such meta-knowledge to the target task with a disjoint label set.
An End-to-End Dialogue Summarization System for Sales Calls
Summarizing sales calls is a routine task performed manually by salespeople.
DialogVED: A Pre-trained Latent Variable Encoder-Decoder Model for Dialog Response Generation
Dialog response generation in open domain is an important research topic where the main challenge is to generate relevant and diverse responses.
PLGAN: Generative Adversarial Networks for Power-Line Segmentation in Aerial Images
Accurate segmentation of power lines in various aerial images is very important for UAV flight safety.
Radiology Text Analysis System (RadText): Architecture and Evaluation
Analyzing radiology reports is a time-consuming and error-prone task, which raises the need for an efficient automated radiology report analysis system to alleviate the workloads of radiologists and encourage precise diagnosis.
MISF: Multi-level Interactive Siamese Filtering for High-Fidelity Image Inpainting
As a result, the final method takes the advantage of effective semantic & image-level filling for high-fidelity inpainting.
Self-supervised Social Relation Representation for Human Group Detection
The core of human group detection is the human social relation representation and division. In this paper, we propose a new two-stage multi-head framework for human group detection.
Panoramic Human Activity Recognition
To obtain a more comprehensive activity understanding for a crowded scene, in this paper, we propose a new problem of panoramic human activity recognition (PAR), which aims to simultaneous achieve the individual action, social group activity, and global activity recognition.
Meta-RangeSeg: LiDAR Sequence Semantic Segmentation Using Multiple Feature Aggregation
Furthermore, Feature Aggregation Module (FAM) aggregates the meta features and multi-scale features, which tends to strengthen the role of range channel.
Ranked #9 on
3D Semantic Segmentation
on SemanticKITTI
Prior Knowledge Enhances Radiology Report Generation
In this work, we propose to mine and represent the associations among medical findings in an informative knowledge graph and incorporate this prior knowledge with radiology report generation to help improve the quality of generated reports.
Uncertainty-Aware Cascaded Dilation Filtering for High-Efficiency Deraining
First, we propose the uncertainty-aware cascaded predictive filtering (UC-PFilt) that can identify the difficulties of reconstructing clean pixels via predicted kernels and remove the residual rain traces effectively.
Connecting the Complementary-View Videos: Joint Camera Identification and Subject Association
In this paper, we develop a new approach that can simultaneously handle three tasks: i) localizing the side-view camera in the top view; ii) estimating the view direction of the side-view camera; iii) detecting and associating the same subjects on the ground across the complementary views.
Style Mixing and Patchwise Prototypical Matching for One-Shot Unsupervised Domain Adaptive Semantic Segmentation
In this paper, we tackle the problem of one-shot unsupervised domain adaptation (OSUDA) for semantic segmentation where the segmentors only see one unlabeled target image during training.
One-shot Unsupervised Domain Adaptation
Semantic Segmentation
+2
Benchmarking Shadow Removal for Facial Landmark Detection and Beyond
The observation of this work motivates us to design a novel detection-aware shadow removal framework, which empowers shadow removal to achieve higher restoration quality and enhance the shadow robustness of deployed facial landmark detectors.
ATLANTIS: A Benchmark for Semantic Segmentation of Waterbody Images
We claim that ATLANTIS is the largest waterbody image dataset for semantic segmentation providing a wide range of water and water-related classes and it will benefit researchers of both computer vision and water resources engineering.
Ranked #1 on
Semantic Segmentation
on ATLANTIS
Hierarchical Heterogeneous Graph Representation Learning for Short Text Classification
Short text classification is a fundamental task in natural language processing.
VIL-100: A New Dataset and A Baseline Model for Video Instance Lane Detection
Lane detection plays a key role in autonomous driving.
CPNet: Cycle Prototype Network for Weakly-supervised 3D Renal Compartments Segmentation on CT Images
We propose a novel weakly supervised learning framework, Cycle Prototype Network, for 3D renal compartment segmentation.
JPGNet: Joint Predictive Filtering and Generative Network for Image Inpainting
In this paper, for the first time, we formulate image inpainting as a mix of two problems, predictive filtering and deep generation.
Long-Tailed Multi-Label Visual Recognition by Collaborative Training on Uniform and Re-Balanced Samplings
While re-balanced data sampling can improve the performance on tail classes, it may also hurt the performance on head classes in training due to label co-occurrence.
Sparta: Spatially Attentive and Adversarially Robust Activation
In both cases, Sparta leads to CNNs with higher robustness than the vanilla ReLU, verifying the flexibility and versatility of the proposed method.
Let There be Light: Improved Traffic Surveillance via Detail Preserving Night-to-Day Transfer
As one of the state-of-the-art perception approaches, detecting the interested objects in each frame of video surveillance is widely desired by ITS.
DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentation
We further design a re-weighting strategy to handle the inaccuracy caused by misalignment between day-night image pairs and wrong predictions of daytime images, as well as boost the prediction accuracy of small objects.
Ranked #2 on
Semantic Segmentation
on Nighttime Driving
From Shadow Generation to Shadow Removal
Shadow removal is a computer-vision task that aims to restore the image content in shadow regions.
Auto-Exposure Fusion for Single-Image Shadow Removal
We conduct extensive experiments on the ISTD, ISTD+, and SRD datasets to validate our method's effectiveness and show better performance in shadow regions and comparable performance in non-shadow regions over the state-of-the-art methods.
Multi-Domain Multi-Task Rehearsal for Lifelong Learning
Rehearsal, seeking to remind the model by storing old knowledge in lifelong learning, is one of the most effective ways to mitigate catastrophic forgetting, i. e., biased forgetting of previous knowledge when moving to new tasks.
Contour Transformer Network for One-shot Segmentation of Anatomical Structures
In this work, we present Contour Transformer Network (CTN), a one-shot anatomy segmentation method with a naturally built-in human-in-the-loop mechanism.
Using Radiomics as Prior Knowledge for Thorax Disease Classification and Localization in Chest X-rays
After a number of iterations and with the help of radiomic features, our framework can converge to more accurate image regions.
TTPLA: An Aerial-Image Dataset for Detection and Segmentation of Transmission Towers and Power Lines
Accurate detection and segmentation of transmission towers~(TTs) and power lines~(PLs) from aerial images plays a key role in protecting power-grid security and low-altitude UAV safety.
Can You Spot the Chameleon? Adversarially Camouflaging Images from Co-Salient Object Detection
In this paper, we address this problem from the perspective of adversarial attacks and identify a novel task: adversarial co-saliency attack.
The Statistical Characteristics of Power-Spectrum Subband Energy Ratios under Additive Gaussian White Noise
When Gaussian white noise was mixed with the known signal, the resulting PSER followed a doubly non-central beta distribution.
Learning to Segment Anatomical Structures Accurately from One Exemplar
Accurate segmentation of critical anatomical structures is at the core of medical image analysis.
Shadow Removal by a Lightness-Guided Network with Training on Unpaired Data
In this paper, we present a new Lightness-Guided Shadow Removal Network (LG-ShadowNet) for shadow removal by training on unpaired data.
Modeling Cross-view Interaction Consistency for Paired Egocentric Interaction Recognition
Paired egocentric interaction recognition (PEIR) is the task to collaboratively recognize the interactions between two persons with the videos in their corresponding views.
MUTATT: Visual-Textual Mutual Guidance for Referring Expression Comprehension
In this paper, we argue that for REC the referring expression and the target region are semantically correlated and subject, location and relationship consistency exist between vision and language. On top of this, we propose a novel approach called MutAtt to construct mutual guidance between vision and language, which treat vision and language equally thus yield compact information matching.
Label-guided Learning for Text Classification
In this study, we propose a label-guided learning framework LguidedLearn for text representation and classification.
Deep Poisoning: Towards Robust Image Data Sharing against Visual Disclosure
Due to respectively limited training data, different entities addressing the same vision task based on certain sensitive images may not train a robust deep network.
Transductive Zero-Shot Hashing for Multilabel Image Retrieval
Given semantic annotations such as class labels and pairwise similarities of the training data, hashing methods can learn and generate effective and compact binary codes.
An End-to-End Network for Co-Saliency Detection in One Single Image
As a common visual problem, co-saliency detection within a single image does not attract enough attention and yet has not been well addressed.
Language-independent Cross-lingual Contextual Representations
Contextual representation models like BERT have achieved state-of-the-art performance on a diverse range of NLP tasks.
Effects of Blur and Deblurring to Visual Object Tracking
In this paper, we address these two problems by constructing a Blurred Video Tracking benchmark, which contains a variety of videos with different levels of motion blurs, as well as ground truth tracking results for evaluating trackers.
Multiple Human Association between Top and Horizontal Views by Matching Subjects' Spatial Distributions
However, for such collaborative analysis, the first step is to associate people, referred to as subjects in this paper, across these two views.
Goal-Oriented End-to-End Conversational Models with Profile Features in a Real-World Setting
To test our models, a customer service agent handles live contacts and at each turn we present the top four model responses and allow the agent to select (and optionally edit) one of the suggestions or to type their own.
Global and Local Sensitivity Guided Key Salient Object Re-augmentation for Video Saliency Detection
In this paper, based on the fact that salient areas in videos are relatively small and concentrated, we propose a \textbf{key salient object re-augmentation method (KSORA) using top-down semantic knowledge and bottom-up feature guidance} to improve detection accuracy in video scenes.
Dating Ancient Paintings of Mogao Grottoes Using Deeply Learnt Visual Codes
Cultural heritage is the asset of all the peoples of the world.
Effects of Image Degradations to CNN-based Image Classification
In this paper, we empirically study this problem for four kinds of degraded images -- hazy images, underwater images, motion-blurred images and fish-eye images.
Does Haze Removal Help CNN-based Image Classification?
Typically, the goal of image dehazing is to produce clearer images from which human vision can better identify the object and structural details present in the images.
Interactive Binary Image Segmentation with Edge Preservation
Binary image segmentation plays an important role in computer vision and has been widely used in many applications such as image and video editing, object extraction, and photo composition.
Unsupervised Learning for Large-Scale Fiber Detection and Tracking in Microscopic Material Images
Constructing 3D structures from serial section data is a long standing problem in microscopy.
Design Identification of Curve Patterns on Cultural Heritage Objects: Combining Template Matching and CNN-based Re-Ranking
The goal of this paper is to address the challenging problem of automatically identifying the underlying full design of curve patterns from such a sherd.
Improved Deep Hashing with Soft Pairwise Similarity for Multi-label Image Retrieval
In this paper, a new deep hashing method is proposed for multi-label image retrieval by re-defining the pairwise similarity into an instance similarity, where the instance similarity is quantified into a percentage based on the normalized semantic labels.
Object Detection with Mask-based Feature Encoding
In particular, we design a Mask Weight Network (MWN) to learn a set of masks and then apply channel-wise masking operations to ROI feature map, followed by a global pooling and a cheap fully-connected layer.
Curve-Structure Segmentation from Depth Maps: A CNN-based Approach and Its Application to Exploring Cultural Heritage Objects
Motivated by the important archaeological application of exploring cultural heritage objects, in this paper we study the challenging problem of automatically segmenting curve structures that are very weakly stamped or carved on an object surface in the form of a highly noisy depth map.
Learning Dynamic Siamese Network for Visual Object Tracking
How to effectively learn temporal variation of target appearance, to exclude the interference of cluttered background, while maintaining real-time response, is an essential problem of visual object tracking.
Ranked #5 on
Visual Object Tracking
on OTB-2013
Learning View-Invariant Features for Person Identification in Temporally Synchronized Videos Taken by Wearable Cameras
In this paper, we attempt to utilize 3D human-skeleton sequences to learn a model that can extract view-invariant motion features from optical flows in different views.
Deep Reinforcement Learning with Surrogate Agent-Environment Interface
We introduce surrogate probability action and develop the probability surrogate action deterministic policy gradient (PSADPG) algorithm based on SAEI.
On Study of the Reliable Fully Convolutional Networks with Tree Arranged Outputs (TAO-FCN) for Handwritten String Recognition
The handwritten string recognition is still a challengeable task, though the powerful deep learning tools were introduced.
An Automated CNN Recommendation System for Image Classification Tasks
In order to solve this problem, we proposed an automated CNN recommendation system for image classification task.
Robust Gait Recognition by Integrating Inertial and RGBD Sensors
We propose two new algorithms, namely EigenGait and TrajGait, to extract gait features from the inertial data and the RGBD (color and depth) data, respectively.
Who Leads the Clothing Fashion: Style, Color, or Texture? A Computational Study
Specifically, a classification-based model is proposed to quantify the influence of different visual stimuli, in which each visual stimulus's influence is quantified by its corresponding accuracy in fashion classification.
Identifying Designs from Incomplete, Fragmented Cultural Heritage Objects by Curve-Pattern Matching
The challenge to reconstruct and study complete designs is stymied because 1) most fragmentary cultural-heritage objects contain only a small portion of the underlying full design, 2) in the case of a stamping application, the same design may be applied multiple times with spatial overlap on one object, and 3) curve patterns detected on an object are usually incomplete and noisy.
Groupwise Tracking of Crowded Similar-Appearance Targets From Low-Continuity Image Sequences
In particular, the within-group association is modeled by a nonrigid 2D Thin-Plate transform and a sequence of group shrinking, group growing and group merging operations are then developed to refine the composition of each group.
On Study of the Binarized Deep Neural Network for Image Classification
Unlike those trials, in this paper, we focused on the basic propagation function of the artificial neural network and proposed the binarized deep neural network.
Co-interest Person Detection from Multiple Wearable Camera Videos
Wearable cameras, such as Google Glass and Go Pro, enable video data collection over larger areas and from different views.
Unsupervised Cross-Domain Recognition by Identifying Compact Joint Subspaces
By adopting a natural and widely used assumption -- "the data samples from the same class should lay on a low-dimensional subspace, even if they come from different domains", the proposed method circumvents the limitation of the global domain shift, and solves the cross-domain recognition by finding the compact joint subspaces of source and target domain.
LooseCut: Interactive Image Segmentation with Loosely Bounded Boxes
In this paper, we develop a new LooseCut algorithm that can handle cases where the input bounding box only loosely covers the foreground object.
Combining Local Appearance and Holistic View: Dual-Source Deep Neural Networks for Human Pose Estimation
We propose a new learning-based method for estimating 2D human pose from a single image, using Dual-Source Deep Convolutional Neural Networks (DS-CNN).
Feature Sampling Strategies for Action Recognition
Although dense local spatial-temporal features with bag-of-features representation achieve state-of-the-art performance for action recognition, the huge feature number and feature size prevent current methods from scaling up to real size problems.
Video In Sentences Out
We present a system that produces sentential descriptions of video: who did what to whom, and where and how they did it.
Recognize Human Activities from Partially Observed Videos
In this paper, we propose a new method that can recognize human activities from partially observed videos in the general case.
