Search Results for author:
Found 221 papers, 112 papers with code
SRCB at SemEval-2022 Task 5: Pretraining Based Image to Text Late Sequential Fusion System for Multimodal Misogynous Meme Identification
Online misogyny meme detection is an image/text multimodal classification task, the complicated relation of image and text challenges the intelligent system’s modality fusion learning capability.
Long-range Sequence Modeling with Predictable Sparse Attention
(2) A sparse attention matrix estimation module, which predicts dominant elements of an attention matrix based on the output of the previous hidden state cross module.
P-INT: A Path-based Interaction Model for Few-shot Knowledge Graph Completion
Its general process is to first encode the implicit relation of an entity pair and then match the relation of a query entity pair with the relations of the reference entity pairs.
HOSMEL: A Hot-Swappable Modularized Entity Linking Toolkit for Chinese
We investigate the usage of entity linking (EL)in downstream tasks and present the first modularized EL toolkit for easy task adaptation.
A Pretraining Numerical Reasoning Model for Ordinal Constrained Question Answering on Knowledge Base
Knowledge Base Question Answering (KBQA) is to answer natural language questions posed over knowledge bases (KBs).
Audio-Visual Segmentation with Semantics
To deal with these problems, we propose a new baseline method that uses a temporal pixel-wise audio-visual interaction module to inject audio semantics as guidance for the visual segmentation process.
APAC: Authorized Probability-controlled Actor-Critic For Offline Reinforcement Learning
Due to the inability to interact with the environment, offline reinforcement learning (RL) methods face the challenge of estimating the Out-of-Distribution (OOD) points.
Localizing Scan Targets from Human Pose for Autonomous Lung Ultrasound Imaging
Ultrasound is progressing toward becoming an affordable and versatile solution to medical imaging.
Joint Spatio-Temporal Modeling for the Semantic Change Detection in Remote Sensing Images
Semantic Change Detection (SCD) refers to the task of simultaneously extracting the changed areas and the semantic categories (before and after the changes) in Remote Sensing Images (RSIs).
ViTPose+: Vision Transformer Foundation Model for Generic Body Pose Estimation
In this paper, we show the surprisingly good properties of plain vision transformers for body pose estimation from various aspects, namely simplicity in model structure, scalability in model size, flexibility in training paradigm, and transferability of knowledge between models, through a simple baseline model dubbed ViTPose.
Learning to Learn Better for Video Object Segmentation
Recently, the joint learning framework (JOINT) integrates matching based transductive reasoning and online inductive learning to achieve accurate and robust semi-supervised video object segmentation (SVOS).
Semantic Segmentation
Semi-Supervised Video Object Segmentation
+1
1st Workshop on Maritime Computer Vision (MaCVi) 2023: Challenge Results
The 1$^{\text{st}}$ Workshop on Maritime Computer Vision (MaCVi) 2023 focused on maritime computer vision for Unmanned Aerial Vehicles (UAV) and Unmanned Surface Vehicle (USV), and organized several subchallenges in this domain: (i) UAV-based Maritime Object Detection, (ii) UAV-based Maritime Object Tracking, (iii) USV-based Maritime Obstacle Segmentation and (iv) USV-based Maritime Obstacle Detection.
GLT-T: Global-Local Transformer Voting for 3D Single Object Tracking in Point Clouds
Technically, a global-local transformer (GLT) module is employed to integrate object- and patch-aware prior into seed point features to effectively form strong feature representation for geometric positions of the seed points, thus providing more robust and accurate cues for offset learning.
DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting
In this paper, we present DeepSolo, a simple detection transformer baseline that lets a single Decoder with Explicit Points Solo for text detection and recognition simultaneously.
Energy-Based Residual Latent Transport for Unsupervised Point Cloud Completion
Unsupervised point cloud completion aims to infer the whole geometry of a partial object observation without requiring partial-complete correspondence.
Unifying Flow, Stereo and Depth Estimation
We present a unified formulation and model for three motion and 3D perception tasks: optical flow, rectified stereo matching and unrectified stereo depth estimation from posed images.
Ranked #1 on
Optical Flow Estimation
on Sintel-clean
Rethinking Hierarchies in Pre-trained Plain Vision Transformer
Self-supervised pre-training vision transformer (ViT) via masked image modeling (MIM) has been proven very effective.
Watermarking for Out-of-distribution Detection
Out-of-distribution (OOD) detection aims to identify OOD data based on representations extracted from well-trained deep models.
Adaptive Test-Time Defense with the Manifold Hypothesis
In this work, we formulate a novel framework of adversarial robustness using the manifold hypothesis.
Oscillatory cooperation prevalence emerges from misperception
Here we show that oscillatory behaviors naturally emerge if incomplete information is incorporated into the cooperation evolution of a non-Markov model.
Towards Explainable 3D Grounded Visual Question Answering: A New Benchmark and Strong Baseline
We also propose a new 3D VQA framework to effectively predict the completely visually grounded and explainable answer.
On Robust Cross-View Consistency in Self-Supervised Monocular Depth Estimation
Compared with the photometric consistency loss as well as the rigid point cloud alignment loss, the proposed DFA and VDA losses are more robust owing to the strong representation power of deep features as well as the high tolerance of voxel density to the aforementioned challenges.
Improving RGB-D Point Cloud Registration by Learning Multi-scale Local Linear Transformation
In addition to previous methods that seek correspondences by hand-crafted or learnt geometric features, recent point cloud registration methods have tried to apply RGB-D data to achieve more accurate correspondence.
Grounded Affordance from Exocentric View
Due to the diversity of interactive affordance, the uniqueness of different individuals leads to diverse interactions, which makes it difficult to establish an explicit link between object parts and affordance labels.
Robust control problems of BSDEs coupled with value functions
A robust control problem is considered in this paper, where the controlled stochastic differential equations (SDEs) include ambiguity parameters and their coefficients satisfy non-Lipschitz continuous and non-linear growth conditions, the objective function is expressed as a backward stochastic differential equation (BSDE) with the generator depending on the value function.
Generalised Co-Salient Object Detection
To evaluate the performance of CoSOD models under the GCoSOD setting, we propose two new testing datasets, namely CoCA-Common and CoCA-Zero, where a common salient object is partially present in the former and completely absent in the latter.
Transformer Networks for Predictive Group Elevator Control
We propose a Predictive Group Elevator Scheduler by using predictive information of passengers arrivals from a Transformer based destination predictor and a linear regression model that predicts remaining time to destinations.
Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model
Large-scale vision foundation models have made significant progress in visual tasks on natural images, with vision transformers being the primary choice due to their good scalability and representation ability.
Subtype-Former: a deep learning approach for cancer subtype discovery with multi-omics data
In addition, Subtype-Former also achieved outstanding results in pan-cancer subtyping, which can help analyze the commonalities and differences across various cancer types at the molecular level.
MeshMAE: Masked Autoencoders for 3D Mesh Data Analysis
We first randomly mask some patches of the mesh and feed the corrupted mesh into Mesh Transformers.
FakeCLR: Exploring Contrastive Learning for Solving Latent Discontinuity in Data-Efficient GANs
Since data augmentation strategies have largely alleviated the training instability, how to further improve the generative performance of DE-GANs becomes a hotspot.
JPerceiver: Joint Perception Network for Depth, Pose and Layout Estimation in Driving Scenes
A naive way is to accomplish them independently in a sequential or parallel manner, but there are many drawbacks, i. e., 1) the depth and VO results suffer from the inherent scale ambiguity issue; 2) the BEV layout is directly predicted from the front-view image without using any depth-related information, although the depth map contains useful geometry clues for inferring scene layouts.
Transformer-based Context Condensation for Boosting Feature Pyramids in Object Detection
Current object detectors typically have a feature pyramid (FP) module for multi-level feature fusion (MFF) which aims to mitigate the gap between features from different levels and form a comprehensive object representation to achieve better detection performance.
ReAct: Temporal Action Detection with Relational Queries
Moreover, we propose two losses to facilitate and stabilize the training of action classification.
Ranked #4 on
Temporal Action Localization
on THUMOS’14
Audio-Visual Segmentation
To deal with the AVS problem, we propose a novel method that uses a temporal pixel-wise audio-visual interaction module to inject audio semantics as guidance for the visual segmentation process.
Towards Scale-Aware, Robust, and Generalizable Unsupervised Monocular Depth Estimation by Integrating IMU Motion Dynamics
Unsupervised monocular depth and ego-motion estimation has drawn extensive research attention in recent years.
DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer
However, these methods built upon detection transformer framework might achieve sub-optimal training efficiency and performance due to coarse positional query modeling. In addition, the point label form exploited in previous works implies the reading order of humans, which impedes the detection robustness from our observation.
Ranked #1 on
Scene Text Detection
on SCUT-CTW1500
A State Transition Model for Mobile Notifications via Survival Analysis
In particular, we provide an online use case on notification delivery time optimization to show how we make better decisions, drive more user engagement, and provide more value to users.
Re-weighting Negative Samples for Model-Agnostic Matching
Recommender Systems (RS), as an efficient tool to discover users' interested items from a very large corpus, has attracted more and more attention from academia and industry.
CLAMP: Prompt-based Contrastive Learning for Connecting Language and Animal Pose
Motivated by the progress of visual-language research, we propose that pre-trained language models (e. g., CLIP) can facilitate animal pose estimation by providing rich prior knowledge for describing animal keypoints in text.
Knowledge Learning with Crowdsourcing: A Brief Review and Systematic Perspective
Big data have the characteristics of enormous volume, high velocity, diversity, value-sparsity, and uncertainty, which lead the knowledge learning from them full of challenges.
APT-36K: A Large-scale Benchmark for Animal Pose Estimation and Tracking
Based on APT-36K, we benchmark several representative models on the following three tracks: (1) supervised animal pose estimation on a single frame under intra- and inter-domain transfer learning settings, (2) inter-species domain generalization test for unseen animals, and (3) animal pose estimation with animal tracking.
Toward Real-world Single Image Deraining: A New Benchmark and Beyond
To address these issues, we establish a new high-quality dataset named RealRain-1k, consisting of $1, 120$ high-resolution paired clean and rainy images with low- and high-density rain streaks, respectively.
Referring Image Matting
RIM aims to extract the meticulous alpha matte of the specific object that best matches the given natural language description, thus enabling a more natural and simpler instruction for image matting.
Ranked #1 on
Referring Image Matting (RefMatte-RW100)
on RefMatte
Multi-Task Learning with Multi-Query Transformer for Dense Prediction
Secondly, we design a cross task attention module to reason the dependencies among multiple tasks and feature scales from two perspectives including different tasks of the same scale and different scales of the same task.
Towards Deeper Understanding of Camouflaged Object Detection
With the above understanding about camouflaged objects, we present the first triple-task learning framework to simultaneously localize, segment, and rank camouflaged objects, indicating the conspicuousness level of camouflage.
Salient Object Detection via Bounding-box Supervision
However, as a large amount of background is excluded, the foreground bounding box region contains a less complex background, making it possible to perform handcrafted features-based saliency detection with only the cropped foreground region.
From Heavy Rain Removal to Detail Restoration: A Faster and Better Network
Firstly, a dilated dense residual block (DDRB) within the rain streaks removal network is presented to aggregate high/low level features of heavy rain.
RU-Net: Regularized Unrolling Network for Scene Graph Generation
Scene graph generation (SGG) aims to detect objects and predict the relationships between each pair of objects.
DearKD: Data-Efficient Early Knowledge Distillation for Vision Transformers
Our DearKD is a two-stage framework that first distills the inductive biases from the early intermediate layers of a CNN and then gives the transformer full play by training without distillation.
ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation
In this paper, we show the surprisingly good capabilities of plain vision transformers for pose estimation from various aspects, namely simplicity in model structure, scalability in model size, flexibility in training paradigm, and transferability of knowledge between models, through a simple baseline model called ViTPose.
Ranked #1 on
Pose Estimation
on MPII Human Pose
(using extra training data)
Learning to Purification for Unsupervised Person Re-identification
To purify the label noise, we propose to take advantage of the knowledge of teacher model in an offline scheme.
Knowledge Distillation
Unsupervised Person Re-Identification
An Energy-Based Prior for Generative Saliency
With the generative saliency model, we can obtain a pixel-wise uncertainty map from an image, indicating model confidence in the saliency prediction.
A Comprehensive Survey on Data-Efficient GANs in Image Generation
Generative Adversarial Networks (GANs) have achieved remarkable achievements in image synthesis.
VSA: Learning Varied-Size Window Attention in Vision Transformers
Attention within windows has been widely explored in vision transformers to balance the performance, computation complexity, and memory footprint.
An Empirical Study of Remote Sensing Pretraining
To this end, we train different networks from scratch with the help of the largest RS scene recognition dataset up to now -- MillionAID, to obtain a series of RS pretrained backbones, including both convolutional neural networks (CNN) and vision transformers such as Swin and ViTAE, which have shown promising performance on computer vision tasks.
Ranked #1 on
Aerial Scene Classification
on UCM (80% as trainset)
Aerial Scene Classification
Building change detection for remote sensing images
+5
BMD: A General Class-balanced Multicentric Dynamic Prototype Strategy for Source-free Domain Adaptation
Source-free Domain Adaptation (SFDA) aims to adapt a pre-trained source model to the unlabeled target domain without accessing the well-labeled source data, which is a much more practical setting due to the data privacy, security, and transmission issues.
Dynamic Focus-aware Positional Queries for Semantic Segmentation
In this paper, we propose a simple yet effective query design for semantic segmentation termed Dynamic Focus-aware Positional Queries (DFPQ), which dynamically generates positional queries conditioned on the cross-attention scores from the preceding decoder block and the positional encodings for the corresponding image features, simultaneously.
Ranked #18 on
Semantic Segmentation
on ADE20K
(using extra training data)
Rethinking Portrait Matting with Privacy Preserving
We systematically evaluate both trimap-free and trimap-based matting methods on P3M-10k and find that existing matting methods show different generalization abilities under the privacy preserving training setting, i. e., training only on face-blurred images while testing on arbitrary images.
A Roadmap for Big Model
With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm.
Learning Affordance Grounding from Exocentric Images
To empower an agent with such ability, this paper proposes a task of affordance grounding from exocentric view, i. e., given exocentric human-object interaction and egocentric object images, learning the affordance knowledge of the object and transferring it to the egocentric image using only the affordance label as supervision.
AlignTransformer: Hierarchical Alignment of Visual Regions and Disease Tags for Medical Report Generation
The acquired disease-grounded visual features can better represent the abnormal regions of the input image, which could alleviate data bias problem; 2) MGT module effectively uses the multi-grained features and Transformer framework to generate the long medical report.
Towards Data-Efficient Detection Transformers
Besides, we introduce a simple yet effective label augmentation method to provide richer supervision and improve data efficiency.
Towards Scale Consistent Monocular Visual Odometry by Learning from the Virtual World
In this work, we propose VRVO, a novel framework for retrieving the absolute scale from virtual data that can be easily obtained from modern simulation environments, whereas in the real domain no stereo or ground-truth data are required in either the training or inference phases.
Information-Theoretic Odometry Learning
In this paper, we propose a unified information theoretic framework for learning-motivated methods aimed at odometry estimation, a crucial component of many robotics and vision tasks such as navigation and virtual reality where relative camera poses are required in real time.
Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answering
Recent works on knowledge base question answering (KBQA) retrieve subgraphs for easier reasoning.
ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond
Vision transformers have shown great potential in various computer vision tasks owing to their strong capability to model long-range dependency using the self-attention mechanism.
Ranked #2 on
Image Classification
on ImageNet ReaL
Deep Interest Highlight Network for Click-Through Rate Prediction in Trigger-Induced Recommendation
In many classical e-commerce platforms, personalized recommendation has been proven to be of great business value, which can improve user satisfaction and increase the revenue of platforms.
SASA: Semantics-Augmented Set Abstraction for Point-based 3D Object Detection
We observe that the prevailing set abstraction design for down-sampling points may maintain too much unimportant background information that can affect feature learning for detecting objects.
Exemplar-free Class Incremental Learning via Discriminative and Comparable One-class Classifiers
DisCOIL follows the basic principle of POC, but it adopts variational auto-encoders (VAE) instead of other well-established one-class classifiers (e. g. deep SVDD), because a trained VAE can not only identify the probability of an input sample belonging to a class but also generate pseudo samples of the class to assist in learning new tasks.
3DJCG: A Unified Framework for Joint Dense Captioning and Visual Grounding on 3D Point Clouds
Observing that the 3D captioning task and the 3D grounding task contain both shared and complementary information in nature, in this work, we propose a unified framework to jointly solve these two distinct but closely related tasks in a synergistic fashion, which consists of both shared task-agnostic modules and lightweight task-specific modules.
ISNet: Shape Matters for Infrared Small Target Detection
TOAA block calculates the low-level information with attention mechanism in both row and column directions and fuses it with the high-level information to capture the shape characteristic of targets and suppress noises.
Siamese Network with Interactive Transformer for Video Object Segmentation
Semi-supervised video object segmentation (VOS) refers to segmenting the target object in remaining frames given its annotation in the first frame, which has been actively studied in recent years.
Semantic Segmentation
Semi-Supervised Video Object Segmentation
+1
Semi-supervised Salient Object Detection with Effective Confidence Estimation
The success of existing salient object detection models relies on a large pixel-wise labeled training dataset.
MetaCVR: Conversion Rate Prediction via Meta Learning in Small-Scale Recommendation Scenarios
At last, we develop an Ensemble Prediction Network (EPN) which incorporates the output of FRN and DMN to make the final CVR prediction.
Modeling Occasion Evolution in Frequency Domain for Promotion-Aware Click-Through Rate Prediction
In this paper, we propose a novel CTR model named MOEF for recommendations under frequent changes of occasions.
Learning Generative Vision Transformer with Energy-Based Latent Space for Saliency Prediction
In this paper, we take a step further by proposing a novel generative vision transformer with latent variables following an informative energy-based prior for salient object detection.
Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition
Technically, given the character segmentation maps predicted by a VR model, we construct a subgraph for each instance, where nodes represent the pixels in it and edges are added between nodes based on their spatial similarity.
Ranked #2 on
Scene Text Recognition
on SVTP
(using extra training data)
Injecting Numerical Reasoning Skills into Knowledge Base Question Answering Models
Embedding-based methods are popular for Knowledge Base Question Answering (KBQA), but few current models have numerical reasoning skills and thus struggle to answer ordinal constrained questions.
Recurrent Glimpse-based Decoder for Detection with Transformer
Then, a glimpse-based decoder is introduced to provide refined detection results based on both the glimpse features and the attention modeling outputs of the previous stage.
Ranked #1 on
Object Detection
on COCO
NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation
Data augmentation is an important component in the robustness evaluation of models in natural language processing (NLP) and in enhancing the diversity of the data they are trained on.
GETAM: Gradient-weighted Element-wise Transformer Attention Map for Weakly-supervised Semantic segmentation
To bridge their gap, a Class Activation Map (CAM) is usually generated to provide pixel level pseudo labels.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
PolyphonicFormer: Unified Query Learning for Depth-aware Video Panoptic Segmentation
The Depth-aware Video Panoptic Segmentation (DVPS) is a new challenging vision problem that aims to predict panoptic segmentation and depth in a video simultaneously.
A Multi-Strategy based Pre-Training Method for Cold-Start Recommendation
In terms of the pretext task, in addition to considering the intra-correlations of users and items by the embedding reconstruction task, we add embedding contrastive learning task to capture inter-correlations of users and items.
FIBA: Frequency-Injection based Backdoor Attack in Medical Image Analysis
However, designing a unified BA method that can be applied to various MIA systems is challenging due to the diversity of imaging modalities (e. g., X-Ray, CT, and MRI) and analysis tasks (e. g., classification, detection, and segmentation).
GMFlow: Learning Optical Flow via Global Matching
Learning-based optical flow estimation has been dominated with the pipeline of cost volume with convolutions for flow regression, which is inherently limited to local correlations and thus is hard to address the long-standing challenge of large displacements.
RegionCL: Can Simple Region Swapping Contribute to Contrastive Learning?
In this paper, we make the first attempt to demonstrate the importance of both regions in cropping from a complete perspective and propose a simple yet effective pretext task called Region Contrastive Learning (RegionCL).
Pruning Self-attentions into Convolutional Layers in Single Path
Vision Transformers (ViTs) have achieved impressive performance over various computer vision tasks.
A General Divergence Modeling Strategy for Salient Object Detection
Given multiple saliency annotations, we introduce a general divergence modeling strategy via random sampling, and apply our strategy to an ensemble based framework and three latent variable model based solutions to explore the subjective nature of saliency.
Dense Uncertainty Estimation via an Ensemble-based Conditional Latent Variable Model
Uncertainty estimation has been extensively studied in recent literature, which can usually be classified as aleatoric uncertainty and epistemic uncertainty.
Inferring the Class Conditional Response Map for Weakly Supervised Semantic Segmentation
To solve this, most existing approaches follow a multi-training pipeline to refine CAMs for better pseudo-labels, which includes: 1) re-training the classification model to generate CAMs; 2) post-processing CAMs to obtain pseudo labels; and 3) training a semantic segmentation model with the obtained pseudo labels.
Ranked #9 on
Weakly-Supervised Semantic Segmentation
on PASCAL VOC 2012 test
(using extra training data)
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Capsule Graph Neural Networks with EM Routing
To effectively classify graph instances, graph neural networks need to have the capability to capture the part-whole relationship existing in a graph.
SAR-Net: A Scenario-Aware Ranking Network for Personalized Fair Recommendation in Hundreds of Travel Scenarios
In this paper, we propose a novel Scenario-Aware Ranking Network (SAR-Net) to address these issues.
Dense Uncertainty Estimation
Deep neural networks can be roughly divided into deterministic neural networks and stochastic neural networks. The former is usually trained to achieve a mapping from input space to output space via maximum likelihood estimation for the weights, which leads to deterministic predictions during testing.
FP-DETR: Detection Transformer Advanced by Fully Pre-training
To this end, we propose the task adapter which leverages self-attention to model the contextual relation between object query embedding.
Modeling Variable Space with Residual Tensor Networks for Multivariate Time Series
In this framework, we derive the mathematical representation of the variable space, and then use a tensor network based on the idea of low-rank approximation to model the variable space.
RGB-D Saliency Detection via Cascaded Mutual Information Minimization
In this paper, we introduce a novel multi-stage cascaded learning framework via mutual information minimization to "explicitly" model the multi-modal information between RGB image and depth data.
Stagewise Unsupervised Domain Adaptation with Adversarial Self-Training for Road Segmentation of Remote Sensing Images
In this paper, we propose a novel stagewise domain adaptation model called RoadDA to address the DS issue in this field.
AP-10K: A Benchmark for Animal Pose Estimation in the Wild
The experimental results provide sound empirical evidence on the superiority of learning from diverse animals species in terms of both accuracy and generalization ability.
Out-of-boundary View Synthesis Towards Full-Frame Video Stabilization
However, since the view outside the boundary is not available during warping, the resulting holes around the boundary of the stabilized frame must be discarded (i. e., cropping) to maintain visual consistency, and thus does leads to a tradeoff between stability and cropping ratio.
Graph Contrastive Learning for Anomaly Detection
To achieve the contrastive objective, we design a graph neural network encoder that can infer and further remove suspicious links during message passing, as well as learn the global context of the input graph.
Bi-Temporal Semantic Reasoning for the Semantic Change Detection in HR Remote Sensing Images
Recent studies indicate that the SCD can be modeled through a triple-branch Convolutional Neural Network (CNN), which contains two temporal branches and a change branch.
Learning Visual Affordance Grounding from Demonstration Videos
For the object branch, we introduce a semantic enhancement module (SEM) to make the network focus on different parts of the object according to the action classes and utilize a distillation loss to align the output features of the object branch with that of the video branch and transfer the knowledge in the video branch to the object branch.
One-Shot Object Affordance Detection in the Wild
To empower robots with this ability in unseen scenarios, we first study the challenging one-shot affordance detection problem in this paper, i. e., given a support image that depicts the action purpose, all objects in a scene with the common affordance should be detected.
I3CL:Intra- and Inter-Instance Collaborative Learning for Arbitrary-shaped Scene Text Detection
Existing methods for arbitrary-shaped text detection in natural scenes face two critical issues, i. e., 1) fracture detections at the gaps in a text instance; and 2) inaccurate detections of arbitrary-shaped text instances with diverse background context.
Ranked #2 on
Scene Text Detection
on SCUT-CTW1500
TA-MAMC at SemEval-2021 Task 4: Task-adaptive Pretraining and Multi-head Attention for Abstract Meaning Reading Comprehension
This paper describes our system used in the SemEval-2021 Task4 Reading Comprehension of Abstract Meaning, achieving 1st for subtask 1 and 2nd for subtask 2 on the leaderboard.
Exploring Sequence Feature Alignment for Domain Adaptive Detection Transformers
In DQFA, a novel domain query is used to aggregate and align global context from the token sequence of both domains.
DSP: Dual Soft-Paste for Unsupervised Domain Adaptive Semantic Segmentation
In addition, feature-level alignment is carried out by aligning the feature maps of the source and target images from student network using a weighted maximum mean discrepancy loss.
Ranked #17 on
Synthetic-to-Real Translation
on SYNTHIA-to-Cityscapes
Deep Automatic Natural Image Matting
To address the problem, a novel end-to-end matting network is proposed, which can predict a generalized trimap for any image of the above types as a unified semantic representation.
Ranked #1 on
Image Matting
on AIM-500
Looking Outside the Window: Wide-Context Transformer for the Semantic Segmentation of High-Resolution Remote Sensing Images
To overcome this limitation, we propose a Wide-Context Network (WiCoNet) for the semantic segmentation of HR RSIs.
One-Shot Affordance Detection
To empower robots with this ability in unseen scenarios, we consider the challenging one-shot affordance detection problem in this paper, i. e., given a support image that depicts the action purpose, all objects in a scene with the common affordance should be detected.
Few-Shot Domain Expansion for Face Anti-Spoofing
In practice, given a handful of labeled samples from a new deployment scenario (target domain) and abundant labeled face images in the existing source domain, the FAS system is expected to perform well in the new scenario without sacrificing the performance on the original domain.
Energy-Based Generative Cooperative Saliency Prediction
In this paper, to model the uncertainty of visual saliency, we study the saliency prediction problem from the perspective of generative models by learning a conditional probability distribution over the saliency map given an input image, and treating the saliency prediction as a sampling process from the learned distribution.
Exploring Depth Contribution for Camouflaged Object Detection
In this paper, we study the depth contribution for camouflaged object detection, where the depth maps are generated with existing monocular depth estimation (MDE) methods.
Confidence-Aware Learning for Camouflaged Object Detection
Then, we concatenate it with the input image and feed it to the confidence estimation network to produce an one channel confidence map. We generate dynamic supervision for the confidence estimation network, representing the agreement of camouflage prediction with the ground truth camouflage map.
Invertible Attention
Attention has been proved to be an efficient mechanism to capture long-range dependencies.
ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias
Nevertheless, vision transformers treat an image as 1D sequence of visual tokens, lacking an intrinsic inductive bias (IB) in modeling local visual structures and dealing with scale variance.
Ranked #2 on
Video Object Segmentation
on DAVIS 2017
A Comprehensive Survey and Taxonomy on Single Image Dehazing Based on Deep Learning
With the development of convolutional neural networks, hundreds of deep learning based dehazing methods have been proposed.
Salient Objects in Clutter
This design bias has led to a saturation in performance for state-of-the-art SOD models when evaluated on existing datasets.
End-to-end One-shot Human Parsing
To address three main challenges in OSHP, i. e., small sizes, testing bias, and similar parts, we devise an End-to-end One-shot human Parsing Network (EOP-Net).
Privacy-Preserving Portrait Matting
We systematically evaluate both trimap-free and trimap-based matting methods on P3M-10k and find that existing matting methods show different generalization capabilities when following the Privacy-Preserving Training (PPT) setting, i. e., training on face-blurred images and testing on arbitrary images.
Ranked #1 on
Image Matting
on P3M-10k
Hierarchically Modeling Micro and Macro Behaviors via Multi-Task Learning for Conversion Rate Prediction
Motivated by this observation, we propose a novel \emph{CVR} prediction method by Hierarchically Modeling both Micro and Macro behaviors ($HM^3$).
Generative Transformer for Accurate and Reliable Salient Object Detection
For the former, we apply transformer to a deterministic model, and explain that the effective structure modeling and global context modeling abilities lead to its superior performance compared with the CNN based frameworks.
Learning structure-aware semantic segmentation with image-level supervision
Within this pipeline, the class activation map (CAM) is obtained and further processed to serve as a pseudo label to train the semantic segmentation model in a fully-supervised manner.
Bootstrapping Your Own Positive Sample: Contrastive Learning With Electronic Health Record Data
Electronic Health Record (EHR) data has been of tremendous utility in Artificial Intelligence (AI) for healthcare such as predicting future clinical events.
Weakly Supervised Video Salient Object Detection
Significant performance improvement has been achieved for fully-supervised video salient object detection with the pixel-wise labeled training datasets, which are time-consuming and expensive to obtain.
Uncertainty-aware Joint Salient Object and Camouflaged Object Detection
Visual salient object detection (SOD) aims at finding the salient object(s) that attract human attention, while camouflaged object detection (COD) on the contrary intends to discover the camouflaged object(s) that hidden in the surrounding.
VDM-DA: Virtual Domain Modeling for Source Data-free Domain Adaptation
On the other hand, we also design an effective distribution alignment method to reduce the distribution divergence between the virtual domain and the target domain by gradually improving the compactness of the target domain distribution through model learning.
Forest Fire Clustering for Single-cell Sequencing with Iterative Label Propagation and Parallelized Monte Carlo Simulation
Here, we introduce Forest Fire Clustering, an efficient and interpretable method for cell-type discovery from single-cell data.
Simultaneously Localize, Segment and Rank the Camouflaged Objects
With the above understanding about camouflaged objects, we present the first ranking based COD network (Rank-Net) to simultaneously localize, segment and rank camouflaged objects.
Understanding WeChat User Preferences and "Wow" Diffusion
"Top Stories" is a novel friend-enhanced recommendation engine in WeChat, in which users can read articles based on preferences of both their own and their friends.
Graph Representation Learning
Social and Information Networks
Koopmans' theorem as the mechanism of nearly gapless surface states in self-doped magnetic topological insulators
The magnetization-induced gap at the surface state is widely believed as the kernel of magnetic topological insulators (MTIs) because of its relevance to various topological phenomena, such as the quantum anomalous Hall effect and the axion insulator phase.
Materials Science
Active Learning to Classify Macromolecular Structures in situ for Less Supervision in Cryo-Electron Tomography
Deep learning based subtomogram classification have played critical roles for such tasks.
Multi-Stage Transmission Line Flow Control Using Centralized and Decentralized Reinforcement Learning Agents
At stage one, centralized soft actor-critic (SAC) agent is trained to control generator active power outputs in a wide area to control transmission line flows against specified security limits.
TextTN: Probabilistic Encoding of Language on Tensor Network
As a novel model that bridges machine learning and quantum theory, tensor network (TN) has recently gained increasing attention and successful applications for processing natural images.
Recommending Courses in MOOCs for Jobs: An Auto Weak Supervision Approach
On the one hand, the framework enables training multiple supervised ranking models upon the pseudo labels produced by multiple unsupervised ranking models.
Memory-Gated Recurrent Networks
The essence of multivariate sequential learning is all about how to extract dependencies in data.
Residual Matrix Product State for Machine Learning
Tensor network, which originates from quantum physics, is emerging as an efficient tool for classical and quantum machine learning.
Progressive One-shot Human Parsing
In this paper, we devise a novel Progressive One-shot Parsing network (POPNet) to address two critical challenges , i. e., testing bias and small sizes.
6 GHz hyperfast rotation of an optically levitated nanoparticle in vacuum
We measure a highest rotation frequency about 4. 3 GHz of the trapped nanoparticle without feedback cooling and a 6 GHz rotation with feedback cooling, which is the fastest mechanical rotation ever reported to date.
Optics Mesoscale and Nanoscale Physics Quantum Physics
SPOC learner's final grade prediction based on a novel sampling batch normalization embedded neural network method
To solve this problem, a sampling batch normalization embedded deep neural network (SBNEDNN) method is developed in this paper.
CODE: Contrastive Pre-training with Adversarial Fine-tuning for Zero-shot Expert Linking
In this paper, we propose CODE, which first pre-trains an expert linking model by contrastive learning on AMiner such that it can capture the representation and matching patterns of experts without supervised signals, then it is fine-tuned between AMiner and external sources to enhance the models transferability in an adversarial manner.
Pre-Training Graph Neural Networks for Cold-Start Users and Items Representation
Cold-start problem is a fundamental challenge for recommendation tasks.
Uncertainty-Aware Deep Calibrated Salient Object Detection
Existing deep neural network based salient object detection (SOD) methods mainly focus on pursuing high network accuracy.
Meta Learning-based MIMO Detectors: Design, Simulation, and Experimental Test
An unfolded turbo decoding module, called TurboNet, is used for channel decoding.
Auto Learning Attention
Attention modules have been demonstrated effective in strengthening the representation ability of a neural network via reweighting spatial or channel features or stacking both operations sequentially.
3D Guided Weakly Supervised Semantic Segmentation
In this paper, we propose a weakly supervised 2D semantic segmentation model by incorporating sparse bounding box labels with available 3D information, which is much easier to obtain with advanced sensors.
2D Semantic Segmentation
Weakly supervised Semantic Segmentation
+1
Inter-layer Transition in Neural Architecture Search
Differential Neural Architecture Search (NAS) methods represent the network architecture as a repetitive proxy directed acyclic graph (DAG) and optimize the network weights and architecture weights alternatively in a differential manner.
SIR: Self-supervised Image Rectification via Seeing the Same Scene from Multiple Different Lenses
However, the model may overfit the synthetic images and generalize not well on real-world fisheye images due to the limited universality of a specific distortion model and the lack of explicitly modeling the distortion and rectification process.
DUT: Learning Video Stabilization by Simply Watching Unstable Videos
In this paper, we attempt to tackle the video stabilization problem in a deep unsupervised learning manner, which borrows the divide-and-conquer idea from traditional stabilizers while leveraging the representation power of DNNs to handle the challenges in real-world scenarios.
Empowering Things with Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Things
AI introduced into the IoT heralds the era of artificial intelligence of things (AIoT).