Search Results for author:
Found 155 papers, 72 papers with code
Propagating Over Phrase Relations for One-Stage Visual Grounding
Phrase level visual grounding aims to locate in an image the corresponding visual regions referred to by multiple noun phrases in a given sentence.
UniFL: Improve Stable Diffusion via Unified Feedback Learning
Diffusion models have revolutionized the field of image generation, leading to the proliferation of high-quality models and diverse downstream applications.
OVER-NAV: Elevating Iterative Vision-and-Language Navigation with Open-Vocabulary Detection and StructurEd Representation
Recent advances in Iterative Vision-and-Language Navigation (IVLN) introduce a more meaningful and practical paradigm of VLN by maintaining the agent's memory across tours of scenes.
Decoupled Pseudo-labeling for Semi-Supervised Monocular 3D Object Detection
Additionally, we present a DepthGradient Projection (DGP) module to mitigate optimization conflicts caused by noisy depth supervision of pseudo-labels, effectively decoupling the depth gradient and removing conflicting gradients.
NeRF-HuGS: Improved Neural Radiance Fields in Non-static Scenes Using Heuristics-Guided Segmentation
Neural Radiance Field (NeRF) has been widely recognized for its excellence in novel view synthesis and 3D scene reconstruction.
Gradient-based Sampling for Class Imbalanced Semi-supervised Object Detection
To tackle the confirmation bias from incorrect pseudo labels of minority classes, the class-rebalancing sampling module resamples unlabeled data following the guidance of the gradient-based reweighting module.
Annotation-Efficient Polyp Segmentation via Active Learning
To minimize annotation costs, we propose a deep active learning framework for annotation-efficient polyp segmentation.
Semi- and Weakly-Supervised Learning for Mammogram Mass Segmentation with Limited Annotations
Accurate identification of breast masses is crucial in diagnosing breast cancer; however, it can be challenging due to their small size and being camouflaged in surrounding normal glands.
Mask-Enhanced Segment Anything Model for Tumor Lesion Semantic Segmentation
Tumor lesion segmentation on CT or MRI images plays a critical role in cancer diagnosis and treatment planning.
Large Multimodal Agents: A Survey
In this paper, we conduct a systematic review of LLM-driven multimodal agents, which we refer to as large multimodal agents ( LMAs for short).
UniCell: Universal Cell Nucleus Classification via Prompt Learning
The recognition of multi-class cell nuclei can significantly facilitate the process of histopathological diagnosis.
Cell Graph Transformer for Nuclei Classification
Nuclei classification is a critical step in computer-aided diagnosis with histopathology images.
Multimodal Embodied Interactive Agent for Cafe Scene
To overcome this limitation, we introduce the Multimodal Embodied Interactive Agent (MEIA), capable of translating high-level tasks expressed in natural language into a sequence of executable actions.
TIP-Editor: An Accurate 3D Editor Following Both Text-Prompts And Image-Prompts
To this end, we propose a 3D scene editing framework, TIPEditor, that accepts both text and image prompts and a 3D bounding box to specify the editing region.
Inter-Domain Mixup for Semi-Supervised Domain Adaptation
However, existing SSDA work fails to make full use of label information from both source and target domains for feature alignment across domains, resulting in label mismatch in the label space during model testing.
Semi-supervised Domain Adaptation
Unsupervised Domain Adaptation
Adaptive Betweenness Clustering for Semi-Supervised Domain Adaptation
Once the graph has been refined, Adaptive Betweenness Clustering is introduced to facilitate semantic transfer by using across-domain betweenness clustering and within-domain betweenness clustering, thereby propagating semantic label information from labeled samples across domains to unlabeled target data.
ECC-PolypDet: Enhanced CenterNet with Contrastive Learning for Automatic Polyp Detection
Accurate polyp detection is critical for early colorectal cancer diagnosis.
Credible Teacher for Semi-Supervised Object Detection in Open Scene
Credible Teacher adopts an interactive teaching mechanism using flexible labels to prevent uncertain pseudo labels from misleading the model and gradually reduces its uncertainty through the guidance of other credible pseudo labels.
Removing Interference and Recovering Content Imaginatively for Visible Watermark Removal
Visible watermarks, while instrumental in protecting image copyrights, frequently distort the underlying content, complicating tasks like scene interpretation and image editing.
Variance-insensitive and Target-preserving Mask Refinement for Interactive Image Segmentation
We introduce a novel method, Variance-Insensitive and Target-Preserving Mask Refinement to enhance segmentation quality with fewer user inputs.
FedDiv: Collaborative Noise Filtering for Federated Learning with Noisy Labels
However, these prior methods do not learn noise filters by exploiting knowledge across all clients, leading to sub-optimal and inferior noise filtering performance and thus damaging training stability.
GSmoothFace: Generalized Smooth Talking Face Generation via Fine Grained 3D Face Guidance
Our proposed GSmoothFace model mainly consists of the Audio to Expression Prediction (A2EP) module and the Target Adaptive Face Translation (TAFT) module.
Open-Vocabulary Segmentation with Semantic-Assisted Calibration
We attribute this to the in-vocabulary embedding and domain-biased CLIP prediction.
Customize your NeRF: Adaptive Source Driven 3D Scene Editing via Local-Global Iterative Training
In this paper, we target the adaptive source driven 3D scene editing task by proposing a CustomNeRF model that unifies a text description or a reference image as the editing prompt.
Affine-Consistent Transformer for Multi-Class Cell Nuclei Detection
Multi-class cell nuclei detection is a fundamental prerequisite in the diagnosis of histopathology.
Prompt-based Grouping Transformer for Nucleus Detection and Classification
Automatic nuclei detection and classification can produce effective information for disease diagnosis.
Diffusion-based Data Augmentation for Nuclei Image Segmentation
Therefore, augmenting a dataset with only a few labeled images to improve the segmentation performance is of significant research and application value.
Multi-stream Cell Segmentation with Low-level Cues for Multi-modality Images
Afterward, we train a separate segmentation model for each category using the images in the corresponding category.
Semantic-aware Temporal Channel-wise Attention for Cardiac Function Assessment
Cardiac function assessment aims at predicting left ventricular ejection fraction (LVEF) given an echocardiogram video, which requests models to focus on the changes in the left ventricle during the cardiac cycle.
ArSDM: Colonoscopy Images Synthesis with Adaptive Refinement Semantic Diffusion Models
Colonoscopy analysis, particularly automatic polyp segmentation and detection, is essential for assisting clinical diagnosis and treatment.
MMAPS: End-to-End Multi-Grained Multi-Modal Attribute-Aware Product Summarization
Furthermore, we model product attributes based on both text and image modalities so that multi-modal product characteristics can be manifested in the generated summaries.
WMFormer++: Nested Transformer for Visible Watermark Removal via Implict Joint Learning
Existing watermark removal methods mainly rely on UNet with task-specific decoder branches--one for watermark localization and the other for background image restoration.
Bridging Vision and Language Encoders: Parameter-Efficient Tuning for Referring Image Segmentation
Parameter Efficient Tuning (PET) has gained attention for reducing the number of parameters while maintaining performance and providing better hardware resource savings, but few studies investigate dense prediction tasks and interaction between modalities.
Ranked #2 on
Referring Expression Segmentation
on RefCOCO
Divide and Adapt: Active Domain Adaptation via Customized Learning
To accommodate active learning and domain adaption, the two naturally different tasks, in a collaborative framework, we advocate that a customized learning strategy for the target data is the key to the success of ADA solutions.
Advancing Visual Grounding with Scene Knowledge: Benchmark and Method
Therefore, in this paper, we propose a novel benchmark of \underline{S}cene \underline{K}nowledge-guided \underline{V}isual \underline{G}rounding (SK-VG), where the image content and referring expressions are not sufficient to ground the target objects, forcing the models to have a reasoning ability on the long-form scene knowledge.
Improved Distribution Matching for Dataset Condensation
In this paper, we propose a novel dataset condensation method based on distribution matching, which is more efficient and promising.
SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training
Moreover, these methods ignore how to utilize the fine-grained dependencies among different skeleton joints to pre-train an efficient skeleton sequence learning model that can generalize well across different datasets.
Semi-DETR: Semi-Supervised Object Detection with Detection Transformers
Specifically, we propose a Stage-wise Hybrid Matching strategy that combines the one-to-many assignment and one-to-one assignment strategies to improve the training efficiency of the first stage and thus provide high-quality pseudo labels for the training of the second stage.
Universal Semi-supervised Model Adaptation via Collaborative Consistency Training
In this paper, we introduce a realistic and challenging domain adaptation problem called Universal Semi-supervised Model Adaptation (USMA), which i) requires only a pre-trained source model, ii) allows the source and target domain to have different label sets, i. e., they share a common label set and hold their own private label set, and iii) requires only a few labeled samples in each class of the target domain.
CausalVLR: A Toolbox and Benchmark for Visual-Linguistic Causal Reasoning
We present CausalVLR (Causal Visual-Linguistic Reasoning), an open-source toolbox containing a rich set of state-of-the-art causal relation discovery and causal inference methods for various visual-linguistic reasoning tasks, such as VQA, image/video captioning, medical report generation, model generalization and robustness, etc.
Exploration and Exploitation of Unlabeled Data for Open-Set Semi-Supervised Learning
In this paper, we address a complex but practical scenario in semi-supervised learning (SSL) named open-set SSL, where unlabeled data contain both in-distribution (ID) and out-of-distribution (OOD) samples.
DreamEditor: Text-Driven 3D Scene Editing with Neural Fields
Neural fields have achieved impressive advancements in view synthesis and scene reconstruction.
DenseLight: Efficient Control for Large-scale Traffic Signals with Dense Feedback
1) The travel time of a vehicle is delayed feedback on the effectiveness of TSC policy at each traffic intersection since it is obtained after the vehicle has left the road network.
Parametric Implicit Face Representation for Audio-Driven Facial Reenactment
In this work, we break these trade-offs with our novel parametric implicit face representation and propose a novel audio-driven facial reenactment framework that is both controllable and can generate high-quality talking heads.
YONA: You Only Need One Adjacent Reference-frame for Accurate and Fast Video Polyp Detection
YONA fully exploits the information of one previous adjacent frame and conducts polyp detection on the current frame without multi-frame collaborations.
Long-term Wind Power Forecasting with Hierarchical Spatial-Temporal Transformer
In this work, we propose a novel end-to-end wind power forecasting model named Hierarchical Spatial-Temporal Transformer Network (HSTTN) to address the long-term WPF problems.
Identity-Preserving Talking Face Generation with Landmark and Appearance Priors
Prior landmark characteristics of the speaker's face are employed to make the generated landmarks coincide with the facial outline of the speaker.
Visual Causal Scene Refinement for Video Question Answering
Our VCSR involves two essential modules: i) the Question-Guided Refiner (QGR) module, which refines consecutive video frames guided by the question semantics to obtain more representative segment features for causal front-door intervention; ii) the Causal Scene Separator (CSS) module, which discovers a collection of visual causal and non-causal scenes based on the visual-linguistic causal relevance and estimates the causal effect of the scene-separating intervention in a contrastive learning manner.
SCoDA: Domain Adaptive Shape Completion for Real Scans
Thus, we propose a new task, SCoDA, for the domain adaptation of real scan shape completion from synthetic data.
Urban Regional Function Guided Traffic Flow Prediction
The prediction of traffic flow is a challenging yet crucial problem in spatial-temporal analysis, which has recently gained increasing interest.
Cross-Modal Causal Intervention for Medical Report Generation
Medical report generation (MRG) is essential for computer-aided diagnosis and medication guidance, which can relieve the heavy burden of radiologists by automatically generating the corresponding medical reports according to the given radiology image.
Structure Embedded Nucleus Classification for Histopathology Images
Next, we convert a histopathology image into a graph structure with nuclei as nodes, and build a graph neural network to embed the spatial distribution of nuclei into their representations.
Towards Unifying Medical Vision-and-Language Pre-training via Soft Prompts
Medical vision-and-language pre-training (Med-VLP) has shown promising improvements on many downstream medical tasks owing to its applicability to extracting generic representations from medical images and texts.
Adaptive Context Selection for Polyp Segmentation
To tackle these issues, we propose an adaptive context selection based encoder-decoder framework which is composed of Local Context Attention (LCA) module, Global Context Module (GCM) and Adaptive Selection Module (ASM).
Self-Supervised Correction Learning for Semi-Supervised Biomedical Image Segmentation
Since the two tasks rely on similar feature information, the unlabeled data effectively enhances the representation of the network to the lesion regions and further improves the segmentation performance.
Lesion-aware Dynamic Kernel for Polyp Segmentation
Automatic and accurate polyp segmentation plays an essential role in early colorectal cancer diagnosis.
RankMatch: Fostering Confidence and Consistency in Learning with Noisy Labels
Confidence-wise, we propose a novel sample selection strategy based on confidence representation voting instead of the widely-used small-loss criterion.
Enhanced Soft Label for Semi-Supervised Semantic Segmentation
As a mainstream framework in the field of semi-supervised learning (SSL), self-training via pseudo labeling and its variants have witnessed impressive progress in semi-supervised semantic segmentation with the recent advance of deep neural networks.
Which Pixel to Annotate: a Label-Efficient Nuclei Segmentation Framework
Recently deep neural networks, which require a large amount of annotated samples, have been widely applied in nuclei instance segmentation of H\&E stained pathology images.
BoxPolyp:Boost Generalized Polyp Segmentation Using Extra Coarse Bounding Box Annotations
In practice, box annotations are applied to alleviate the over-fitting issue of previous polyp segmentation models, which generate fine-grained polyp area through the iterative boosted segmentation model.
Compound Batch Normalization for Long-tailed Image Classification
It can model the feature space more comprehensively and reduce the dominance of head classes.
Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning
We investigate a practical domain adaptation task, called source-free domain adaptation (SFUDA), where the source-pretrained model is adapted to the target domain without access to the source data.
Ranked #4 on
Source-Free Domain Adaptation
on VisDA-2017
Being Comes from Not-being: Open-vocabulary Text-to-Motion Generation with Wordless Training
During inference, instead of changing the motion generator, our method reformulates the input text into a masked motion as the prompt for the motion generator to ``reconstruct'' the motion.
View-Disentangled Transformer for Brain Lesion Detection
Deep neural networks (DNNs) have been widely adopted in brain lesion detection and segmentation.
Attentive Symmetric Autoencoder for Brain MRI Segmentation
Self-supervised learning methods based on image patch reconstruction have witnessed great success in training auto-encoders, whose pre-trained weights can be transferred to fine-tune other downstream tasks of image understanding.
Align, Reason and Learn: Enhancing Medical Vision-and-Language Pre-training with Knowledge
Most existing methods mainly contain three elements: uni-modal encoders (i. e., a vision encoder and a language encoder), a multi-modal fusion module, and pretext tasks, with few studies considering the importance of medical domain expert knowledge and explicitly exploiting such knowledge to facilitate Med-VLP.
Multi-Modal Masked Autoencoders for Medical Vision-and-Language Pre-Training
Besides, we conduct further analysis to better verify the effectiveness of different components of our approach and various settings of pre-training.
Neighborhood Collective Estimation for Noisy Label Identification and Correction
Specifically, our method is divided into two steps: 1) Neighborhood Collective Noise Verification to separate all training samples into a clean or noisy subset, 2) Neighborhood Collective Label Correction to relabel noisy samples, and then auxiliary techniques are used to assist further model optimization.
Robust Real-World Image Super-Resolution against Adversarial Attacks
Since the frequency masking may not only destroys the adversarial perturbations but also affects the sharp details in a clean image, we further develop an adversarial sample classifier based on the frequency domain of images to determine if applying the proposed mask module.
Centrality and Consistency: Two-Stage Clean Samples Identification for Learning with Instance-Dependent Noisy Labels
In this paper, we propose a two-stage clean samples identification method to address the aforementioned challenge.
Ranked #3 on
Image Classification
on Clothing1M
(using extra training data)
Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering
Existing visual question answering methods often suffer from cross-modal spurious correlations and oversimplified event-level reasoning processes that fail to capture event temporality, causality, and dynamics spanning over the video.
Less is More: Adaptive Curriculum Learning for Thyroid Nodule Diagnosis
Thyroid nodule classification aims at determining whether the nodule is benign or malignant based on a given ultrasound image.
BronchusNet: Region and Structure Prior Embedded Representation Learning for Bronchus Segmentation and Classification
CT-based bronchial tree analysis plays an important role in the computer-aided diagnosis for respiratory diseases, as it could provide structured information for clinicians.
Multi-level Consistency Learning for Semi-supervised Domain Adaptation
Semi-supervised domain adaptation (SSDA) aims to apply knowledge learned from a fully labeled source domain to a scarcely labeled target domain.
Ranked #1 on
Semi-supervised Domain Adaptation
on VisDA2017
Dual Adversarial Adaptation for Cross-Device Real-World Image Super-Resolution
To address this issue, we propose an unsupervised domain adaptation mechanism for real-world SR, named Dual ADversarial Adaptation (DADA), which only requires LR images in the target domain with available real paired data from a source camera.
Causal Reasoning Meets Visual Representation Learning: A Prospective Study
Visual representation learning is ubiquitous in various real-world applications, including visual comprehension, video understanding, multi-modal analysis, human-computer interaction, and urban computing.
Open Set Domain Adaptation By Novel Class Discovery
In Open Set Domain Adaptation (OSDA), large amounts of target samples are drawn from the implicit categories that never appear in the source domain.
X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning
Thus, a more faithful caption can be generated only using point clouds during the inference.
Unsupervised Domain Adaptive Salient Object Detection Through Uncertainty-Aware Pseudo-Label Learning
To relieve the burden of labor-intensive labeling, deep unsupervised SOD methods have been proposed to exploit noisy labels generated by handcrafted saliency methods.
PointMatch: A Consistency Training Framework for Weakly Supervised Semantic Segmentation of 3D Point Clouds
Semantic segmentation of point cloud usually relies on dense annotation that is exhausting and costly, so it attracts wide attention to investigate solutions for the weakly supervised scheme with only sparse points annotated.
Representation Learning
Weakly supervised Semantic Segmentation
+1
Cross-level Contrastive Learning and Consistency Constraint for Semi-supervised Medical Image Segmentation
Semi-supervised learning (SSL), which aims at leveraging a few labeled images and a large number of unlabeled images for network training, is beneficial for relieving the burden of data annotation in medical image segmentation.
Aerial Images Meet Crowdsourced Trajectories: A New Approach to Robust Road Extraction
Land remote sensing analysis is a crucial research in earth science.
Explore before Moving: A Feasible Path Estimation and Memory Recalling Framework for Embodied Navigation
PEMR includes a "looking ahead" process, \textit{i. e.} a visual feature extractor module that estimates feasible paths for gathering 3D navigational information, which is mimicking the human sense of direction.
Road Network Guided Fine-Grained Urban Traffic Flow Inference
Furthermore, we take the road network feature as a query to capture the long-range spatial distribution of traffic flow with a transformer architecture.
Trash to Treasure: Harvesting OOD Data with Cross-Modal Matching for Open-Set Semi-Supervised Learning
Open-set semi-supervised learning (open-set SSL) investigates a challenging but practical scenario where out-of-distribution (OOD) samples are contained in the unlabeled data.
Towards Interpretable Deep Networks for Monocular Depth Estimation
Based on our observations, we quantify the interpretability of a deep MDE network by the depth selectivity of its hidden units.
Weakly-Supervised Spatio-Temporal Anomaly Detection in Surveillance Video
In this paper, we introduce a novel task, referred to as Weakly-Supervised Spatio-Temporal Anomaly Detection (WSSTAD) in surveillance video.
Colorectal Polyp Classification from White-light Colonoscopy Images via Domain Alignment
Thus, we propose a novel framework based on a teacher-student architecture for the accurate colorectal polyp classification (CPC) through directly using white-light (WL) colonoscopy images in the examination.
Online Metro Origin-Destination Prediction via Heterogeneous Information Aggregation
In this work, we proposed a novel neural network module termed Heterogeneous Information Aggregation Machine (HIAM), which fully exploits heterogeneous information of historical data (e. g., incomplete OD matrices, unfinished order vectors, and DO matrices) to jointly learn the evolutionary patterns of OD and DO ridership.
Bottom-Up Shift and Reasoning for Referring Image Segmentation
In this paper, we tackle the challenge by jointly performing compositional visual reasoning and accurate segmentation in a single stage via the proposed novel Bottom-Up Shift (BUS) and Bidirectional Attentive Refinement (BIAR) modules.
Cross-Modal Progressive Comprehension for Referring Segmentation
In this paper, we propose a Cross-Modal Progressive Comprehension (CMPC) scheme to effectively mimic human behaviors and implement it as a CMPC-I (Image) module and a CMPC-V (Video) module to improve referring image and video segmentation models.
Ranked #7 on
Referring Expression Segmentation
on J-HMDB
Collaborative Spatial-Temporal Modeling for Language-Queried Video Actor Segmentation
Though 3D convolutions are amenable to recognizing which actor is performing the queried actions, it also inevitably introduces misaligned spatial information from adjacent frames, which confuses features of the target frame and yields inaccurate segmentation.
Ranked #8 on
Referring Expression Segmentation
on J-HMDB
Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptation
Pseudo labeling expands the number of ``labeled" samples in each class in the target domain, and thus produces a more robust and powerful cluster core for each class to facilitate adversarial learning.
Deep Transformers for Fast Small Intestine Grounding in Capsule Endoscope Video
In this paper, we propose a deep model to ground shooting range of small intestine from a capsule endoscope video which has duration of tens of hours.
Scene-Intuitive Agent for Remote Embodied Visual Grounding
Intuitively, we comprehend the semantics of the instruction to form an overview of where a bathroom is and what a blue towel is in mind; then, we navigate to the target location by consistently matching the bathroom appearance in mind with the current scene.
LapsCore: Language-Guided Person Search via Color Reasoning
The key point of language-guided person search is to construct the cross-modal association between visual and textual input.
Adversarial Training using Contrastive Divergence
To protect the security of machine learning models against adversarial examples, adversarial training becomes the most popular and powerful strategy against various adversarial attacks by injecting adversarial examples into training data.
Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting
Extensive experiments conducted on the RGBT-CC benchmark demonstrate the effectiveness of our framework for RGBT crowd counting.
Human-centric Spatio-Temporal Video Grounding With Visual Transformers
HC-STVG is a video grounding task that requires both spatial (where) and temporal (when) localization.
A Hamiltonian Monte Carlo Method for Probabilistic Adversarial Attack and Learning
Although deep convolutional neural networks (CNNs) have demonstrated remarkable performance on multiple computer vision tasks, researches on adversarial learning have shown that deep models are vulnerable to adversarial examples, which are crafted by adding visually imperceptible perturbations to the input images.
Contralaterally Enhanced Networks for Thoracic Disease Detection
Aimed at improving the performance of existing detection methods, we propose a deep end-to-end module to exploit the contralateral context information for enhancing feature representations of disease proposals.
Linguistic Structure Guided Context Modeling for Referring Image Segmentation
Referring image segmentation aims to predict the foreground mask of the object referred by a natural language sentence.
Referring Image Segmentation via Cross-Modal Progressive Comprehension
In addition to the CMPC module, we further leverage a simple yet effective TGFE module to integrate the reasoned multimodal features from different levels with the guidance of textual information.
Ranked #14 on
Referring Expression Segmentation
on RefCOCO testB
Reinforcement Learning for Weakly Supervised Temporal Grounding of Natural Language in Untrimmed Videos
Temporal grounding of natural language in untrimmed videos is a fundamental yet challenging multimedia task facilitating cross-media visual content retrieval.
Online Alternate Generator against Adversarial Attacks
The field of computer vision has witnessed phenomenal progress in recent years partially due to the development of deep convolutional neural networks.
Collaborative Training between Region Proposal Localization and Classification for Domain Adaptive Object Detection
Domain adaptation for object detection tries to adapt the detector from labeled datasets to unlabeled ones for better performance.
Semantics-aware Adaptive Knowledge Distillation for Sensor-to-Vision Action Recognition
In this paper, we propose a novel framework, named Semantics-aware Adaptive Knowledge Distillation Networks (SAKDN), to enhance action recognition in vision-sensor modality (videos) by adaptively transferring and distilling the knowledge from multiple wearable sensors.
Graph-Structured Referring Expression Reasoning in The Wild
The linguistic structure of a referring expression provides a layout of reasoning over the visual contents, and it is often crucial to align and jointly understand the image and the referring expression.
Efficient Crowd Counting via Structured Knowledge Transfer
Crowd counting is an application-oriented task and its inference efficiency is crucial for real-world applications.
Peeking into occluded joints: A novel framework for crowd pose estimation
Although occlusion widely exists in nature and remains a fundamental challenge for pose estimation, existing heatmap-based approaches suffer serious degradation on occlusions.
Depthwise Non-local Module for Fast Salient Object Detection Using a Single Thread
The proposed algorithm for the first time achieves competitive accuracy and high inference efficiency simultaneously with a single CPU thread.
Tree-Structured Policy based Progressive Reinforcement Learning for Temporally Language Grounding in Video
Temporally language grounding in untrimmed videos is a newly-raised task in video understanding.
Physical-Virtual Collaboration Modeling for Intra-and Inter-Station Metro Ridership Prediction
To address this problem, we model a metro system as graphs with various topologies and propose a unified Physical-Virtual Collaboration Graph Network (PVCGN), which can effectively learn the complex ridership patterns from the tailor-designed graphs.
An Adversarial Perturbation Oriented Domain Adaptation Approach for Semantic Segmentation
In contrast to adversarial alignment, we propose to explicitly train a domain-invariant classifier by generating and defensing against pointwise feature space adversarial perturbations.
Self-Enhanced Convolutional Network for Facial Video Hallucination
It further recurrently exploits the reconstructed results and intermediate features of a sequence of preceding frames to improve the initial super-resolution of the current frame by modelling the coherence of structural facial features across frames.
Globally Guided Progressive Fusion Network for 3D Pancreas Segmentation
Recently 3D volumetric organ segmentation attracts much research interest in medical image analysis due to its significance in computer aided diagnosis.
Knowledge Graph Transfer Network for Few-Shot Recognition
In this work, we represent the semantic correlations in the form of structured knowledge graph and integrate this graph into deep neural networks to promote few-shot learning by a novel Knowledge Graph Transfer Network (KGTN).
Learning to Recognize the Unseen Visual Predicates
Visual relationship recognition models are limited in the ability to generalize from finite seen predicates to unseen ones.
Dynamic Graph Attention for Referring Expression Comprehension
In this paper, we explore the problem of referring expression comprehension from the perspective of language-driven visual reasoning, and propose a dynamic graph attention network to perform multi-step reasoning by modeling both the relationships among the objects in the image and the linguistic structure of the expression.
A Real-Time Cross-modality Correlation Filtering Method for Referring Expression Comprehension
RCCF reformulates the referring expression comprehension as a correlation filtering process.
Motion Guided Attention for Video Salient Object Detection
In this paper, we develop a multi-task motion guided video salient object detection network, which learns to accomplish two sub-tasks using two sub-networks, one sub-network for salient object detection in still images and the other for motion saliency detection in optical flow images.
Dynamic Spatial-Temporal Representation Learning for Traffic Flow Prediction
Specifically, the first ConvLSTM unit takes normal traffic flow features as input and generates a hidden state at each time-step, which is further fed into the connected convolutional layer for spatial attention map inference.
Fashion Retrieval via Graph Reasoning Networks on a Similarity Pyramid
To address this issue, we propose a novel Graph Reasoning Network (GRNet) on a Similarity Pyramid, which learns similarities between a query and a gallery cloth by using both global and local representations in multiple scales.
Ranked #4 on
Image Retrieval
on DeepFashion - Consumer-to-shop
(Rank-1 metric)
Crowd Counting with Deep Structured Scale Integration Network
Automatic estimation of the number of people in unconstrained crowded scenes is a challenging task and one major difficulty stems from the huge scale variation of people.
Semi-Supervised Video Salient Object Detection Using Pseudo-Labels
Specifically, we present an effective video saliency detector that consists of a spatial refinement network and a spatiotemporal module.
Ranked #1 on
Video Salient Object Detection
on VOS-T
(using extra training data)
Semi-supervised Skin Detection by Network with Mutual Guidance
In this paper we present a new data-driven method for robust skin detection from a single human portrait image.
Multivariate-Information Adversarial Ensemble for Scalable Joint Distribution Matching
A broad range of cross-$m$-domain generation researches boil down to matching a joint distribution by deep generative models (DGMs).
Relationship-Embedded Representation Learning for Grounding Referring Expressions
Unfortunately, existing work on grounding referring expressions fails to accurately extract multi-order relationships from the referring expression and associate them with the objects and their related contexts in the image.
Contextualized Spatial-Temporal Network for Taxi Origin-Destination Demand Prediction
Finally, a GCC module is applied to model the correlation between all regions by computing a global correlation feature as a weighted sum of all regional features, with the weights being calculated as the similarity between the corresponding region pairs.
ROSA: Robust Salient Object Detection against Adversarial Attacks
To our knowledge, this paper is the first one that mounts successful adversarial attacks on salient object detection models and verifies that adversarial samples are effective on a wide range of existing methods.
Face Hallucination by Attentive Sequence Optimization with Reinforcement Learning
Face hallucination is a domain-specific super-resolution problem that aims to generate a high-resolution (HR) face image from a low-resolution~(LR) input.
Semantic Relationships Guided Representation Learning for Facial Action Unit Recognition
Specifically, by analyzing the symbiosis and mutual exclusion of AUs in various facial expressions, we organize the facial AUs in the form of structured knowledge-graph and integrate a Gated Graph Neural Network (GGNN) in a multi-scale CNN framework to propagate node information through the graph for generating enhanced AU representation.
Harvesting Visual Objects from Internet Images via Deep Learning Based Objectness Assessment
As a concrete example, a database of over 1. 2 million visual objects has been built using the proposed method, and has been successfully used in various data-driven image applications.
Deep RBFNet: Point Cloud Feature Learning using Radial Basis Functions
Three-dimensional object recognition has recently achieved great progress thanks to the development of effective point cloud-based learning frameworks, such as PointNet and its extensions.
Facial Landmark Machines: A Backbone-Branches Architecture with Progressive Representation Learning
In this paper, we propose a novel cascaded backbone-branches fully convolutional neural network~(BB-FCN) for rapidly and accurately localizing facial landmarks in unconstrained and cluttered settings.
FRAME Revisited: An Interpretation View Based on Particle Evolution
FRAME (Filters, Random fields, And Maximum Entropy) is an energy-based descriptive model that synthesizes visual realism by capturing mutual patterns from structural input signals.
Larger Norm More Transferable: An Adaptive Feature Norm Approach for Unsupervised Domain Adaptation
Domain adaptation enables the learner to safely generalize into novel environments by mitigating domain shifts across distributions.
Ranked #7 on
Domain Adaptation
on ImageCLEF-DA
Cross-Modal Attentional Context Learning for RGB-D Object Detection
In this paper, we address this problem by developing a Cross-Modal Attentional Context (CMAC) learning framework, which enables the full exploitation of the context information from both RGB and depth data.
Learning Deep Representations for Semantic Image Parsing: a Comprehensive Overview
Semantic image parsing, which refers to the process of decomposing images into semantic regions and constructing the structure representation of the input, has recently aroused widespread interest in the field of computer vision.
Attentive Crowd Flow Machines
Traffic flow prediction is crucial for urban traffic management and public safety.
Non-locally Enhanced Encoder-Decoder Network for Single Image De-raining
Single image rain streaks removal has recently witnessed substantial progress due to the development of deep convolutional neural networks.
Crowd Counting using Deep Recurrent Spatial-Aware Network
Crowd counting from unconstrained scene images is a crucial task in many real-world applications like urban surveillance and management, but it is greatly challenged by the camera's perspective that causes huge appearance variations in people's scales and rotations.
Interpretable Video Captioning via Trajectory Structured Localization
Automatically describing open-domain videos with natural language are attracting increasing interest in the field of artificial intelligence.
Flow Guided Recurrent Neural Encoder for Video Salient Object Detection
Image saliency detection has recently witnessed significant progress due to deep convolutional neural networks.
Ranked #2 on
Video Salient Object Detection
on DAVSOD-Difficult20
(using extra training data)
Visual Question Reasoning on General Dependency Tree
This network comprises of two collaborative modules: i) an adversarial attention module to exploit the local visual evidence for each word parsed from the question; ii) a residual composition module to compose the previously mined evidence.
Contrast-Oriented Deep Neural Networks for Salient Object Detection
In this paper, we develop hybrid contrast-oriented deep neural networks to overcome the aforementioned limitations.
Weakly Supervised Salient Object Detection Using Image Labels
Our algorithm is based on alternately exploiting a graphical model and training a fully convolutional network for model updating.
Context-Aware Semantic Inpainting
Our proposed GAN-based framework consists of a fully convolutional design for the generator which helps to better preserve spatial structures and a joint loss function with a revised perceptual loss to capture high-level semantics in the context.
Recurrent Attentional Reinforcement Learning for Multi-label Image Recognition
Recognizing multiple labels of images is a fundamental but challenging task in computer vision, and remarkable progress has been attained by localizing semantic-aware image regions and predicting their labels with deep convolutional neural networks.
Multi-label Image Recognition by Recurrently Discovering Attentional Regions
This paper proposes a novel deep architecture to address multi-label image recognition, a fundamental and practical task towards general visual understanding.
Attention-Aware Face Hallucination via Deep Reinforcement Learning
Face hallucination is a domain-specific super-resolution problem with the goal to generate high-resolution (HR) faces from low-resolution (LR) input images.
Instance-Level Salient Object Segmentation
Image saliency detection has recently witnessed rapid progress due to deep convolutional neural networks.
Ranked #15 on
RGB Salient Object Detection
on DUTS-TE
(max F-measure metric)
Visual Saliency Detection Based on Multiscale Deep CNN Features
The penultimate layer of our neural network has been confirmed to be a discriminative high-level feature vector for saliency detection, which we call deep contrast feature.
Deep Contrast Learning for Salient Object Detection
Our deep network consists of two complementary components, a pixel-level fully convolutional stream and a segment-wise spatial pooling stream.
Ranked #19 on
RGB Salient Object Detection
on DUTS-TE
(max F-measure metric)
Visual Saliency Based on Multiscale Deep Features
Visual saliency is a fundamental problem in both cognitive and computational sciences, including computer vision.
