Search Results for author:
Found 107 papers, 36 papers with code
Arena: A Patch-of-Interest ViT Inference Acceleration System for Edge-Assisted Video Analytics
In this paper, we find visual foundation models like Vision Transformer (ViT) also have a dedicated acceleration mechanism for video analytics.
Improving Continuous Sign Language Recognition with Adapted Image Models
Besides, fully fine-tuning the model easily forgets the generic essential knowledge acquired in the pretraining stage and overfits the downstream data.
LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks
To achieve high accuracy on both clean and adversarial data, we propose building a spatial-temporal continuous representation using the semantic text guidance of the object of interest.
Dynamic Spatial-Temporal Aggregation for Skeleton-Aware Sign Language Recognition
Current methods utilize spatial graph modules and temporal modules to capture spatial and temporal features, respectively.
Hunting Attributes: Context Prototype-Aware Learning for Weakly Supervised Semantic Segmentation
Inspired by prototype learning theory, we propose leveraging prototype awareness to capture diverse and fine-grained feature attributes of instances.
Edge Information Hub: Orchestrating Satellites, UAVs, MEC, Sensing and Communications for 6G Closed-Loop Controls
Specifically, the linear quadratic regulator (LQR) control cost is used to measure the closed-loop utility, and a sum LQR cost minimization problem is formulated to jointly optimize the splitting of sensor data and allocation of communication and computing resources.
From Synthetic to Real: Unveiling the Power of Synthetic Data for Video Person Re-ID
In this paper, we study a new problem of cross-domain video based person re-identification (Re-ID).
Unveiling the Power of Self-supervision for Multi-view Multi-human Association and Tracking
Multi-view multi-human association and tracking (MvMHAT), is a new but important problem for multi-person scene video surveillance, aiming to track a group of people over time in each view, as well as to identify the same person across different views at the same time, which is different from previous MOT and multi-camera MOT tasks only considering the over-time human tracking.
Elastic Multi-Gradient Descent for Parallel Continual Learning
The goal of Continual Learning (CL) is to continuously learn from new data streams and accomplish the corresponding tasks.
COMMA: Co-Articulated Multi-Modal Learning
First, the prompts of the vision and language branches in these methods are usually separated or uni-directionally correlated.
LLM4VG: Large Language Models Evaluation for Video Grounding
Recently, researchers have attempted to investigate the capability of LLMs in handling videos and proposed several video LLM models.
Generate E-commerce Product Background by Integrating Category Commonality and Personalized Style
Furthermore, for products with specific and fine-grained requirements in layout, elements, etc, a Personality-Wise Generator is devised to learn such personalized style directly from a reference image to resolve textual ambiguities, and is trained in a self-supervised manner for more efficient training data usage.
Planning and Rendering: Towards End-to-End Product Poster Generation
At the planning stage, we propose a PlanNet to generate the layout of the product and other visual components considering both the appearance features of the product and semantic features of the text, which improves the diversity and rationality of the layouts.
Long-Tailed Learning as Multi-Objective Optimization
Real-world data is extremely imbalanced and presents a long-tailed distribution, resulting in models that are biased towards classes with sufficient samples and perform poorly on rare classes.
Towards Novel Class Discovery: A Study in Novel Skin Lesions Clustering
We conducted extensive experiments on the dermatology dataset ISIC 2019, and the experimental results show that our approach can effectively leverage knowledge from known categories to discover new semantic categories.
Adaptive Fusion of Radiomics and Deep Features for Lung Adenocarcinoma Subtype Recognition
The most common type of lung cancer, lung adenocarcinoma (LUAD), has been increasingly detected since the advent of low-dose computed tomography screening technology.
Improving the Transferability of Adversarial Examples with Arbitrary Style Transfer
Deep neural networks are vulnerable to adversarial examples crafted by applying human-imperceptible perturbations on clean inputs.
AdaBrowse: Adaptive Video Browser for Efficient Continuous Sign Language Recognition
Then these features are fed into a policy network to intelligently select a subsequence to process.
Ranked #6 on
Sign Language Recognition
on CSL-Daily
Control-Oriented Deep Space Communications For Unmanned Space Exploration
In this paper, we propose a communication optimization scheme for a specific cooperation system named the "mother-daughter system".
Mutual Query Network for Multi-Modal Product Image Segmentation
Product image segmentation is vital in e-commerce.
Decarbonization patterns of residential building operations in China and India
(2) Building electrification played a significant role in decarbonizing space cooling (-87. 7 in China and -130. 2 kilograms of carbon dioxide (kgCO2) per household in India) and appliances (-169. 7 in China and -43. 4 kgCO2 per household in India).
Relation-Aware Diffusion Model for Controllable Poster Layout Generation
To advance research in this field, we have constructed a poster layout dataset named CGL-Dataset V2.
Learning Restoration is Not Enough: Transfering Identical Mapping for Single-Image Shadow Removal
State-of-the-art shadow removal methods train deep neural networks on collected shadow & shadow-free image pairs, which are desired to complete two distinct tasks via shared weights, i. e., data restoration for shadow regions and identical mapping for non-shadow regions.
Generation of 3D Molecules in Pockets via Language Model
Generative models for molecules based on sequential line notation (e. g.
ESimCSE Unsupervised Contrastive Learning Jointly with UDA Semi-Supervised Learning for Large Label System Text Classification Mode
The challenges faced by text classification with large tag systems in natural language processing tasks include multiple tag systems, uneven data distribution, and high noise.
Towards Open-Scenario Semi-supervised Medical Image Classification
Therefore, in this paper, we proposed a unified framework to leverage these unseen unlabeled data for open-scenario semi-supervised medical image classification.
MMFormer: Multimodal Transformer Using Multiscale Self-Attention for Remote Sensing Image Classification
To benefit the complementary information between heterogeneous data, we introduce a new Multimodal Transformer (MMFormer) for Remote Sensing (RS) image classification using Hyperspectral Image (HSI) accompanied by another source of data such as Light Detection and Ranging (LiDAR).
Continuous Sign Language Recognition with Correlation Network
Visualizations demonstrate the effects of CorrNet on emphasizing human body trajectories across adjacent frames.
Leveraging Inpainting for Single-Image Shadow Removal
In this work, we find that pretraining shadow removal networks on the image inpainting dataset can reduce the shadow remnants significantly: a naive encoder-decoder network gets competitive restoration quality w. r. t.
Structure-Informed Shadow Removal Networks
Hence, in this paper, we propose to remove shadows at the image structure level.
Measuring Asymmetric Gradient Discrepancy in Parallel Continual Learning
In Parallel Continual Learning (PCL), the parallel multiple tasks start and end training unpredictably, thus suffering from training conflict and catastrophic forgetting issues.
From a Bird's Eye View to See: Joint Camera and Subject Registration without the Camera Calibration
We tackle a new problem of multi-view camera and subject registration in the bird's eye view (BEV) without pre-given camera calibration.
CBNet: A Plug-and-Play Network for Segmentation-Based Scene Text Detection
Recently, segmentation-based methods are quite popular in scene text detection, which mainly contain two steps: text kernel segmentation and expansion.
Self-Emphasizing Network for Continuous Sign Language Recognition
To relieve this problem, we propose a self-emphasizing network (SEN) to emphasize informative spatial regions in a self-motivated way, with few extra computations and without additional expensive supervision.
Ranked #7 on
Sign Language Recognition
on CSL-Daily
Multi-Label Continual Learning using Augmented Graph Convolutional Network
In contrast, the inter-task relationships leverage hard and soft labels from data and a constructed expert network.
From Indoor To Outdoor: Unsupervised Domain Adaptive Gait Recognition
In this paper, we study a new problem of unsupervised domain adaptive gait recognition (UDA-GR), that learns a gait identifier with supervised labels from the indoor scenes (source domain), and is applied to the outdoor wild scenes (target domain).
A Benchmark of Video-Based Clothes-Changing Person Re-Identification
In this paper, we focus on the relatively new yet practical problem of clothes-changing video-based person re-identification (CCVReID), which is less studied.
Truthful Transaction Protocol for E-Commerce Networks Based on Double Auction
This screening algorithm is customer-oriented and offers personalized commodities by preventing unqualified sellers from participating in the transaction.
3D Matting: A Benchmark Study on Soft Segmentation Method for Pulmonary Nodules Applied in Computed Tomography
In this work, we introduce the image matting into the 3D scenes and use the alpha matte, i. e., a soft mask, to describe lesions in a 3D medical image.
Exploring Example Influence in Continual Learning
Continual Learning (CL) sequentially learns new tasks like human beings, with the goal to achieve better Stability (S, remembering past tasks) and Plasticity (P, adapting to new tasks).
View-Invariant Skeleton-based Action Recognition via Global-Local Contrastive Learning
Skeleton-based human action recognition has been drawing more interest recently due to its low sensitivity to appearance changes and the accessibility of more skeleton data.
3D Matting: A Soft Segmentation Method Applied in Computed Tomography
It can be caused by many factors, such as the imaging properties, pathological anatomy, and the weak representation of the binary masks, which brings challenges to accurate 3D segmentation.
Control-Oriented Power Allocation for Integrated Satellite-UAV Networks
This letter presents a sensing-communication-computing-control (SC3) integrated satellite unmanned aerial vehicle (UAV) network, where the UAV is equipped with on-board sensors, mobile edge computing (MEC) servers, base stations and satellite communication module.
End-to-end Clinical Event Extraction from Chinese Electronic Health Record
Event extraction is an important work of medical text processing.
Spatial Temporal Graph Attention Network for Skeleton-Based Action Recognition
In such conditions, short-term dependencies are few formally considered, which are critical for classifying similar actions.
Ranked #1 on
Skeleton Based Action Recognition
on Kinetics-400
Integrating Satellites and Mobile Edge Computing for 6G Wide-Area Edge Intelligence: Minimal Structures and Systematic Thinking
The sixth-generation (6G) network will shift its focus to supporting everything including various machine-type devices (MTDs) in an everyone-centric manner.
Temporal Lift Pooling for Continuous Sign Language Recognition
In this paper, we derive temporal lift pooling (TLP) from the Lifting Scheme in signal processing to intelligently downsample features of different temporal hierarchies.
Unsupervised Domain Adaptive Fundus Image Segmentation with Category-level Regularization
Existing unsupervised domain adaptation methods based on adversarial learning have achieved good performance in several medical imaging tasks.
Joint Communication and Sensing: Models and Potential of Using MIMO
In this survey, we discuss joint communication and sensing (JCAS) in the context of MIMO.
Single Object Tracking Research: A Survey
Visual object tracking is an important task in computer vision, which has many real-world applications, e. g., video surveillance, visual navigation.
Illumination-Invariant Active Camera Relocalization for Fine-Grained Change Detection in the Wild
Active camera relocalization (ACR) is a new problem in computer vision that significantly reduces the false alarm caused by image distortions due to camera pose misalignment in fine-grained change detection (FGCD).
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.
AGCN: Augmented Graph Convolutional Network for Lifelong Multi-label Image Recognition
The key challenges of LML image recognition are the construction of label relationships on Partial Labels of training data and the Catastrophic Forgetting on old classes, resulting in poor generalization.
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.
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.
Combining the Silhouette and Skeleton Data for Gait Recognition
Gait recognition, a long-distance biometric technology, has aroused intense interest recently.
Reinforcement Learning-Empowered Mobile Edge Computing for 6G Edge Intelligence
Mobile edge computing (MEC) is considered a novel paradigm for computation-intensive and delay-sensitive tasks in fifth generation (5G) networks and beyond.
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.
Regularized Modal Regression on Markov-dependent Observations: A Theoretical Assessment
Our results show that the Markov dependence impacts on the generalization error in the way that sample size would be discounted by a multiplicative factor depending on the spectral gap of underlying Markov chain.
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.
Rethinking Rehearsal in Lifelong Learning: Does An Example Contribute the Plasticity or Stability?
Traditionally, the primary goal of LL is to achieve the trade-off between the Stability (remembering past tasks) and Plasticity (adapting to new tasks).
VIL-100: A New Dataset and A Baseline Model for Video Instance Lane Detection
Lane detection plays a key role in autonomous driving.
Adversarial Relighting Against Face Recognition
To this end, we first propose the physical modelbased adversarial relighting attack (ARA) denoted as albedoquotient-based adversarial relighting attack (AQ-ARA).
From Synthetic to Real: Image Dehazing Collaborating with Unlabeled Real Data
Our DID-Net predicts the three component maps by progressively integrating features across scales, and refines each map by passing an independent refinement network.
Ranked #6 on
Image Dehazing
on Haze4k
Unsupervised Domain Adaptation for Retinal Vessel Segmentation with Adversarial Learning and Transfer Normalization
In this work, we explore unsupervised domain adaptation in retinal vessel segmentation by using entropy-based adversarial learning and transfer normalization layer to train a segmentation network, which generalizes well across domains and requires no annotation of the target domain.
CarveNet: Carving Point-Block for Complex 3D Shape Completion
3D point cloud completion is very challenging because it heavily relies on the accurate understanding of the complex 3D shapes (e. g., high-curvature, concave/convex, and hollowed-out 3D shapes) and the unknown & diverse patterns of the partially available point clouds.
Semantic-Aware Video Text Detection
To overcome the lack of character-level annotations, we propose a novel weakly-supervised character center detection module, which only uses word-level annotated real images to generate character-level labels.
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.
AdvHaze: Adversarial Haze Attack
We also visualize the correlation matrices, which inspire us to jointly apply different perturbations to improve the success rate of the attack.
MEC-Empowered Non-Terrestrial Network for 6G Wide-Area Time-Sensitive Internet of Things
Nevertheless, communication and MEC systems are coupled with each other under the influence of complex propagation environment in the MEC-empowered NTN, which makes it hard to orchestrate the resources.
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.
Improving prediction of the terrestrial water storage anomalies during the GRACE and GRACE-FO gap with Bayesian convolutional neural networks
The Gravity Recovery and Climate Experiment (GRACE) satellite and its successor GRACE Follow-On (GRACE-FO) provide valuable and accurate observations of terrestrial water storage anomalies (TWSAs) at a global scale.
Sparta: Spatially Attentive and Adversarially Robust Activations
Moreover, comprehensive evaluations have demonstrated two important properties of our method: First, superior transferability across DNNs.
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.
Weakly-Supervised Arbitrary-Shaped Text Detection with Expectation-Maximization Algorithm
We propose an Expectation-Maximization (EM) based weakly-supervised learning framework to train an accurate arbitrary-shaped text detector using only a small amount of polygon-level annotated data combined with a large amount of weakly annotated data.
EfficientDeRain: Learning Pixel-wise Dilation Filtering for High-Efficiency Single-Image Deraining
To fill this gap, in this paper, we regard the single-image deraining as a general image-enhancing problem and originally propose a model-free deraining method, i. e., EfficientDeRain, which is able to process a rainy image within 10~ms (i. e., around 6~ms on average), over 80 times faster than the state-of-the-art method (i. e., RCDNet), while achieving similar de-rain effects.
Adversarial Rain Attack and Defensive Deraining for DNN Perception
To defend the DNNs from the negative rain effect, we also present a defensive deraining strategy, for which we design an adversarial rain augmentation that uses mixed adversarial rain layers to enhance deraining models for downstream DNN perception.
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.
Delay Characterization of Mobile Edge Computing for 6G Time-Sensitive Services
Only a few research efforts have been devoted to other random delay characteristics, such as the delay bound violation probability and the probability distribution of the delay, by decoupling the transmission and computation processes of MEC.
Cell-Free Satellite-UAV Networks for 6G Wide-Area Internet of Things
In fifth generation (5G) and beyond Internet of Things (IoT), it becomes increasingly important to serve a massive number of IoT devices outside the coverage of terrestrial cellular networks.
Pasadena: Perceptually Aware and Stealthy Adversarial Denoise Attack
To this end, we initiate the very first attempt to study this problem from the perspective of adversarial attack and propose the adversarial denoise attack.
DeepRhythm: Exposing DeepFakes with Attentional Visual Heartbeat Rhythms
As the GAN-based face image and video generation techniques, widely known as DeepFakes, have become more and more matured and realistic, there comes a pressing and urgent demand for effective DeepFakes detectors.
Enabling 5G on the Ocean: A Hybrid Satellite-UAV-Terrestrial Network Solution
In this paper, we study the integration of UAVs with existing MCNs, and investigate the potential gains of hybrid satellite-UAV-terrestrial networks for maritime coverage.
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.
Active Lighting Recurrence by Parallel Lighting Analogy for Fine-Grained Change Detection
Besides, we also theoretically prove the invariance of our ALR approach to the ambiguity of normal and lighting decomposition.
Trend and forecasting of the COVID-19 outbreak in China
By using the public data from Jan. 20 to Feb. 11, 2020, we perform data-driven analysis and forecasting on the COVID-19 epidemic in mainland China, especially Hubei province.
Watch out! Motion is Blurring the Vision of Your Deep Neural Networks
Besides, the attack is further enhanced by adaptively tuning the translations of object and background.
SPARK: Spatial-aware Online Incremental Attack Against Visual Tracking
We identify that online object tracking poses two new challenges: 1) it is difficult to generate imperceptible perturbations that can transfer across frames, and 2) real-time trackers require the attack to satisfy a certain level of efficiency.
TextDragon: An End-to-End Framework for Arbitrary Shaped Text Spotting
Motivated from the name of TextSnake, which is only a detection model, we call the proposed text spotting framework TextDragon.
Ranked #11 on
Text Spotting
on SCUT-CTW1500
Dynamically Pruned Message Passing Networks for Large-Scale Knowledge Graph Reasoning
We propose Dynamically Pruned Message Passing Networks (DPMPN) for large-scale knowledge graph reasoning.
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.
OD-GCN: Object Detection Boosted by Knowledge GCN
Classical CNN based object detection methods only extract the objects' image features, but do not consider the high-level relationship among objects in context.
Learning Guided Convolutional Network for Depth Completion
It is thus necessary to complete the sparse LiDAR data, where a synchronized guidance RGB image is often used to facilitate this completion.
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.
Neural Consciousness Flow
Instead, inspired by the consciousness prior proposed by Yoshua Bengio, we explore reasoning with the notion of attentive awareness from a cognitive perspective, and formulate it in the form of attentive message passing on graphs, called neural consciousness flow (NeuCFlow).
Turbo Learning Framework for Human-Object Interactions Recognition and Human Pose Estimation
Human-object interactions (HOI) recognition and pose estimation are two closely related tasks.
Modeling Attention Flow on Graphs
Real-world scenarios demand reasoning about process, more than final outcome prediction, to discover latent causal chains and better understand complex systems.
Backprop-Q: Generalized Backpropagation for Stochastic Computation Graphs
Then, the SCG can be trained based on these surrogate costs using standard backpropagation.
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.
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
6D Dynamic Camera Relocalization From Single Reference Image
Based on inexpensive platform with unreliable absolute repositioning accuracy (ARA), we propose a hand-eye calibration free strategy to actively relocate camera into the same 6D pose that produces the input reference image, by sequentially correcting 3D relative rotation and translation.
Fine-Grained Change Detection of Misaligned Scenes With Varied Illuminations
To guarantee detection sensitivity and accuracy of minute changes, in an observation, we capture a group of images under multiple illuminations, which need only to be roughly aligned to the last time lighting conditions.
ESSP: An Efficient Approach to Minimizing Dense and Nonsubmodular Energy Functions
From our study, we make some reasonable recommendations of combining existing methods that perform the best in different situations for this challenging problem.
Maximum Cohesive Grid of Superpixels for Fast Object Localization
For this purpose, we aim at constructing maximum cohesive SP-grid, which is composed of real nodes, i. e. SPs, and dummy nodes that are meaningless in the image with only position-taking function in the grid.
