Search Results for author:
Found 145 papers, 43 papers with code
AAAR-1.0: Assessing AI's Potential to Assist Research
Numerous studies have assessed the proficiency of AI systems, particularly large language models (LLMs), in facilitating everyday tasks such as email writing, question answering, and creative content generation.
Securing Federated Learning Against Novel and Classic Backdoor Threats During Foundation Model Integration
Federated learning (FL) enables decentralized model training while preserving privacy.
CamI2V: Camera-Controlled Image-to-Video Diffusion Model
We innovatively associate the quality of a condition with its ability to reduce uncertainty and interpret noisy cross-frame features as a form of noisy condition.
Ego3DT: Tracking Every 3D Object in Ego-centric Videos
Addressing this issue, this paper introduces a novel zero-shot approach for the 3D reconstruction and tracking of all objects from the ego-centric video.
Smart Audit System Empowered by LLM
Manufacturing quality audits are pivotal for ensuring high product standards in mass production environments.
Associate Everything Detected: Facilitating Tracking-by-Detection to the Unknown
Different from existing tracking-by-detection MOT methods, AED gets rid of prior knowledge (e. g. motion cues) and relies solely on highly robust feature learning to handle complex trajectories in OV-MOT tasks while keeping excellent performance in CV-MOT tasks.
Ranked #1 on
Multi-Object Tracking
on TAO
(using extra training data)
Hybrid Mask Generation for Infrared Small Target Detection with Single-Point Supervision
Single-frame infrared small target (SIRST) detection poses a significant challenge due to the requirement to discern minute targets amidst complex infrared background clutter.
CustomCrafter: Customized Video Generation with Preserving Motion and Concept Composition Abilities
However, since it is only trained on static images, the fine-tuning process of subject learning disrupts abilities of video diffusion models (VDMs) to combine concepts and generate motions.
Envisioning Class Entity Reasoning by Large Language Models for Few-shot Learning
Few-shot learning (FSL) aims to recognize new concepts using a limited number of visual samples.
TXL-PBC: a freely accessible labeled peripheral blood cell dataset
Moreover, we used the YOLOv8n model to train these three datasets, the performance of the TXL-PBC dataset surpass the original two datasets.
CLASH: Complementary Learning with Neural Architecture Search for Gait Recognition
To enhance the sensitivity to the walking pattern while maintaining the robustness of recognition, we present a Complementary Learning with neural Architecture Search (CLASH) framework, consisting of walking pattern sensitive gait descriptor named dense spatial-temporal field (DSTF) and neural architecture search based complementary learning (NCL).
GVDIFF: Grounded Text-to-Video Generation with Diffusion Models
In text-to-video (T2V) generation, significant attention has been directed toward its development, yet unifying discrete and continuous grounding conditions in T2V generation remains under-explored.
Solving Token Gradient Conflict in Mixture-of-Experts for Large Vision-Language Model
The Mixture-of-Experts (MoE) has gained increasing attention in studying Large Vision-Language Models (LVLMs).
ScanFormer: Referring Expression Comprehension by Iteratively Scanning
This inspires us to explore a question: can we eliminate linguistic-irrelevant redundant visual regions to improve the efficiency of the model?
SemanticMIM: Marring Masked Image Modeling with Semantics Compression for General Visual Representation
This paper represents a neat yet effective framework, named SemanticMIM, to integrate the advantages of masked image modeling (MIM) and contrastive learning (CL) for general visual representation.
BEVSpread: Spread Voxel Pooling for Bird's-Eye-View Representation in Vision-based Roadside 3D Object Detection
Vision-based roadside 3D object detection has attracted rising attention in autonomous driving domain, since it encompasses inherent advantages in reducing blind spots and expanding perception range.
Chain-of-Scrutiny: Detecting Backdoor Attacks for Large Language Models
Backdoor attacks present significant threats to Large Language Models (LLMs), particularly with the rise of third-party services that offer API integration and prompt engineering.
CityCraft: A Real Crafter for 3D City Generation
The rendered scenes lack variety, resembling the training images, resulting in monotonous styles.
A Survey of Multimodal Large Language Model from A Data-centric Perspective
Multimodal large language models (MLLMs) enhance the capabilities of standard large language models by integrating and processing data from multiple modalities, including text, vision, audio, video, and 3D environments.
CM-UNet: Hybrid CNN-Mamba UNet for Remote Sensing Image Semantic Segmentation
In this paper, we propose CM-UNet, comprising a CNN-based encoder for extracting local image features and a Mamba-based decoder for aggregating and integrating global information, facilitating efficient semantic segmentation of remote sensing images.
MovieChat+: Question-aware Sparse Memory for Long Video Question Answering
Recently, integrating video foundation models and large language models to build a video understanding system can overcome the limitations of specific pre-defined vision tasks.
Ranked #4 on
Question Answering
on NExT-QA (Open-ended VideoQA)
Joint Physical-Digital Facial Attack Detection Via Simulating Spoofing Clues
SPSC and SDSC augment live samples into simulated attack samples by simulating spoofing clues of physical and digital attacks, respectively, which significantly improve the capability of the model to detect "unseen" attack types.
SphereDiffusion: Spherical Geometry-Aware Distortion Resilient Diffusion Model
Controllable spherical panoramic image generation holds substantial applicative potential across a variety of domains. However, it remains a challenging task due to the inherent spherical distortion and geometry characteristics, resulting in low-quality content generation. In this paper, we introduce a novel framework of SphereDiffusion to address these unique challenges, for better generating high-quality and precisely controllable spherical panoramic images. For the spherical distortion characteristic, we embed the semantics of the distorted object with text encoding, then explicitly construct the relationship with text-object correspondence to better use the pre-trained knowledge of the planar images. Meanwhile, we employ a deformable technique to mitigate the semantic deviation in latent space caused by spherical distortion. For the spherical geometry characteristic, in virtue of spherical rotation invariance, we improve the data diversity and optimization objectives in the training process, enabling the model to better learn the spherical geometry characteristic. Furthermore, we enhance the denoising process of the diffusion model, enabling it to effectively use the learned geometric characteristic to ensure the boundary continuity of the generated images. With these specific techniques, experiments on Structured3D dataset show that SphereDiffusion significantly improves the quality of controllable spherical image generation and relatively reduces around 35% FID on average.
Personalized Behavior-Aware Transformer for Multi-Behavior Sequential Recommendation
To tackle these challenges, we propose a Personalized Behavior-Aware Transformer framework (PBAT) for MBSR problem, which models personalized patterns and multifaceted sequential collaborations in a novel way to boost recommendation performance.
Universal Post-Training Reverse-Engineering Defense Against Backdoors in Deep Neural Networks
A variety of defenses have been proposed against backdoors attacks on deep neural network (DNN) classifiers.
Position Paper: Assessing Robustness, Privacy, and Fairness in Federated Learning Integrated with Foundation Models
Federated Learning (FL), while a breakthrough in decentralized machine learning, contends with significant challenges such as limited data availability and the variability of computational resources, which can stifle the performance and scalability of the models.
Vulnerabilities of Foundation Model Integrated Federated Learning Under Adversarial Threats
Federated Learning (FL) addresses critical issues in machine learning related to data privacy and security, yet suffering from data insufficiency and imbalance under certain circumstances.
Virtual Immunohistochemistry Staining for Histological Images Assisted by Weakly-supervised Learning
Recently virtual staining technology has greatly promoted the advancement of histopathology.
TextFusion: Unveiling the Power of Textual Semantics for Controllable Image Fusion
Advanced image fusion methods are devoted to generating the fusion results by aggregating the complementary information conveyed by the source images.
Bridging Cross-task Protocol Inconsistency for Distillation in Dense Object Detection
Thus, the optimum of the distillation loss does not necessarily lead to the optimal student classification scores for dense object detectors.
Temporal-Distributed Backdoor Attack Against Video Based Action Recognition
Although there are extensive studies on backdoor attacks against image data, the susceptibility of video-based systems under backdoor attacks remains largely unexplored.
Backdoor Mitigation by Correcting the Distribution of Neural Activations
Backdoor (Trojan) attacks are an important type of adversarial exploit against deep neural networks (DNNs), wherein a test instance is (mis)classified to the attacker's target class whenever the attacker's backdoor trigger is present.
HeightFormer: Explicit Height Modeling without Extra Data for Camera-only 3D Object Detection in Bird's Eye View
In this work, we propose to explicitly model heights in the BEV space, which needs no extra data like LiDAR and can fit arbitrary camera rigs and types compared to modeling depths.
SGAT4PASS: Spherical Geometry-Aware Transformer for PAnoramic Semantic Segmentation
Experimental results on Stanford2D3D Panoramic datasets show that SGAT4PASS significantly improves performance and robustness, with approximately a 2% increase in mIoU, and when small 3D disturbances occur in the data, the stability of our performance is improved by an order of magnitude.
Ranked #4 on
Semantic Segmentation
on Stanford2D3D Panoramic
GaitGCI: Generative Counterfactual Intervention for Gait Recognition
Gait is one of the most promising biometrics that aims to identify pedestrians from their walking patterns.
MetaGait: Learning to Learn an Omni Sample Adaptive Representation for Gait Recognition
Towards this goal, MetaGait injects meta-knowledge, which could guide the model to perceive sample-specific properties, into the calibration network of the attention mechanism to improve the adaptiveness from the omni-scale, omni-dimension, and omni-process perspectives.
DenseDINO: Boosting Dense Self-Supervised Learning with Token-Based Point-Level Consistency
In this paper, we propose a simple yet effective transformer framework for self-supervised learning called DenseDINO to learn dense visual representations.
GaitMPL: Gait Recognition with Memory-Augmented Progressive Learning
In this work, we propose to solve the hard sample issue with a Memory-augmented Progressive Learning network (GaitMPL), including Dynamic Reweighting Progressive Learning module (DRPL) and Global Structure-Aligned Memory bank (GSAM).
Language Adaptive Weight Generation for Multi-task Visual Grounding
The active perception can take expressions as priors to extract relevant visual features, which can effectively alleviate the mismatches.
Referring Expression Comprehension Using Language Adaptive Inference
Different from universal object detection, referring expression comprehension (REC) aims to locate specific objects referred to by natural language expressions.
A Deep RL Approach on Task Placement and Scaling of Edge Resources for Cellular Vehicle-to-Network Service Provisioning
Cellular-Vehicle-to-Everything (C-V2X) is currently at the forefront of the digital transformation of our society.
FusionBooster: A Unified Image Fusion Boosting Paradigm
We argue that there is a scope to improve the fusion performance with the help of the FusionBooster, a model specifically designed for the fusion task.
LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation
To overcome the difficult multimodal fusion of image and layout, we propose to construct a structural image patch with region information and transform the patched image into a special layout to fuse with the normal layout in a unified form.
Ranked #1 on
Layout-to-Image Generation
on Visual Genome 128x128
PUPS: Point Cloud Unified Panoptic Segmentation
Point cloud panoptic segmentation is a challenging task that seeks a holistic solution for both semantic and instance segmentation to predict groupings of coherent points.
RWSC-Fusion: Region-Wise Style-Controlled Fusion Network for the Prohibited X-Ray Security Image Synthesis
Automatic prohibited item detection in security inspection X-ray images is necessary for transportation. The abundance and diversity of the X-ray security images with prohibited item, termed as prohibited X-ray security images, are essential for training the detection model.
DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detection
In this study, we propose an improved model called DeSTSeg, which integrates a pre-trained teacher network, a denoising student encoder-decoder, and a segmentation network into one framework.
Ranked #49 on
Anomaly Detection
on MVTec AD
Adaptive Edge-to-Edge Interaction Learning for Point Cloud Analysis
To explore the role of the relation between edges, this paper proposes a novel Adaptive Edge-to-Edge Interaction Learning module, which aims to enhance the point-to-point relation through modelling the edge-to-edge interaction in the local region adaptively.
UniFusion: Unified Multi-view Fusion Transformer for Spatial-Temporal Representation in Bird's-Eye-View
Bird's eye view (BEV) representation is a new perception formulation for autonomous driving, which is based on spatial fusion.
Dynamic Low-Resolution Distillation for Cost-Efficient End-to-End Text Spotting
In this paper, to address this problem, we propose a novel cost-efficient Dynamic Low-resolution Distillation (DLD) text spotting framework, which aims to infer images in different small but recognizable resolutions and achieve a better balance between accuracy and efficiency.
Knowledge Distillation
Optical Character Recognition (OCR)
+1
Entropy-driven Sampling and Training Scheme for Conditional Diffusion Generation
Denoising Diffusion Probabilistic Model (DDPM) is able to make flexible conditional image generation from prior noise to real data, by introducing an independent noise-aware classifier to provide conditional gradient guidance at each time step of denoising process.
Ranked #2 on
Conditional Image Generation
on ImageNet 128x128
Ultra Fast Deep Lane Detection with Hybrid Anchor Driven Ordinal Classification
With the help of the anchor-driven representation, we then reformulate the lane detection task as an ordinal classification problem to get the coordinates of lanes.
MonoGround: Detecting Monocular 3D Objects from the Ground
To alleviate this problem, we propose to introduce the ground plane as a prior in the monocular 3d object detection.
F3A-GAN: Facial Flow for Face Animation with Generative Adversarial Networks
Formulated as a conditional generation problem, face animation aims at synthesizing continuous face images from a single source image driven by a set of conditional face motion.
D3T-GAN: Data-Dependent Domain Transfer GANs for Few-shot Image Generation
To transfer knowledge between discriminators, we design a multi-level discriminant knowledge distillation from the source discriminator to the target discriminator on both the real and fake samples.
Pricing Path-dependent Options under Stochastic Volatility via Mellin Transform
In this paper, we derive closed-form formulas of first-order approximation for down-and-out barrier and floating strike lookback put option prices under a stochastic volatility model, by using an asymptotic approach.
MIPR:Automatic Annotation of Medical Images with Pixel Rearrangement
In this paper, inspired by self-training of semi-supervised learning, we pro? pose a novel approach to solve the lack of annotated data from another angle, called medical image pixel rearrangement (short in MIPR).
Self-paced Multi-grained Cross-modal Interaction Modeling for Referring Expression Comprehension
As an important and challenging problem in vision-language tasks, referring expression comprehension (REC) generally requires a large amount of multi-grained information of visual and linguistic modalities to realize accurate reasoning.
RBC: Rectifying the Biased Context in Continual Semantic Segmentation
In practice, new images are usually made available in a consecutive manner, leading to a problem called Continual Semantic Segmentation (CSS).
A Review on Methods and Applications in Multimodal Deep Learning
Deep Learning has implemented a wide range of applications and has become increasingly popular in recent years.
Bias-Eliminated Semantic Refinement for Any-Shot Learning
When training samples are scarce, the semantic embedding technique, ie, describing class labels with attributes, provides a condition to generate visual features for unseen objects by transferring the knowledge from seen objects.
Dual-Tasks Siamese Transformer Framework for Building Damage Assessment
Considering the frontier advances of Transformer architecture in the computer vision field, in this paper, we present the first attempt at designing a Transformer-based damage assessment architecture (DamFormer).
Ranked #6 on
Extracting Buildings In Remote Sensing Images
on xBD
CFNet: Learning Correlation Functions for One-Stage Panoptic Segmentation
Recently, there is growing attention on one-stage panoptic segmentation methods which aim to segment instances and stuff jointly within a fully convolutional pipeline efficiently.
Phocus: Picking Valuable Research from a Sea of Citations
The global influential factor of the reference to the citing paper is the product of the local influential factor and the total influential factor of the citing paper.
Test-Time Detection of Backdoor Triggers for Poisoned Deep Neural Networks
A DNN being attacked will predict to an attacker-desired target class whenever a test sample from any source class is embedded with a backdoor pattern; while correctly classifying clean (attack-free) test samples.
Detecting Backdoor Attacks Against Point Cloud Classifiers
Backdoor attacks (BA) are an emerging threat to deep neural network classifiers.
MGH: Metadata Guided Hypergraph Modeling for Unsupervised Person Re-identification
As a challenging task, unsupervised person ReID aims to match the same identity with query images which does not require any labeled information.
Backdoor Attack and Defense for Deep Regression
We demonstrate a backdoor attack on a deep neural network used for regression.
Crypto Wash Trading
We introduce systematic tests exploiting robust statistical and behavioral patterns in trading to detect fake transactions on 29 cryptocurrency exchanges.
Robust and Active Learning for Deep Neural Network Regression
We describe a gradient-based method to discover local error maximizers of a deep neural network (DNN) used for regression, assuming the availability of an "oracle" capable of providing real-valued supervision (a regression target) for samples.
A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets
At the end, we showed future directions with existing challenges of the field.
Multitask Identity-Aware Image Steganography via Minimax Optimization
The key issue of the direct recognition is to preserve identity information of secret images into container images and make container images look similar to cover images at the same time.
When Video Classification Meets Incremental Classes
With the rapid development of social media, tremendous videos with new classes are generated daily, which raise an urgent demand for video classification methods that can continuously update new classes while maintaining the knowledge of old videos with limited storage and computing resources.
Progressive Class-based Expansion Learning For Image Classification
In this paper, we propose a novel image process scheme called class-based expansion learning for image classification, which aims at improving the supervision-stimulation frequency for the samples of the confusing classes.
Attend and select: A segment selective transformer for microblog hashtag generation
These tokens or phrases may originate from primary fragmental textual pieces (e. g., segments) in the original text and are separated into different segments.
VersatileGait: A Large-Scale Synthetic Gait Dataset Towards in-the-Wild Simulation
To diversify the extrinsic factors of gait, we build a complicated scene with a dense camera layout.
CNTLS: A Benchmark Dataset for Abstractive or Extractive Chinese Timeline Summarization
We meticulously analyze the corpus using well-known metrics, focusing on the style of the summaries and the complexity of the summarization task.
A BIC-based Mixture Model Defense against Data Poisoning Attacks on Classifiers
Data Poisoning (DP) is an effective attack that causes trained classifiers to misclassify their inputs.
Recent Advances and Trends in Multimodal Deep Learning: A Review
Deep Learning has implemented a wide range of applications and has become increasingly popular in recent years.
Video Frame Interpolation via Structure-Motion based Iterative Fusion
Inspired by the observation that audiences have different visual preferences on foreground and background objects, we for the first time propose to use saliency masks in the evaluation processes of the task of video frame interpolation.
Deep RGB-D Saliency Detection with Depth-Sensitive Attention and Automatic Multi-Modal Fusion
In principle, the feature modeling scheme is carried out in a depth-sensitive attention module, which leads to the RGB feature enhancement as well as the background distraction reduction by capturing the depth geometry prior.
PcmNet: Position-Sensitive Context Modeling Network for Temporal Action Localization
In this paper, we propose a temporal-position-sensitive context modeling approach to incorporate both positional and semantic information for more precise action localization.
Unsupervised Domain Adaptation for Image Classification via Structure-Conditioned Adversarial Learning
Unsupervised domain adaptation (UDA) typically carries out knowledge transfer from a label-rich source domain to an unlabeled target domain by adversarial learning.
Efficient Style-Corpus Constrained Learning for Photorealistic Style Transfer
Photorealistic style transfer is a challenging task, which demands the stylized image remains real.
Blockchain-empowered Data-driven Networks: A Survey and Outlook
The paths leading to future networks are pointing towards a data-driven paradigm to better cater to the explosive growth of mobile services as well as the increasing heterogeneity of mobile devices, many of which generate and consume large volumes and variety of data.
Networking and Internet Architecture
VersatileGait: A Large-Scale Synthetic Gait Dataset with Fine-GrainedAttributes and Complicated Scenarios
With the motivation of practical gait recognition applications, we propose to automatically create a large-scale synthetic gait dataset (called VersatileGait) by a game engine, which consists of around one million silhouette sequences of 11, 000 subjects with fine-grained attributes in various complicated scenarios.
RDI-Net: Relational Dynamic Inference Networks
In this paper, we model the relations for dynamic inference from two aspects: the routers and the samples.
FcaNet: Frequency Channel Attention Networks
With the proof, we naturally generalize the compression of the channel attention mechanism in the frequency domain and propose our method with multi-spectral channel attention, termed as FcaNet.
Learning to Generate Content-Aware Dynamic Detectors
To the best of our knowledge, our CADDet is the first work to introduce dynamic routing mechanism in object detection.
TextRay: Contour-based Geometric Modeling for Arbitrary-shaped Scene Text Detection
Arbitrary-shaped text detection is a challenging task due to the complex geometric layouts of texts such as large aspect ratios, various scales, random rotations and curve shapes.
Memory Efficient Class-Incremental Learning for Image Classification
To cope with the forgetting problem, many CIL methods transfer the knowledge of old classes by preserving some exemplar samples into the size-constrained memory buffer.
What and Where: Learn to Plug Adapters via NAS for Multi-Domain Learning
As an important and challenging problem, multi-domain learning (MDL) typically seeks for a set of effective lightweight domain-specific adapter modules plugged into a common domain-agnostic network.
A Multi-Semantic Metapath Model for Large Scale Heterogeneous Network Representation Learning
In real-world applications, networks usually consist of billions of various types of nodes and edges with abundant attributes.
Multitask Non-Autoregressive Model for Human Motion Prediction
Human motion prediction, which aims at predicting future human skeletons given the past ones, is a typical sequence-to-sequence problem.
MgSvF: Multi-Grained Slow vs. Fast Framework for Few-Shot Class-Incremental Learning
As a challenging problem, few-shot class-incremental learning (FSCIL) continually learns a sequence of tasks, confronting the dilemma between slow forgetting of old knowledge and fast adaptation to new knowledge.
class-incremental learning
Few-Shot Class-Incremental Learning
+1
Epoch-evolving Gaussian Process Guided Learning
In this paper, we propose a novel learning scheme called epoch-evolving Gaussian Process Guided Learning (GPGL), which aims at characterizing the correlation information between the batch-level distribution and the global data distribution.
A Survey on Generative Adversarial Networks: Variants, Applications, and Training
We survey, (I) the original GAN model and its modified classical versions, (II) detail analysis of various GAN applications in different domains, (III) detail study about the various GAN training obstacles as well as training solutions.
ResKD: Residual-Guided Knowledge Distillation
In this paper, we see knowledge distillation in a fresh light, using the knowledge gap, or the residual, between a teacher and a student as guidance to train a much more lightweight student, called a res-student.
CoDiNet: Path Distribution Modeling with Consistency and Diversity for Dynamic Routing
In this paper, we see dynamic routing networks in a fresh light, formulating a routing method as a mapping from a sample space to a routing space.
Unsupervised segmentation via semantic-apparent feature fusion
In order to solve this problem, the research proposes an unsupervised foreground segmentation method based on semantic-apparent feature fusion (SAFF).
Tamed Warping Network for High-Resolution Semantic Video Segmentation
Based on the feature fusion, our Context Feature Rectification~(CFR) module learns the model's difference from a per-frame model to correct the warped features.
Semantic Neighborhood-Aware Deep Facial Expression Recognition
Different from many other attributes, facial expression can change in a continuous way, and therefore, a slight semantic change of input should also lead to the output fluctuation limited in a small scale.
Facial Expression Recognition
Facial Expression Recognition (FER)
Ultra Fast Structure-aware Deep Lane Detection
Modern methods mainly regard lane detection as a problem of pixel-wise segmentation, which is struggling to address the problem of challenging scenarios and speed.
Ranked #50 on
Lane Detection
on CULane
Progressive Multi-Stage Learning for Discriminative Tracking
Visual tracking is typically solved as a discriminative learning problem that usually requires high-quality samples for online model adaptation.
Real-Time Semantic Segmentation via Auto Depth, Downsampling Joint Decision and Feature Aggregation
To satisfy the stringent requirements on computational resources in the field of real-time semantic segmentation, most approaches focus on the hand-crafted design of light-weight segmentation networks.
Neural Architecture Search
Real-Time Semantic Segmentation
+1
BANet: Bidirectional Aggregation Network with Occlusion Handling for Panoptic Segmentation
Panoptic segmentation aims to perform instance segmentation for foreground instances and semantic segmentation for background stuff simultaneously.
TapLab: A Fast Framework for Semantic Video Segmentation Tapping into Compressed-Domain Knowledge
Real-time semantic video segmentation is a challenging task due to the strict requirements of inference speed.
Realizing Pixel-Level Semantic Learning in Complex Driving Scenes based on Only One Annotated Pixel per Class
Semantic segmentation tasks based on weakly supervised condition have been put forward to achieve a lightweight labeling process.
WSOD with PSNet and Box Regression
To solve this problem, we added the box regression module to the weakly supervised object detection network and proposed a proposal scoring network (PSNet) to supervise it.
Ranked #22 on
Weakly Supervised Object Detection
on PASCAL VOC 2007
Graph-guided Architecture Search for Real-time Semantic Segmentation
Unlike previous works that use a simplified search space and stack a repeatable cell to form a network, we introduce a novel search mechanism with new search space where a lightweight model can be effectively explored through the cell-level diversity and latencyoriented constraint.
Adaptive Graph Representation Learning for Video Person Re-identification
While correlations between parts are ignored in the previous methods, to leverage the relations of different parts, we propose an innovative adaptive graph representation learning scheme for video person Re-ID, which enables the contextual interactions between relevant regional features.
Ranked #3 on
Person Re-Identification
on PRID2011
Graph Representation Learning
Video-Based Person Re-Identification
Spatiotemporal graph routing for skeleton-based action recognition
With the representation effectiveness, skeleton-based human action recognition has received considerable research attention, and has a wide range of real applications.
OVSNet : Towards One-Pass Real-Time Video Object Segmentation
Video object segmentation aims at accurately segmenting the target object regions across consecutive frames.
On a caching system with object sharing
We consider a content-caching system thatis shared by a number of proxies.
Performance Networking and Internet Architecture
Deep Q Learning Driven CT Pancreas Segmentation with Geometry-Aware U-Net
Segmentation of pancreas is important for medical image analysis, yet it faces great challenges of class imbalance, background distractions and non-rigid geometrical features.
Perceiving Physical Equation by Observing Visual Scenarios
To tackle this challenge, we present a novel pipeline comprised of an Observer Engine and a Physicist Engine by respectively imitating the actions of an observer and a physicist in the real world.
GroundNet: Monocular Ground Plane Normal Estimation with Geometric Consistency
We focus on estimating the 3D orientation of the ground plane from a single image.
Context-Aware Deep Spatio-Temporal Network for Hand Pose Estimation from Depth Images
As a fundamental and challenging problem in computer vision, hand pose estimation aims to estimate the hand joint locations from depth images.
Stacked Pooling: Improving Crowd Counting by Boosting Scale Invariance
In this work, we explore the cross-scale similarity in crowd counting scenario, in which the regions of different scales often exhibit high visual similarity.
Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Features
Then in the top-down step, the refined object regions are used as supervision to train the segmentation network and to predict object masks.
Geometry-Aware Scene Text Detection With Instance Transformation Network
Localizing text in the wild is challenging in the situations of complicated geometric layout of the targets like random orientation and large aspect ratio.
State Distribution-aware Sampling for Deep Q-learning
A critical and challenging problem in reinforcement learning is how to learn the state-action value function from the experience replay buffer and simultaneously keep sample efficiency and faster convergence to a high quality solution.
GNAS: A Greedy Neural Architecture Search Method for Multi-Attribute Learning
A key problem in deep multi-attribute learning is to effectively discover the inter-attribute correlation structures.
Multi-Channel Pyramid Person Matching Network for Person Re-Identification
In particular, we learn separate deep representations for semantic-components and color-texture distributions from two person images and then employ pyramid person matching network (PPMN) to obtain correspondence representations.
Pyramid Person Matching Network for Person Re-identification
In this work, we present a deep convolutional pyramid person matching network (PPMN) with specially designed Pyramid Matching Module to address the problem of person re-identification.
DR-Net: Transmission Steered Single Image Dehazing Network with Weakly Supervised Refinement
Despite the recent progress in image dehazing, several problems remain largely unsolved such as robustness for varying scenes, the visual quality of reconstructed images, and effectiveness and flexibility for applications.
Deep Air Learning: Interpolation, Prediction, and Feature Analysis of Fine-grained Air Quality
The interpolation, prediction, and feature analysis of fine-gained air quality are three important topics in the area of urban air computing.
Graph-Theoretic Spatiotemporal Context Modeling for Video Saliency Detection
As a result, a key issue in video saliency detection is how to effectively capture the intrinsical properties of atomic video structures as well as their associated contextual interactions along the spatial and temporal dimensions.
Boosted Zero-Shot Learning with Semantic Correlation Regularization
For adaptable knowledge transfer, we devise a Semantic Correlation Regularization (SCR) approach to regularize the boosted model to be consistent with the inter-class semantic correlations.
Group-wise Deep Co-saliency Detection
In this paper, we propose an end-to-end group-wise deep co-saliency detection approach to address the co-salient object discovery problem based on the fully convolutional network (FCN) with group input and group output.
Deeply-Learned Part-Aligned Representations for Person Re-Identification
In this paper, we address the problem of person re-identification, which refers to associating the persons captured from different cameras.
Ranked #110 on
Person Re-Identification
on Market-1501
Deep Optical Flow Estimation Via Multi-Scale Correspondence Structure Learning
Therefore, a key issue to solve in this area is how to effectively model the multi-scale correspondence structure properties in an adaptive end-to-end learning fashion.
Transductive Zero-Shot Learning with a Self-training dictionary approach
As an important and challenging problem in computer vision, zero-shot learning (ZSL) aims at automatically recognizing the instances from unseen object classes without training data.
Deep Convolutional Neural Networks with Merge-and-Run Mappings
A deep residual network, built by stacking a sequence of residual blocks, is easy to train, because identity mappings skip residual branches and thus improve information flow.
DLAU: A Scalable Deep Learning Accelerator Unit on FPGA
As the emerging field of machine learning, deep learning shows excellent ability in solving complex learning problems.
Deep Learning Driven Visual Path Prediction from a Single Image
The highly effective visual representation and deep context models ensure that our framework makes a deep semantic understanding of the scene and motion pattern, consequently improving the performance of the visual path prediction task.
3D Hand Pose Estimation Using Randomized Decision Forest With Segmentation Index Points
In this paper, we propose a real-time 3D hand pose estimation algorithm using the randomized decision forest framework.
DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection
A key problem in salient object detection is how to effectively model the semantic properties of salient objects in a data-driven manner.
Online Metric-Weighted Linear Representations for Robust Visual Tracking
Object identification results for an entire video sequence are achieved by systematically combining the tracking information and visual recognition at each frame.
Metric Learning Driven Multi-Task Structured Output Optimization for Robust Keypoint Tracking
As an important and challenging problem in computer vision and graphics, keypoint-based object tracking is typically formulated in a spatio-temporal statistical learning framework.
Context-Aware Hypergraph Construction for Robust Spectral Clustering
Using both CAHSM and DHPC, a robust spectral clustering algorithm is developed.
Contextual Hypergraph Modelling for Salient Object Detection
In this work, we model an image as a hypergraph that utilizes a set of hyperedges to capture the contextual properties of image pixels or regions.
Learning Compact Binary Codes for Visual Tracking
A key problem in visual tracking is to represent the appearance of an object in a way that is robust to visual changes.
3D R Transform on Spatio-temporal Interest Points for Action Recognition
In this paper, we propose a new global feature to capture the detailed geometrical distribution of interest points.
