Search Results for author:
Found 45 papers, 18 papers with code
HARD-Net: Hardness-AwaRe Discrimination Network for 3D Early Activity Prediction
In this paper, we propose a novel Hardness-AwaRe Discrimination Network (HARD-Net) to specifically investigate the relationships between the similar activity pairs that are hard to be discriminated.
Ranked #4 on
Skeleton Based Action Recognition
on UAV-Human
FHDe²Net: Full High Definition Demoireing Network
Frequency aliasing in the digital capture of display screens leads to the moir´e pattern, appearing as stripe-shaped distortions in images.
Exploring Model Transferability through the Lens of Potential Energy
The experimental results on 10 downstream tasks and 12 self-supervised models demonstrate that our approach can seamlessly integrate into existing ranking techniques and enhance their performances, revealing its effectiveness for the model selection task and its potential for understanding the mechanism in transfer learning.
Modeling Uncertain Feature Representation for Domain Generalization
In this paper, we improve the network generalization ability by modeling domain shifts with uncertainty (DSU), i. e., characterizing the feature statistics as uncertain distributions during training.
Switchable Representation Learning Framework with Self-compatibility
Existing research mainly focuses on the one-to-one compatible paradigm, which is limited in learning compatibility among multiple models.
mc-BEiT: Multi-choice Discretization for Image BERT Pre-training
Image BERT pre-training with masked image modeling (MIM) becomes a popular practice to cope with self-supervised representation learning.
Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning
Instead, we propose a data-free knowledge distillation method to fine-tune the global model in the server (FedFTG), which relieves the issue of direct model aggregation.
Bridging the Source-to-target Gap for Cross-domain Person Re-Identification with Intermediate Domains
Instead of directly aligning the source and target domains against each other, we propose to align the source and target domains against their intermediate domains for a smooth knowledge transfer.
Uncertainty Modeling for Out-of-Distribution Generalization
In this paper, we improve the network generalization ability by modeling the uncertainty of domain shifts with synthesized feature statistics during training.
Towards Low Light Enhancement with RAW Images
In this paper, we make the first benchmark effort to elaborate on the superiority of using RAW images in the low light enhancement and develop a novel alternative route to utilize RAW images in a more flexible and practical way.
Video Coding for Machine: Compact Visual Representation Compression for Intelligent Collaborative Analytics
By keeping in mind the transferability among different machine vision tasks (e. g. high-level semantic and mid-level geometry-related), we aim to support multiple tasks jointly at low bit rates.
Dual-Tuning: Joint Prototype Transfer and Structure Regularization for Compatible Feature Learning
It is a heavy workload to re-extract features of the whole database every time. Feature compatibility enables the learned new visual features to be directly compared with the old features stored in the database.
IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID
To ensure these two properties to better characterize appropriate intermediate domains, we enforce the bridge losses on intermediate domains' prediction space and feature space, and enforce a diversity loss on the two domain factors.
Domain Adaptive Person Re-Identification
Person Re-Identification
Single Image Reflection Removal With Absorption Effect
In this paper, we consider the absorption effect for the problem of single image reflection removal.
Person30K: A Dual-Meta Generalization Network for Person Re-Identification
Recently, person re-identification (ReID) has vastly benefited from the surging waves of data-driven methods.
Generalizable Person Re-identification with Relevance-aware Mixture of Experts
Specifically, we propose a decorrelation loss to make the source domain networks (experts) keep the diversity and discriminability of individual domains' characteristics.
Federated Learning for Non-IID Data via Unified Feature Learning and Optimization Objective Alignment
Federated Learning (FL) aims to establish a shared model across decentralized clients under the privacy-preserving constraint.
Dual-Refinement: Joint Label and Feature Refinement for Unsupervised Domain Adaptive Person Re-Identification
To this end, we propose a novel approach, called Dual-Refinement, that jointly refines pseudo labels at the off-line clustering phase and features at the on-line training phase, to alternatively boost the label purity and feature discriminability in the target domain for more reliable re-ID.
Market2Dish: Health-aware Food Recommendation
With the rising incidence of some diseases, such as obesity and diabetes, a healthy diet is arousing increasing attention.
Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation
To fully exploit the supervision in the source domain, we propose a fine-grained adversarial learning strategy for class-level feature alignment while preserving the internal structure of semantics across domains.
Ranked #15 on
Image-to-Image Translation
on SYNTHIA-to-Cityscapes
Video Coding for Machines: A Paradigm of Collaborative Compression and Intelligent Analytics
Meanwhile, we systematically review state-of-the-art techniques in video compression and feature compression from the unique perspective of MPEG standardization, which provides the academic and industrial evidence to realize the collaborative compression of video and feature streams in a broad range of AI applications.
An Emerging Coding Paradigm VCM: A Scalable Coding Approach Beyond Feature and Signal
To this end, we make endeavors in leveraging the strength of predictive and generative models to support advanced compression techniques for both machine and human vision tasks simultaneously, in which visual features serve as a bridge to connect signal-level and task-level compact representations in a scalable manner.
Towards Coding for Human and Machine Vision: A Scalable Image Coding Approach
In this paper, we come up with a novel image coding framework by leveraging both the compressive and the generative models, to support machine vision and human perception tasks jointly.
Towards Digital Retina in Smart Cities: A Model Generation, Utilization and Communication Paradigm
The digital retina in smart cities is to select what the City Eye tells the City Brain, and convert the acquired visual data from front-end visual sensors to features in an intelligent sensing manner.
Hard-Aware Fashion Attribute Classification
For "hard" attributes with insufficient training data, Deact brings more stable synthetic samples for training and further improve the performance.
NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding
Research on depth-based human activity analysis achieved outstanding performance and demonstrated the effectiveness of 3D representation for action recognition.
Ranked #5 on
One-Shot 3D Action Recognition
on NTU RGB+D 120
SPLINE-Net: Sparse Photometric Stereo through Lighting Interpolation and Normal Estimation Networks
This paper solves the Sparse Photometric stereo through Lighting Interpolation and Normal Estimation using a generative Network (SPLINE-Net).
Exploring Object Relation in Mean Teacher for Cross-Domain Detection
The whole architecture is then optimized with three consistency regularizations: 1) region-level consistency to align the region-level predictions between teacher and student, 2) inter-graph consistency for matching the graph structures between teacher and student, and 3) intra-graph consistency to enhance the similarity between regions of same class within the graph of student.
Towards Accurate One-Stage Object Detection with AP-Loss
For this purpose, we develop a novel optimization algorithm, which seamlessly combines the error-driven update scheme in perceptron learning and backpropagation algorithm in deep networks.
Face Image Reflection Removal
Face images captured through the glass are usually contaminated by reflections.
Skeleton-Based Online Action Prediction Using Scale Selection Network
Since there are significant temporal scale variations in the observed part of the ongoing action at different time steps, a novel window scale selection method is proposed to make our network focus on the performed part of the ongoing action and try to suppress the possible incoming interference from the previous actions at each step.
Ranked #64 on
Skeleton Based Action Recognition
on NTU RGB+D 120
Feature Boosting Network For 3D Pose Estimation
Learning a set of features that are reliable and discriminatively representative of the pose of a hand (or body) part is difficult due to the ambiguities, texture and illumination variation, and self-occlusion in the real application of 3D pose estimation.
Transfer Metric Learning: Algorithms, Applications and Outlooks
Distance metric learning (DML) aims to find an appropriate way to reveal the underlying data relationship.
Intermediate Deep Feature Compression: the Next Battlefield of Intelligent Sensing
The recent advances of hardware technology have made the intelligent analysis equipped at the front-end with deep learning more prevailing and practical.
SSNet: Scale Selection Network for Online 3D Action Prediction
As there are significant temporal scale variations of the observed part of the ongoing action at different progress levels, we propose a novel window scale selection scheme to make our network focus on the performed part of the ongoing action and try to suppress the noise from the previous actions at each time step.
CRRN: Multi-Scale Guided Concurrent Reflection Removal Network
Removing the undesired reflections from images taken through the glass is of broad application to various computer vision tasks.
AI Oriented Large-Scale Video Management for Smart City: Technologies, Standards and Beyond
To practically facilitate deep neural network models in the large-scale video analysis, there are still unprecedented challenges for the large-scale video data management.
Benchmarking Single-Image Reflection Removal Algorithms
Removing undesired reflections from a photo taken in front of a glass is of great importance for enhancing the efficiency of visual computing systems.
Skeleton-Based Human Action Recognition with Global Context-Aware Attention LSTM Networks
In this paper, we propose a new class of LSTM network, Global Context-Aware Attention LSTM (GCA-LSTM), for skeleton based action recognition.
Ranked #62 on
Skeleton Based Action Recognition
on NTU RGB+D 120
Pruning Convolutional Neural Networks for Image Instance Retrieval
In this work, we focus on the problem of image instance retrieval with deep descriptors extracted from pruned Convolutional Neural Networks (CNN).
Global Context-Aware Attention LSTM Networks for 3D Action Recognition
Hence we propose a new class of LSTM network, Global Context-Aware Attention LSTM (GCA-LSTM), for 3D action recognition, which is able to selectively focus on the informative joints in the action sequence with the assistance of global contextual information.
Ranked #7 on
One-Shot 3D Action Recognition
on NTU RGB+D 120
Compact Descriptors for Video Analysis: the Emerging MPEG Standard
This paper provides an overview of the on-going compact descriptors for video analysis standard (CDVA) from the ISO/IEC moving pictures experts group (MPEG).
Incorporating Intra-Class Variance to Fine-Grained Visual Recognition
In this paper, we propose to leverage intra-class variance in metric learning of triplet network to improve the performance of fine-grained recognition.
Improving Object Detection with Region Similarity Learning
Object detection aims to identify instances of semantic objects of a certain class in images or videos.
Compression of Deep Neural Networks for Image Instance Retrieval
One major drawback of CNN-based {\it global descriptors} is that uncompressed deep neural network models require hundreds of megabytes of storage making them inconvenient to deploy in mobile applications or in custom hardware.
