Search Results for author:
Found 58 papers, 15 papers with code
IDOL: Unified Dual-Modal Latent Diffusion for Human-Centric Joint Video-Depth Generation
First, to enable dual-modal generation and maximize the information exchange between video and depth generation, we propose a unified dual-modal U-Net, a parameter-sharing framework for joint video and depth denoising, wherein a modality label guides the denoising target, and cross-modal attention enables the mutual information flow.
ClawMachine: Fetching Visual Tokens as An Entity for Referring and Grounding
Existing methods, including proxy encoding and geometry encoding, incorporate additional syntax to encode the object's location, bringing extra burdens in training MLLMs to communicate between language and vision.
Motion Consistency Model: Accelerating Video Diffusion with Disentangled Motion-Appearance Distillation
Extensive experiments show that our MCM achieves the state-of-the-art video diffusion distillation performance.
Artemis: Towards Referential Understanding in Complex Videos
Videos carry rich visual information including object description, action, interaction, etc., but the existing multimodal large language models (MLLMs) fell short in referential understanding scenarios such as video-based referring.
ChartReformer: Natural Language-Driven Chart Image Editing
Chart visualizations are essential for data interpretation and communication; however, most charts are only accessible in image format and lack the corresponding data tables and supplementary information, making it difficult to alter their appearance for different application scenarios.
Federated Learning via Input-Output Collaborative Distillation
Federated learning (FL) is a machine learning paradigm in which distributed local nodes collaboratively train a central model without sharing individually held private data.
The Analysis and Extraction of Structure from Organizational Charts
Organizational charts, also known as org charts, are critical representations of an organization's structure and the hierarchical relationships between its components and positions.
Player Re-Identification Using Body Part Appearences
Our model consists of a two-stream network (one stream for appearance map extraction and the other for body part map extraction) and a bilinear-pooling layer that generates and spatially pools the body part map.
SOAR: Scene-debiasing Open-set Action Recognition
The former prevents the decoder from reconstructing the video background given video features, and thus helps reduce the background information in feature learning.
Towards Generic Image Manipulation Detection with Weakly-Supervised Self-Consistency Learning
To improve the generalization ability, we propose weakly-supervised self-consistency learning (WSCL) to leverage the weakly annotated images.
Language-guided Human Motion Synthesis with Atomic Actions
In this paper, we propose ATOM (ATomic mOtion Modeling) to mitigate this problem, by decomposing actions into atomic actions, and employing a curriculum learning strategy to learn atomic action composition.
SpaDen : Sparse and Dense Keypoint Estimation for Real-World Chart Understanding
A combination of sparse and dense per-pixel objectives coupled with a uni-modal self-attention-based feature-fusion layer is applied to learn KP embeddings.
Filter Pruning for Efficient CNNs via Knowledge-driven Differential Filter Sampler
In this paper, we propose a novel Knowledge-driven Differential Filter Sampler~(KDFS) with Masked Filter Modeling~(MFM) framework for filter pruning, which globally prunes the redundant filters based on the prior knowledge of a pre-trained model in a differential and non-alternative optimization.
Context-Aware Chart Element Detection
As a prerequisite of chart data extraction, the accurate detection of chart basic elements is essential and mandatory.
LineFormer: Rethinking Line Chart Data Extraction as Instance Segmentation
Existing works, however, are not robust to all these variations, either taking an all-chart unified approach or relying on auxiliary information such as legends for line data extraction.
Progressive Multi-view Human Mesh Recovery with Self-Supervision
To date, little attention has been given to multi-view 3D human mesh estimation, despite real-life applicability (e. g., motion capture, sport analysis) and robustness to single-view ambiguities.
Federated Learning with Privacy-Preserving Ensemble Attention Distillation
We propose a privacy-preserving FL framework leveraging unlabeled public data for one-way offline knowledge distillation in this work.
PREF: Predictability Regularized Neural Motion Fields
We propose to regularize the estimated motion to be predictable.
Self-supervised Human Mesh Recovery with Cross-Representation Alignment
However, on synthetic dense correspondence maps (i. e., IUV) few have been explored since the domain gap between synthetic training data and real testing data is hard to address for 2D dense representation.
Preserving Privacy in Federated Learning with Ensemble Cross-Domain Knowledge Distillation
Federated Learning (FL) is a machine learning paradigm where local nodes collaboratively train a central model while the training data remains decentralized.
Confidence Dimension for Deep Learning based on Hoeffding Inequality and Relative Evaluation
Research on the generalization ability of deep neural networks (DNNs) has recently attracted a great deal of attention.
Associative Adversarial Learning Based on Selective Attack
We show that our method improves the recognition accuracy of adversarial training on ImageNet by 8. 32% compared with the baseline.
Semantic Text-to-Face GAN -ST^2FG
Our approach is capable of generating images that are very accurately aligned to the exhaustive textual descriptions of faces with many fine detail features of the face and helps in generating better images.
Two-Stream Consensus Network: Submission to HACS Challenge 2021 Weakly-Supervised Learning Track
The base model training encourages the model to predict reliable predictions based on single modality (i. e., RGB or optical flow), based on the fusion of which a pseudo ground truth is generated and in turn used as supervision to train the base models.
Cogradient Descent for Dependable Learning
Conventional gradient descent methods compute the gradients for multiple variables through the partial derivative.
Layer-Wise Searching for 1-Bit Detectors
At each layer, it exploits a differentiable binarization search (DBS) to minimize the angular error in a student-teacher framework.
Oriented Object Detection with Transformer
Object detection with Transformers (DETR) has achieved a competitive performance over traditional detectors, such as Faster R-CNN.
Probabilistic Ranking-Aware Ensembles for Enhanced Object Detections
This leads to a new problem of confidence discrepancy for the detector ensembles.
Multi-UAV Mobile Edge Computing and Path Planning Platform based on Reinforcement Learning
Unmanned Aerial vehicles (UAVs) are widely used as network processors in mobile networks, but more recently, UAVs have been used in Mobile Edge Computing as mobile servers.
IDARTS: Interactive Differentiable Architecture Search
Differentiable Architecture Search (DARTS) improves the efficiency of architecture search by learning the architecture and network parameters end-to-end.
Ensemble Attention Distillation for Privacy-Preserving Federated Learning
Such decentralized training naturally leads to issues of imbalanced or differing data distributions among the local models and challenges in fusing them into a central model.
Deformable Gabor Feature Networks for Biomedical Image Classification
In recent years, deep learning has dominated progress in the field of medical image analysis.
A Review of Recent Advances of Binary Neural Networks for Edge Computing
Edge computing is promising to become one of the next hottest topics in artificial intelligence because it benefits various evolving domains such as real-time unmanned aerial systems, industrial applications, and the demand for privacy protection.
Binarized Neural Architecture Search for Efficient Object Recognition
In this paper, binarized neural architecture search (BNAS), with a search space of binarized convolutions, is introduced to produce extremely compressed models to reduce huge computational cost on embedded devices for edge computing.
Anti-Bandit Neural Architecture Search for Model Defense
Deep convolutional neural networks (DCNNs) have dominated as the best performers in machine learning, but can be challenged by adversarial attacks.
iffDetector: Inference-aware Feature Filtering for Object Detection
In this paper, we propose a new feature optimization approach to enhance features and suppress background noise in both the training and inference stages.
Cogradient Descent for Bilinear Optimization
Conventional learning methods simplify the bilinear model by regarding two intrinsically coupled factors independently, which degrades the optimization procedure.
CP-NAS: Child-Parent Neural Architecture Search for Binary Neural Networks
To this end, a Child-Parent (CP) model is introduced to a differentiable NAS to search the binarized architecture (Child) under the supervision of a full-precision model (Parent).
NAS-Count: Counting-by-Density with Neural Architecture Search
Most of the recent advances in crowd counting have evolved from hand-designed density estimation networks, where multi-scale features are leveraged to address the scale variation problem, but at the expense of demanding design efforts.
Binarized Neural Architecture Search
A variant, binarized neural architecture search (BNAS), with a search space of binarized convolutions, can produce extremely compressed models.
Circulant Binary Convolutional Networks: Enhancing the Performance of 1-bit DCNNs with Circulant Back Propagation
The CiFs can be easily incorporated into existing deep convolutional neural networks (DCNNs), which leads to new Circulant Binary Convolutional Networks (CBCNs).
Towards Optimal Structured CNN Pruning via Generative Adversarial Learning
In this paper, we propose an effective structured pruning approach that jointly prunes filters as well as other structures in an end-to-end manner.
Crowd Counting and Density Estimation by Trellis Encoder-Decoder Network
In this paper, we propose a trellis encoder-decoder network (TEDnet) for crowd counting, which focuses on generating high-quality density estimation maps.
Exploiting Kernel Sparsity and Entropy for Interpretable CNN Compression
The relationship between the input feature maps and 2D kernels is revealed in a theoretical framework, based on which a kernel sparsity and entropy (KSE) indicator is proposed to quantitate the feature map importance in a feature-agnostic manner to guide model compression.
Projection Convolutional Neural Networks for 1-bit CNNs via Discrete Back Propagation
The advancement of deep convolutional neural networks (DCNNs) has driven significant improvement in the accuracy of recognition systems for many computer vision tasks.
IOD-CNN: Integrating Object Detection Networks for Event Recognition
Many previous methods have showed the importance of considering semantically relevant objects for performing event recognition, yet none of the methods have exploited the power of deep convolutional neural networks to directly integrate relevant object information into a unified network.
A Graphical Model Approach for Matching Partial Signatures
In this paper, we present a novel partial signature matching method using graphical models.
SHOE: Supervised Hashing with Output Embeddings
We present a supervised binary encoding scheme for image retrieval that learns projections by taking into account similarity between classes obtained from output embeddings.
A random forest system combination approach for error detection in digital dictionaries
We investigate combining methods and show that using random forests is a promising approach.
Detecting Structural Irregularity in Electronic Dictionaries Using Language Modeling
Dictionaries are often developed using tools that save to Extensible Markup Language (XML)-based standards.
Correcting Errors in Digital Lexicographic Resources Using a Dictionary Manipulation Language
We describe a paradigm for combining manual and automatic error correction of noisy structured lexicographic data.
Active Sampling for Subjective Image Quality Assessment
Subjective tests based on the Mean Opinion Score (MOS) have been widely used in previous studies, but have many known problems such as an ambiguous scale definition and dissimilar interpretations of the scale among subjects.
Orientation Robust Text Line Detection in Natural Images
In this paper, higher-order correlation clustering (HOCC) is used for text line detection in natural images.
Convolutional Neural Networks for No-Reference Image Quality Assessment
In this work we describe a Convolutional Neural Network (CNN) to accurately predict image quality without a reference image.
Beyond Human Opinion Scores: Blind Image Quality Assessment based on Synthetic Scores
Instead of training on human opinion scores, we propose to train BIQA models on synthetic scores derived from Full-Reference (FR) IQA measures.
Real-Time No-Reference Image Quality Assessment Based on Filter Learning
Second, the proposed method has the potential to be used in multiple image domains.
Linguistic Resources for Handwriting Recognition and Translation Evaluation
LDC has developed a stable pipeline and infrastructures for collecting and annotating handwriting linguistic resources to support the evaluation of MADCAT and OpenHaRT.
