Search Results for author:
Found 101 papers, 33 papers with code
CALLIC: Content Adaptive Learning for Lossless Image Compression
To address this challenge, we explore the connection between the Minimum Description Length (MDL) principle and Parameter-Efficient Transfer Learning (PETL), leading to the development of a novel content-adaptive approach for learned lossless image compression, dubbed CALLIC.
Predicting Satisfied User and Machine Ratio for Compressed Images: A Unified Approach
It is meaningful to predict the perceptual quality of compressed images for both humans and machines, which guides the optimization for compression.
Image-based Freeform Handwriting Authentication with Energy-oriented Self-Supervised Learning
Freeform handwriting authentication verifies a person's identity from their writing style and habits in messy handwriting data.
Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI
In this survey, we give a comprehensive exploration of the latest advancements in Embodied AI.
Understanding is Compression
The better a large model understands the data, the better LMCompress compresses.
VLBiasBench: A Comprehensive Benchmark for Evaluating Bias in Large Vision-Language Model
The emergence of Large Vision-Language Models (LVLMs) marks significant strides towards achieving general artificial intelligence.
GroupedMixer: An Entropy Model with Group-wise Token-Mixers for Learned Image Compression
To further expedite the network inference, we introduce context cache optimization to GroupedMixer, which caches attention activation values in cross-group token-mixers and avoids complex and duplicated computation.
Stream State-tying for Sign Language Recognition
In this paper, a novel approach to sign language recognition based on state tying in each of data streams is presented.
IME: Integrating Multi-curvature Shared and Specific Embedding for Temporal Knowledge Graph Completion
However, existing Temporal Knowledge Graph Completion (TKGC) methods either model TKGs in a single space or neglect the heterogeneity of different curvature spaces, thus constraining their capacity to capture these intricate geometric structures.
SPC-NeRF: Spatial Predictive Compression for Voxel Based Radiance Field
Representing the Neural Radiance Field (NeRF) with the explicit voxel grid (EVG) is a promising direction for improving NeRFs.
Lightweight super resolution network for point cloud geometry compression
This paper presents an approach for compressing point cloud geometry by leveraging a lightweight super-resolution network.
AI Alignment: A Comprehensive Survey
The former aims to make AI systems aligned via alignment training, while the latter aims to gain evidence about the systems' alignment and govern them appropriately to avoid exacerbating misalignment risks.
Intelligence-Endogenous Management Platform for Computing and Network Convergence
Therefore, in this article, we present the concept of an intelligence-endogenous management platform for CNCs called \emph{CNC brain} based on artificial intelligence technologies.
A Survey on Temporal Knowledge Graph Completion: Taxonomy, Progress, and Prospects
Temporal characteristics are prominently evident in a substantial volume of knowledge, which underscores the pivotal role of Temporal Knowledge Graphs (TKGs) in both academia and industry.
CSSL-RHA: Contrastive Self-Supervised Learning for Robust Handwriting Authentication
In this paper, we propose a novel Contrastive Self-Supervised Learning framework for Robust Handwriting Authentication (CSSL-RHA) to address these issues.
SpikeCodec: An End-to-end Learned Compression Framework for Spiking Camera
Recently, the bio-inspired spike camera with continuous motion recording capability has attracted tremendous attention due to its ultra high temporal resolution imaging characteristic.
Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation
On the other hand, JPMA is proposed to assemble multiple hypotheses generated by D3DP into a single 3D pose for practical use.
Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey
We also give visualization and analysis of the model parameters and results on representative downstream tasks.
Learning to Compress Unmanned Aerial Vehicle (UAV) Captured Video: Benchmark and Analysis
During the past decade, the Unmanned-Aerial-Vehicles (UAVs) have attracted increasing attention due to their flexible, extensive, and dynamic space-sensing capabilities.
Perceptual Video Coding for Machines via Satisfied Machine Ratio Modeling
Each score is derived from machine perceptual differences between original and compressed images.
Deep Lossy Plus Residual Coding for Lossless and Near-lossless Image Compression
In the lossless mode, the DLPR coding system first performs lossy compression and then lossless coding of residuals.
Cross Modal Compression: Towards Human-comprehensible Semantic Compression
With the recent advances in cross modal translation and generation, in this paper, we propose the cross modal compression~(CMC), a semantic compression framework for visual data, to transform the high redundant visual data~(such as image, video, etc.)
Towards Hybrid-Optimization Video Coding
Our idea is to provide multiple discrete starting points in the global space and optimize the local optimum around each point by numerical algorithm efficiently.
STIP: A SpatioTemporal Information-Preserving and Perception-Augmented Model for High-Resolution Video Prediction
To solve the information loss problem, the proposed model aims to preserve the spatiotemporal information for videos during the feature extraction and the state transitions, respectively.
Hierarchical Similarity Learning for Aliasing Suppression Image Super-Resolution
As a highly ill-posed issue, single image super-resolution (SISR) has been widely investigated in recent years.
Textural-Perceptual Joint Learning for No-Reference Super-Resolution Image Quality Assessment
Image super-resolution (SR) has been widely investigated in recent years.
Learning Weighting Map for Bit-Depth Expansion within a Rational Range
Existing BDE methods have no unified solution for various BDE situations, and directly learn a mapping for each pixel from LBD image to the desired value in HBD image, which may change the given high-order bits and lead to a huge deviation from the ground truth.
STAU: A SpatioTemporal-Aware Unit for Video Prediction and Beyond
In this paper, we propose a SpatioTemporal-Aware Unit (STAU) for video prediction and beyond by exploring the significant spatiotemporal correlations in videos.
STRPM: A Spatiotemporal Residual Predictive Model for High-Resolution Video Prediction
In this paper, we propose a Spatiotemporal Residual Predictive Model (STRPM) for high-resolution video prediction.
Gradient Correction beyond Gradient Descent
GCGD consists of two plug-in modules: 1) inspired by the idea of gradient prediction, we propose a \textbf{GC-W} module for weight gradient correction; 2) based on Neural ODE, we propose a \textbf{GC-ODE} module for hidden states gradient correction.
P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimation
In Stage II, the pre-trained encoder is loaded to STMO model and fine-tuned.
Ranked #11 on
Monocular 3D Human Pose Estimation
on Human3.6M
Cross-SRN: Structure-Preserving Super-Resolution Network with Cross Convolution
It is challenging to restore low-resolution (LR) images to super-resolution (SR) images with correct and clear details.
Instance-Aware Dynamic Neural Network Quantization
However, natural images are of huge diversity with abundant content and using such a universal quantization configuration for all samples is not an optimal strategy.
ERNIE 3.0 Titan: Exploring Larger-scale Knowledge Enhanced Pre-training for Language Understanding and Generation
A unified framework named ERNIE 3. 0 was recently proposed for pre-training large-scale knowledge enhanced models and trained a model with 10 billion parameters.
Towards End-to-End Image Compression and Analysis with Transformers
Meanwhile, we propose a feature aggregation module to fuse the compressed features with the selected intermediate features of the Transformer, and feed the aggregated features to a deconvolutional neural network for image reconstruction.
MAU: A Motion-Aware Unit for Video Prediction and Beyond
The attention module aims to learn an attention map based on the correlations between the current spatial state and the historical spatial states.
Ranked #19 on
Video Prediction
on Moving MNIST
Improving Robustness and Accuracy via Relative Information Encoding in 3D Human Pose Estimation
To alleviate these two problems, we propose a relative information encoding method that yields positional and temporal enhanced representations.
Ranked #14 on
Monocular 3D Human Pose Estimation
on Human3.6M
Post-Training Quantization for Vision Transformer
Recently, transformer has achieved remarkable performance on a variety of computer vision applications.
Rate Distortion Characteristic Modeling for Neural Image Compression
End-to-end optimized neural image compression (NIC) has obtained superior lossy compression performance recently.
Progressive Stage-wise Learning for Unsupervised Feature Representation Enhancement
For a given unsupervised task, we design multilevel tasks and define different learning stages for the deep network.
Recent Standard Development Activities on Video Coding for Machines
Specifically, we will first provide an overview of the MPEG VCM group including use cases, requirements, processing pipelines, plan for potential VCM standards, followed by the evaluation framework including machine-vision tasks, dataset, evaluation metrics, and anchor generation.
Intrinsic Temporal Regularization for High-resolution Human Video Synthesis
Temporal consistency is crucial for extending image processing pipelines to the video domain, which is often enforced with flow-based warping error over adjacent frames.
Pre-Trained Image Processing Transformer
To maximally excavate the capability of transformer, we present to utilize the well-known ImageNet benchmark for generating a large amount of corrupted image pairs.
Ranked #1 on
Single Image Deraining
on Rain100L
(using extra training data)
Implicit Subspace Prior Learning for Dual-Blind Face Restoration
Face restoration is an inherently ill-posed problem, where additional prior constraints are typically considered crucial for mitigating such pathology.
Sequential Hierarchical Learning with Distribution Transformation for Image Super-Resolution
Based on the observation, in this paper, we build a sequential hierarchical learning super-resolution network (SHSR) for effective image SR.
Ranked #15 on
Image Super-Resolution
on Manga109 - 3x upscaling
SACNN: Self-Attention Convolutional Neural Network for Low-Dose CT Denoising With Self-Supervised Perceptual Loss Network
We combine these two methods and demonstrate their effectiveness on both CNN-based neural networks and WGAN-based neural networks with comprehensive experiments.
Towards Fine-grained Human Pose Transfer with Detail Replenishing Network
Human pose transfer (HPT) is an emerging research topic with huge potential in fashion design, media production, online advertising and virtual reality.
Region-adaptive Texture Enhancement for Detailed Person Image Synthesis
The ability to produce convincing textural details is essential for the fidelity of synthesized person images.
Ranked #4 on
Pose Transfer
on Deep-Fashion
Iterative Network for Image Super-Resolution
A novel iterative super-resolution network (ISRN) is proposed on top of the iterative optimization.
HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment
Existing face restoration researches typically relies on either the degradation prior or explicit guidance labels for training, which often results in limited generalization ability over real-world images with heterogeneous degradations and rich background contents.
Segatron: Segment-Aware Transformer for Language Modeling and Understanding
To verify this, we propose a segment-aware Transformer (Segatron), by replacing the original token position encoding with a combined position encoding of paragraph, sentence, and token.
Ranked #20 on
Language Modelling
on WikiText-103
Location-Aware Feature Selection Text Detection Network
However, they are behind in accuracy comparing with recent segmentation-based text detectors.
Towards Analysis-friendly Face Representation with Scalable Feature and Texture Compression
In particular, we study the feature and texture compression in a scalable coding framework, where the base layer serves as the deep learning feature and enhancement layer targets to perfectly reconstruct the texture.
Learning to fool the speaker recognition
Due to the widespread deployment of fingerprint/face/speaker recognition systems, attacking deep learning based biometric systems has drawn more and more attention.
Audio and Speech Processing Cryptography and Security Sound
Universal Adversarial Perturbations Generative Network for Speaker Recognition
Attacking deep learning based biometric systems has drawn more and more attention with the wide deployment of fingerprint/face/speaker recognition systems, given the fact that the neural networks are vulnerable to the adversarial examples, which have been intentionally perturbed to remain almost imperceptible for human.
Direct Speech-to-image Translation
In this paper, we attempt to translate the speech signals into the image signals without the transcription stage.
Multimedia Sound Audio and Speech Processing
Semantics of the Unwritten: The Effect of End of Paragraph and Sequence Tokens on Text Generation with GPT2
Experimental results show that the Chinese GPT2 can generate better essay endings with \eop.
Rectified Meta-Learning from Noisy Labels for Robust Image-based Plant Disease Diagnosis
However, the performance of CNN-based classification approach depends on a large amount of high-quality manually labeled training data, which are inevitably introduced noise on labels in practice, leading to model overfitting and performance degradation.
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.
Knowledge Transfer via Student-Teacher Collaboration
One way to compress these heavy models is knowledge transfer (KT), in which a light student network is trained through absorbing the knowledge from a powerful teacher network.
Global-Local Temporal Representations For Video Person Re-Identification
The long-term relations are captured by a temporal self-attention model to alleviate the occlusions and noises in video sequences.
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.
FedHealth: A Federated Transfer Learning Framework for Wearable Healthcare
It is able to achieve accurate and personalized healthcare without compromising privacy and security.
Single Image Blind Deblurring Using Multi-Scale Latent Structure Prior
Blind image deblurring is a challenging problem in computer vision, which aims to restore both the blur kernel and the latent sharp image from only a blurry observation.
Masked Non-Autoregressive Image Captioning
Existing captioning models often adopt the encoder-decoder architecture, where the decoder uses autoregressive decoding to generate captions, such that each token is generated sequentially given the preceding generated tokens.
Self-critical n-step Training for Image Captioning
Existing methods for image captioning are usually trained by cross entropy loss, which leads to exposure bias and the inconsistency between the optimizing function and evaluation metrics.
Scalable Facial Image Compression with Deep Feature Reconstruction
In this paper, we propose a scalable image compression scheme, including the base layer for feature representation and enhancement layer for texture representation.
Attention Driven Person Re-identification
Person re-identification (ReID) is a challenging task due to arbitrary human pose variations, background clutters, etc.
Computed Tomography Image Enhancement using 3D Convolutional Neural Network
Computed tomography (CT) is increasingly being used for cancer screening, such as early detection of lung cancer.
RAM: A Region-Aware Deep Model for Vehicle Re-Identification
Specifically, in addition to extracting global features, RAM also extracts features from a series of local regions.
Depth-Aware Stereo Video Retargeting
As compared with traditional video retargeting, stereo video retargeting poses new challenges because stereo video contains the depth information of salient objects and its time dynamics.
Graph-Based Blind Image Deblurring From a Single Photograph
We leverage the new graph spectral interpretation for RGTV to design an efficient algorithm that solves for the skeleton image and the blur kernel alternately.
Blind Image Deblurring via Reweighted Graph Total Variation
The problem can be solved in two parts: i) estimate a blur kernel from the blurry image, and ii) given estimated blur kernel, de-convolve blurry input to restore the target image.
LVreID: Person Re-Identification with Long Sequence Videos
This paper mainly establishes a large-scale Long sequence Video database for person re-IDentification (LVreID).
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.
Person Transfer GAN to Bridge Domain Gap for Person Re-Identification
Although the performance of person Re-Identification (ReID) has been significantly boosted, many challenging issues in real scenarios have not been fully investigated, e. g., the complex scenes and lighting variations, viewpoint and pose changes, and the large number of identities in a camera network.
Ranked #11 on
Unsupervised Person Re-Identification
on DukeMTMC-reID
(Rank-10 metric)
A Bio-Inspired Multi-Exposure Fusion Framework for Low-light Image Enhancement
Inspired by human visual system, we design a multi-exposure fusion framework for low-light image enhancement.
Pose-driven Deep Convolutional Model for Person Re-identification
Our deep architecture explicitly leverages the human part cues to alleviate the pose variations and learn robust feature representations from both the global image and different local parts.
Ranked #105 on
Person Re-Identification
on Market-1501
GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval
Targeting to solve these problems, this work proposes a Global-Local-Alignment Descriptor (GLAD) and an efficient indexing and retrieval framework, respectively.
Ranked #92 on
Person Re-Identification
on Market-1501
Performance Guaranteed Network Acceleration via High-Order Residual Quantization
Input binarization has shown to be an effective way for network acceleration.
Beyond Monte Carlo Tree Search: Playing Go with Deep Alternative Neural Network and Long-Term Evaluation
We show such setting can preserve more contexts of local features and its evolutions which are beneficial for move prediction.
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).
Learning a collaborative multiscale dictionary based on robust empirical mode decomposition
The multiscale dictionary is considered as the product of oscillating dictionary and tolerance dictionary.
Local Patch Encoding-Based Method for Single Image Super-Resolution
The proposed method consists of a learning stage and a reconstructing stage.
Correlation Preserving Sparse Coding Over Multi-level Dictionaries for Image Denoising
In this letter, we propose a novel image denoising method based on correlation preserving sparse coding.
Blind restoration for non-uniform aerial images using non-local Retinex model and shearlet-based higher-order regularization
Aerial images are often degraded by space-varying motion blur and simultaneous uneven illumination.
An Attention-Driven Approach of No-Reference Image Quality Assessment
The model learning is implemented by a reinforcement strategy, in which the rewards of both tasks guide the learning of the optimal sampling policy to acquire the "task-informative" image regions so that the predictions can be made accurately and efficiently (in terms of the sampling steps).
Deep Alternative Neural Network: Exploring Contexts as Early as Possible for Action Recognition
This paper instead explores contexts as early as possible and leverages their evolutions for action recognition.
Globally Variance-Constrained Sparse Representation and Its Application in Image Set Coding
Therefore, introducing an accurate rate-constraint in sparse coding and dictionary learning becomes meaningful, which has not been fully exploited in the context of sparse representation.
Deep Attributes Driven Multi-Camera Person Re-identification
And we propose a semi-supervised attribute learning framework which progressively boosts the accuracy of attributes only using a limited number of labeled data.
Maximal Sparsity with Deep Networks?
The iterations of many sparse estimation algorithms are comprised of a fixed linear filter cascaded with a thresholding nonlinearity, which collectively resemble a typical neural network layer.
Multi-Task Learning With Low Rank Attribute Embedding for Person Re-Identification
Since attributes are generally correlated, we introduce a low rank attribute embedding into the MTL formulation to embed original binary attributes to a continuous attribute space, where incorrect and incomplete attributes are rectified and recovered to better describe people.
Cross-pose Face Recognition by Canonical Correlation Analysis
We argue that one of the diffculties in this problem is the severe misalignment in face images or feature vectors with different poses.
Image Denoising via Adaptive Soft-Thresholding Based on Non-Local Samples
To estimate the expectation and variance parameters for the transform bands of a particular patch, we exploit the non-local correlation of image and collect a set of similar patches as data samples to form the distribution.
Background Subtraction via Generalized Fused Lasso Foreground Modeling
Background Subtraction (BS) is one of the key steps in video analysis.
Stable Feature Selection from Brain sMRI
Neuroimage analysis usually involves learning thousands or even millions of variables using only a limited number of samples.
Robust Estimation of 3D Human Poses from a Single Image
We address the challenges in three ways: (i) We represent a 3D pose as a linear combination of a sparse set of bases learned from 3D human skeletons.
Ranked #29 on
3D Human Pose Estimation
on HumanEva-I
Group-based Sparse Representation for Image Restoration
In this paper, instead of using patch as the basic unit of sparse representation, we exploit the concept of group as the basic unit of sparse representation, which is composed of nonlocal patches with similar structures, and establish a novel sparse representation modeling of natural images, called group-based sparse representation (GSR).
Image Restoration Using Joint Statistical Modeling in Space-Transform Domain
This paper presents a novel strategy for high-fidelity image restoration by characterizing both local smoothness and nonlocal self-similarity of natural images in a unified statistical manner.
Image Compressive Sensing Recovery Using Adaptively Learned Sparsifying Basis via L0 Minimization
From many fewer acquired measurements than suggested by the Nyquist sampling theory, compressive sensing (CS) theory demonstrates that, a signal can be reconstructed with high probability when it exhibits sparsity in some domain.
Structural Group Sparse Representation for Image Compressive Sensing Recovery
Compressive Sensing (CS) theory shows that a signal can be decoded from many fewer measurements than suggested by the Nyquist sampling theory, when the signal is sparse in some domain.
