Search Results for author:
Found 137 papers, 54 papers with code
Face Alignment In-the-Wild: A Survey
Over the last two decades, face alignment or localizing fiducial facial points has received increasing attention owing to its comprehensive applications in automatic face analysis.
ILGNet: Inception Modules with Connected Local and Global Features for Efficient Image Aesthetic Quality Classification using Domain Adaptation
Thus, it is easy to use a pre-trained GoogLeNet for large-scale image classification problem and fine tune our connected layers on an large scale database of aesthetic related images: AVA, i. e. \emph{domain adaptation}.
Efficient Privacy Preserving Viola-Jones Type Object Detection via Random Base Image Representation
Only the base images are submitted randomly to the cloud server.
Privacy Preserving Face Retrieval in the Cloud for Mobile Users
The experimental results reveal that our protocol can successfully retrieve the proper photos from the cloud server and protect the user photos and the face detector.
Single Reference Image based Scene Relighting via Material Guided Filtering
We propose a novel outdoor scene relighting method, which needs only a single reference image and is based on material constrained layer decomposition.
Predicting Aesthetic Score Distribution through Cumulative Jensen-Shannon Divergence
Thus, a novel CNN based on the Cumulative distribution with Jensen-Shannon divergence (CJS-CNN) is presented to predict the aesthetic score distribution of human ratings, with a new reliability-sensitive learning method based on the kurtosis of the score distribution, which eliminates the requirement of the original full data of human ratings (without normalization).
Multi-level Chaotic Maps for 3D Textured Model Encryption
In this work, a multi-level chaotic maps models for 3D textured encryption was presented by observing the different contributions for recognizing cipher 3D models between vertices (point cloud), polygons and textures.
Learning for Video Compression
One key challenge to learning-based video compression is that motion predictive coding, a very effective tool for video compression, can hardly be trained into a neural network.
Multimedia Image and Video Processing
Unsupervised Learnable Sinogram Inpainting Network (SIN) for Limited Angle CT reconstruction
In this paper, we propose a sinogram inpainting network (SIN) to solve limited-angle CT reconstruction problem, which is a very challenging ill-posed issue and of great interest for several clinical applications.
Medical Physics Image and Video Processing
Unsupervised Single Image Deraining with Self-supervised Constraints
Most existing single image deraining methods require learning supervised models from a large set of paired synthetic training data, which limits their generality, scalability and practicality in real-world multimedia applications.
Flash: Efficient Dynamic Routing for Offchain Networks
Mice payments are directly sent by looking up a routing table with a few precomputed paths to reduce probing overhead.
Networking and Internet Architecture
Neural Packet Classification
First, many of the existing solutions are iteratively building a decision tree by splitting nodes in the tree.
Relation-Aware Global Attention for Person Re-identification
For person re-identification (re-id), attention mechanisms have become attractive as they aim at strengthening discriminative features and suppressing irrelevant ones, which matches well the key of re-id, i. e., discriminative feature learning.
CaseNet: Content-Adaptive Scale Interaction Networks for Scene Parsing
We achieve this by the context interaction among the features of different scales.
Harmonia: Near-Linear Scalability for Replicated Storage with In-Network Conflict Detection
Experimental results show that Harmonia improves the throughput of these protocols by up to 10X for a replication factor of 10, providing near-linear scalability up to the limit of our testbed.
Distributed, Parallel, and Cluster Computing
Semantics-Aligned Representation Learning for Person Re-identification
Specifically, we build a Semantics Aligning Network (SAN) which consists of a base network as encoder (SA-Enc) for re-ID, and a decoder (SA-Dec) for reconstructing/regressing the densely semantics aligned full texture image.
A Survey and Experimental Analysis of Distributed Subgraph Matching
We conduct extensive experiments for both unlabelled matching and labelled matching to analyze the performance of distributed subgraph matching under various settings, which is finally summarized as a practical guide.
Databases
Facial Makeup Transfer Combining Illumination Transfer
To meet the women appearance needs, we present a novel virtual experience approach of facial makeup transfer, developed into windows platform application software.
Aesthetic Attributes Assessment of Images
This is a new formula of image aesthetic assessment, which predicts aesthetic attributes captions together with the aesthetic score of each attribute.
Region Normalization for Image Inpainting
In this work, we show that the mean and variance shifts caused by full-spatial FN limit the image inpainting network training and we propose a spatial region-wise normalization named Region Normalization (RN) to overcome the limitation.
Uncertainty-Aware Multi-Shot Knowledge Distillation for Image-Based Object Re-Identification
To the best of our knowledge, we are the first to make use of multi-shots of an object in a teacher-student learning manner for effectively boosting the single image based re-id.
Exploring Categorical Regularization for Domain Adaptive Object Detection
Specifically, by integrating an image-level multi-label classifier upon the detection backbone, we can obtain the sparse but crucial image regions corresponding to categorical information, thanks to the weakly localization ability of the classification manner.
On Construction of the ASR-oriented Indian English Pronunciation Dictionary
An Automatic Speech Recognition (ASR) system simply trained on British English (BE) /American English (AE) speech data and using the BE/AE pronunciation dictionary performs much worse when applied to IE.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Style Normalization and Restitution for Generalizable Person Re-identification
Existing fully-supervised person re-identification (ReID) methods usually suffer from poor generalization capability caused by domain gaps.
Ranked #8 on
Unsupervised Domain Adaptation
on Market to Duke
Global Distance-distributions Separation for Unsupervised Person Re-identification
To address this problem, we introduce a global distance-distributions separation (GDS) constraint over the two distributions to encourage the clear separation of positive and negative samples from a global view.
Is Network the Bottleneck of Distributed Training?
As such, we advocate that the real challenge of distributed training is for the network community to develop high-performance network transport to fully utilize the network capacity and achieve linear scale-out.
Feature Alignment and Restoration for Domain Generalization and Adaptation
To ensure high discrimination, we propose a Feature Restoration (FR) operation to distill task-relevant features from the residual information and use them to compensate for the aligned features.
Ranked #73 on
Domain Generalization
on PACS
Learning Disentangled Feature Representation for Hybrid-distorted Image Restoration
Hybrid-distorted image restoration (HD-IR) is dedicated to restore real distorted image that is degraded by multiple distortions.
Hierarchical Context Embedding for Region-based Object Detection
To address this issue, we present a simple but effective Hierarchical Context Embedding (HCE) framework, which can be applied as a plug-and-play component, to facilitate the classification ability of a series of region-based detectors by mining contextual cues.
AIM 2020 Challenge on Real Image Super-Resolution: Methods and Results
This paper introduces the real image Super-Resolution (SR) challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2020.
On Efficient Constructions of Checkpoints
Efficient construction of checkpoints/snapshots is a critical tool for training and diagnosing deep learning models.
FAN: Frequency Aggregation Network for Real Image Super-resolution
Specifically, we extract different frequencies of the LR image and pass them to a channel attention-grouped residual dense network (CA-GRDB) individually to output corresponding feature maps.
A Deep Drift-Diffusion Model for Image Aesthetic Score Distribution Prediction
In this paper, we propose a Deep Drift-Diffusion (DDD) model inspired by psychologists to predict aesthetic score distribution from images.
Deep Multimodality Learning for UAV Video Aesthetic Quality Assessment
Our model can judge whether a UAV video was shot by professional photographers or amateurs together with the scene type classification.
Learning Omni-frequency Region-adaptive Representations for Real Image Super-Resolution
Traditional single image super-resolution (SISR) methods that focus on solving single and uniform degradation (i. e., bicubic down-sampling), typically suffer from poor performance when applied into real-world low-resolution (LR) images due to the complicated realistic degradations.
Learned Block-based Hybrid Image Compression
Recent works on learned image compression perform encoding and decoding processes in a full-resolution manner, resulting in two problems when deployed for practical applications.
Confused Modulo Projection based Somewhat Homomorphic Encryption -- Cryptosystem, Library and Applications on Secure Smart Cities
To make this algorithm easy to use, we also designed and implemented an efficient general blind computing library based on CMP-SWHE.
Style Normalization and Restitution for Domain Generalization and Adaptation
In this paper, we design a novel Style Normalization and Restitution module (SNR) to simultaneously ensure both high generalization and discrimination capability of the networks.
Dense Interaction Learning for Video-based Person Re-identification
The CNN encoder is responsible for efficiently extracting discriminative spatial features while the DI decoder is designed to densely model spatial-temporal inherent interaction across frames.
Ranked #1 on
Person Re-Identification
on DukeMTMC-reID
Local Patch AutoAugment with Multi-Agent Collaboration
We formulate it as a multi-agent reinforcement learning (MARL) problem, where each agent learns an augmentation policy for each patch based on its content together with the semantics of the whole image.
Re-energizing Domain Discriminator with Sample Relabeling for Adversarial Domain Adaptation
Many unsupervised domain adaptation (UDA) methods exploit domain adversarial training to align the features to reduce domain gap, where a feature extractor is trained to fool a domain discriminator in order to have aligned feature distributions.
Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularization
Specifically, we introduce Gait recognition as an auxiliary task to drive the Image ReID model to learn cloth-agnostic representations by leveraging personal unique and cloth-independent gait information, we name this framework as GI-ReID.
Ranked #5 on
Person Re-Identification
on PRCC
Cloth-Changing Person Re-Identification
Computational Efficiency
+1
Can we imitate the principal investor's behavior to learn option price?
This paper presents a framework of imitating the principal investor's behavior for optimal pricing and hedging options.
Membraneless organelles formed by liquid-liquid phase separation increase bacterial fitness
Liquid-liquid phase separation is emerging as a crucial phenomenon in several fundamental cell processes.
FFR_FD: Effective and Fast Detection of DeepFakes Based on Feature Point Defects
The internet is filled with fake face images and videos synthesized by deep generative models.
Focusing on Persons: Colorizing Old Images Learning from Modern Historical Movies
Classification sub-module supplies classifying of images according to the eras, nationalities and garment types; Parsing sub-network supplies the semantic for person contours, clothing and background in the image to achieve more accurate colorization of clothes and persons and prevent color overflow.
Unleash the Potential of Adaptation Models via Dynamic Domain Labels
In this paper, we propose an embarrassing simple yet highly effective adversarial domain adaptation (ADA) method for effectively training models for alignment.
A HYPOTHESIS FOR THE COGNITIVE DIFFICULTY OF IMAGES
This paper proposes a hypothesis to analyze the underlying reason for the cognitive difficulty of an image from two perspectives, i. e. a cognitive image usually makes a DNN strongly activated by cognitive concepts; discarding massive non-cognitive concepts may also help the DNN focus on cognitive concepts.
MC-LCR: Multi-modal contrastive classification by locally correlated representations for effective face forgery detection
Moreover, we make a key observation that subtle forgery artifacts can be further exposed in the patch-wise phase and amplitude spectrum and exhibit different clues.
Meta Clustering Learning for Large-scale Unsupervised Person Re-identification
Unsupervised Person Re-identification (U-ReID) with pseudo labeling recently reaches a competitive performance compared to fully-supervised ReID methods based on modern clustering algorithms.
A Close Look at Few-shot Real Image Super-resolution from the Distortion Relation Perspective
Under this brand-new scenario, we propose Distortion Relation guided Transfer Learning (DRTL) for the few-shot RealSR by transferring the rich restoration knowledge from auxiliary distortions (i. e., synthetic distortions) to the target RealSR under the guidance of distortion relation.
Confounder Identification-free Causal Visual Feature Learning
In this paper, we propose a novel Confounder Identification-free Causal Visual Feature Learning (CICF) method, which obviates the need for identifying confounders.
Unleashing the Potential of Unsupervised Pre-Training with Intra-Identity Regularization for Person Re-Identification
During the pre-training, we attempt to address two critical issues for learning fine-grained ReID features: (1) the augmentations in CL pipeline may distort the discriminative clues in person images.
The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localization
We introduce the first comprehensive 3D dataset for the task of unsupervised anomaly detection and localization.
3D Anomaly Detection and Segmentation
Depth Anomaly Detection and Segmentation
+4
Learning Cross-Scale Weighted Prediction for Efficient Neural Video Compression
Neural video codecs have demonstrated great potential in video transmission and storage applications.
Unleashing Potential of Unsupervised Pre-Training With Intra-Identity Regularization for Person Re-Identification
During the pre-training, we attempt to address two critical issues for learning fine-grained ReID features: (1) the augmentations in CL pipeline may distort the discriminative clues in person images.
Pseudo-labelling and Meta Reweighting Learning for Image Aesthetic Quality Assessment
In the tasks of image aesthetic quality evaluation, it is difficult to reach both the high score area and low score area due to the normal distribution of aesthetic datasets.
Semantically Video Coding: Instill Static-Dynamic Clues into Structured Bitstream for AI Tasks
Traditional media coding schemes typically encode image/video into a semantic-unknown binary stream, which fails to directly support downstream intelligent tasks at the bitstream level.
SADN: Learned Light Field Image Compression with Spatial-Angular Decorrelation
Light field image becomes one of the most promising media types for immersive video applications.
Robust Event Triggering Control for Lateral Dynamics of Intelligent Vehicles with Designable Inter-event Times
In this brief, an improved event-triggered update mechanism (ETM) for the linear quadratic regulator is proposed to solve the lateral motion control problem of intelligent vehicle under bounded disturbances.
ActFormer: A GAN-based Transformer towards General Action-Conditioned 3D Human Motion Generation
We present a GAN-based Transformer for general action-conditioned 3D human motion generation, including not only single-person actions but also multi-person interactive actions.
Attribute Group Editing for Reliable Few-shot Image Generation
Few-shot image generation is a challenging task even using the state-of-the-art Generative Adversarial Networks (GANs).
Unsupervised Coherent Video Cartoonization with Perceptual Motion Consistency
Furthermore, we devise the spatio-temporal correlative map as a style-independent, global-aware regularization on the perceptual motion consistency.
Reusing the Task-specific Classifier as a Discriminator: Discriminator-free Adversarial Domain Adaptation
Such NWD can be coupled with the classifier to serve as a discriminator satisfying the K-Lipschitz constraint without the requirements of additional weight clipping or gradient penalty strategy.
Ranked #2 on
Domain Adaptation
on ImageCLEF-DA
Edge Security: Challenges and Issues
Edge computing is a paradigm that shifts data processing services to the network edge, where data are generated.
Enhanced Bi-directional Motion Estimation for Video Frame Interpolation
We present a novel simple yet effective algorithm for motion-based video frame interpolation.
Ranked #3 on
Video Frame Interpolation
on MSU Video Frame Interpolation
(LPIPS metric)
Short Video Uprising: How #BlackLivesMatter Content on TikTok Challenges the Protest Paradigm
This study concludes that while short-form video platforms could potentially challenge the protest paradigm on the content creators' side, the audiences' preference as measured by social media visibility might still be moderately associated with the protest paradigm.
A perspective on Attitude Control Issues and Techniques
This paper reviews the attitude control problems for rigid-body systems, starting from the attitude representation for rigid body kinematics.
Aesthetic Attribute Assessment of Images Numerically on Mixed Multi-attribute Datasets
Besides, we propose a efficient method for image aesthetic attribute assessment on mixed multi-attribute dataset and construct a multitasking network architecture by using the EfficientNet-B0 as the backbone network.
Image Coding for Machines with Omnipotent Feature Learning
Learning a kind of feature that is both general (for AI tasks) and compact (for compression) is pivotal for its success.
Learning with Recoverable Forgetting
Life-long learning aims at learning a sequence of tasks without forgetting the previously acquired knowledge.
Aesthetic Language Guidance Generation of Images Using Attribute Comparison
The differences of the three attributes between the input images and the photography templates or the guidance images are described in natural language, which is aesthetic natural language guidance (ALG).
Aesthetic Attributes Assessment of Images with AMANv2 and DPC-CaptionsV2
In this paper, we propose aesthetic attribute assessment, which is the aesthetic attributes captioning, i. e., to assess the aesthetic attributes such as composition, lighting usage and color arrangement.
Attribute Controllable Beautiful Caucasian Face Generation by Aesthetics Driven Reinforcement Learning
In recent years, image generation has made great strides in improving the quality of images, producing high-fidelity ones.
Aesthetic Visual Question Answering of Photographs
In this paper, we propose a new task of aesthetic language assessment: aesthetic visual question and answering (AVQA) of images.
Underwater Ranker: Learn Which Is Better and How to Be Better
To achieve that, we also contribute a dataset, URankerSet, containing sufficient results enhanced by different UIE algorithms and the corresponding perceptual rankings, to train our URanker.
Hierarchical Compositional Representations for Few-shot Action Recognition
Recently action recognition has received more and more attention for its comprehensive and practical applications in intelligent surveillance and human-computer interaction.
Aesthetics Driven Autonomous Time-Lapse Photography Generation by Virtual and Real Robots
Then we propose a time-lapse photography interface to facilitate users to view and adjust parameters and use virtual robots to conduct virtual photography in a three-dimensional scene.
Deliberated Domain Bridging for Domain Adaptive Semantic Segmentation
In this work, we resort to data mixing to establish a deliberated domain bridging (DDB) for DASS, through which the joint distributions of source and target domains are aligned and interacted with each in the intermediate space.
Ranked #1 on
Domain Adaptation
on GTAV+Synscapes to Cityscapes
Rewarding Episodic Visitation Discrepancy for Exploration in Reinforcement Learning
Exploration is critical for deep reinforcement learning in complex environments with high-dimensional observations and sparse rewards.
A Unified Pyramid Recurrent Network for Video Frame Interpolation
Cast in a flexible pyramid framework, UPR-Net exploits lightweight recurrent modules for both bi-directional flow estimation and intermediate frame synthesis.
Ranked #2 on
Video Frame Interpolation
on MSU Video Frame Interpolation
(PSNR metric)
Task Residual for Tuning Vision-Language Models
Large-scale vision-language models (VLMs) pre-trained on billion-level data have learned general visual representations and broad visual concepts.
Tackling Visual Control via Multi-View Exploration Maximization
We present MEM: Multi-view Exploration Maximization for tackling complex visual control tasks.
GAS-NeXt: Few-Shot Cross-Lingual Font Generator
Generating new fonts is a time-consuming and labor-intensive task, especially in a language with a huge amount of characters like Chinese.
Discrete Point-wise Attack Is Not Enough: Generalized Manifold Adversarial Attack for Face Recognition
Classical adversarial attacks for Face Recognition (FR) models typically generate discrete examples for target identity with a single state image.
DNF: Decouple and Feedback Network for Seeing in the Dark
The exclusive properties of RAW data have shown great potential for low-light image enhancement.
An Order-Complexity Model for Aesthetic Quality Assessment of Symbolic Homophony Music Scores
Computational aesthetics evaluation has made great achievements in the field of visual arts, but the research work on music still needs to be explored.
Automatic Intrinsic Reward Shaping for Exploration in Deep Reinforcement Learning
We present AIRS: Automatic Intrinsic Reward Shaping that intelligently and adaptively provides high-quality intrinsic rewards to enhance exploration in reinforcement learning (RL).
Stable Attribute Group Editing for Reliable Few-shot Image Generation
SAGE takes use of all given few-shot images and estimates a class center embedding based on the category-relevant attribute dictionary.
AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving
Model parallelism is conventionally viewed as a method to scale a single large deep learning model beyond the memory limits of a single device.
TBFormer: Two-Branch Transformer for Image Forgery Localization
In this paper, we propose a Transformer-style network with two feature extraction branches for image forgery localization, and it is named as Two-Branch Transformer (TBFormer).
QVRF: A Quantization-error-aware Variable Rate Framework for Learned Image Compression
In this paper, we present a Quantization-error-aware Variable Rate Framework (QVRF) that utilizes a univariate quantization regulator a to achieve wide-range variable rates within a single model.
Learning Distortion Invariant Representation for Image Restoration from A Causality Perspective
In this paper, we are the first to propose a novel training strategy for image restoration from the causality perspective, to improve the generalization ability of DNNs for unknown degradations.
Understand Legal Documents with Contextualized Large Language Models
The growth of pending legal cases in populous countries, such as India, has become a major issue.
Bridging Stereo Geometry and BEV Representation with Reliable Mutual Interaction for Semantic Scene Completion
However, due to the inherent representation gap between stereo geometry and BEV features, it is non-trivial to bridge them for dense prediction task of SSC.
Inpaint Anything: Segment Anything Meets Image Inpainting
We are also very willing to help everyone share and promote new projects based on our Inpaint Anything (IA).
[CLS] Token is All You Need for Zero-Shot Semantic Segmentation
Based on that, we build upon the CLIP model as a backbone which we extend with a One-Way [CLS] token navigation from text to the visual branch that enables zero-shot dense prediction, dubbed \textbf{ClsCLIP}.
NaviNeRF: NeRF-based 3D Representation Disentanglement by Latent Semantic Navigation
They are complementary -- the outer navigation is to identify global-view semantic directions, and the inner refinement dedicates to fine-grained attributes.
An Order-Complexity Model for Aesthetic Quality Assessment of Homophony Music Performance
In order to guide the generation task of AI music performance, and to improve the performance effect of human performers, this paper uses Birkhoff's aesthetic measure to propose a method of objective measurement of beauty.
Dynamic Video Frame Interpolation with integrated Difficulty Pre-Assessment
Extensive experiments show that easy samples pass through fast models while difficult samples inference with heavy models, and our proposed pipeline can improve the accuracy-efficiency trade-off for VFI.
Learned Focused Plenoptic Image Compression with Microimage Preprocessing and Global Attention
Also, it achieves 18. 73% bitrate saving and generates perceptually pleasant reconstructions compared to the state-of-the-art end-to-end image compression methods, which benefits the applications of focused plenoptic cameras greatly.
Semantically Structured Image Compression via Irregular Group-Based Decoupling
Nevertheless, they divide the input image into multiple rectangular regions according to semantics and ignore avoiding information interaction among them, causing waste of bitrate and distorted reconstruction of region boundaries.
Prompt-ICM: A Unified Framework towards Image Coding for Machines with Task-driven Prompts
For ICM, developing a unified codec to reduce information redundancy while empowering the compressed features to support various vision tasks is very important, which inevitably faces two core challenges: 1) How should the compression strategy be adjusted based on the downstream tasks?
Fast Distributed Inference Serving for Large Language Models
Based on the new semi information-agnostic setting of LLM inference, the scheduler leverages the input length information to assign an appropriate initial queue for each arrival job to join.
Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning
Training offline reinforcement learning (RL) models using visual inputs poses two significant challenges, i. e., the overfitting problem in representation learning and the overestimation bias for expected future rewards.
EMoG: Synthesizing Emotive Co-speech 3D Gesture with Diffusion Model
In this paper, we present a novel framework (EMoG) to tackle the above challenges with denoising diffusion models: 1) To alleviate the one-to-many problem, we incorporate emotion clues to guide the generation process, making the generation much easier; 2) To model joint correlation, we propose to decompose the difficult gesture generation into two sub-problems: joint correlation modeling and temporal dynamics modeling.
One at a Time: Progressive Multi-step Volumetric Probability Learning for Reliable 3D Scene Perception
Numerous studies have investigated the pivotal role of reliable 3D volume representation in scene perception tasks, such as multi-view stereo (MVS) and semantic scene completion (SSC).
PPN: Parallel Pointer-based Network for Key Information Extraction with Complex Layouts
Firstly, the layout of existing datasets is relatively fixed and limited in the number of semantic entity categories, creating a significant gap between these datasets and the complex real-world scenarios.
Make Explicit Calibration Implicit: Calibrate Denoiser Instead of the Noise Model
However, these methods are impeded by several critical limitations: a) the explicit calibration process is both labor- and time-intensive, b) challenge exists in transferring denoisers across different camera models, and c) the disparity between synthetic and real noise is exacerbated by digital gain.
Ranked #1 on
Image Denoising
on SID SonyA7S2 x300
Diffusion Models for Image Restoration and Enhancement -- A Comprehensive Survey
Image restoration (IR) has been an indispensable and challenging task in the low-level vision field, which strives to improve the subjective quality of images distorted by various forms of degradation.
Generalized Lightness Adaptation with Channel Selective Normalization
Existing methods typically work well on their trained lightness conditions but perform poorly in unknown ones due to their limited generalization ability.
LLMCad: Fast and Scalable On-device Large Language Model Inference
Currently, the execution of these generative tasks heavily depends on Large Language Models (LLMs).
Oobleck: Resilient Distributed Training of Large Models Using Pipeline Templates
Oobleck enables resilient distributed training of large DNN models with guaranteed fault tolerance.
RLLTE: Long-Term Evolution Project of Reinforcement Learning
We present RLLTE: a long-term evolution, extremely modular, and open-source framework for reinforcement learning (RL) research and application.
Breathing Life into Faces: Speech-driven 3D Facial Animation with Natural Head Pose and Detailed Shape
To augment the richness of 3D facial animation, we construct a new 3D dataset with detailed shapes and learn to synthesize facial details in line with speech content.
Predicting Scores of Various Aesthetic Attribute Sets by Learning from Overall Score Labels
Then, we define an aesthetic attribute contribution to describe the role of aesthetic attributes throughout an image and use it with the attribute scores and the overall scores to train our F2S model.
TMID: A Comprehensive Real-world Dataset for Trademark Infringement Detection in E-Commerce
Annually, e-commerce platforms incur substantial financial losses due to trademark infringements, making it crucial to identify and mitigate potential legal risks tied to merchant information registered to the platforms.
DTA: Distribution Transform-based Attack for Query-Limited Scenario
In generating adversarial examples, the conventional black-box attack methods rely on sufficient feedback from the to-be-attacked models by repeatedly querying until the attack is successful, which usually results in thousands of trials during an attack.
Binary Code Summarization: Benchmarking ChatGPT/GPT-4 and Other Large Language Models
Binary code summarization, while invaluable for understanding code semantics, is challenging due to its labor-intensive nature.
Adversarial AutoMixup
In this paper, we propose AdAutomixup, an adversarial automatic mixup augmentation approach that generates challenging samples to train a robust classifier for image classification, by alternatively optimizing the classifier and the mixup sample generator.
Prometheus: Infrastructure Security Posture Analysis with AI-generated Attack Graphs
In this paper, we propose Prometheus, an advanced system designed to provide a detailed analysis of the security posture of computing infrastructures.
Inter-X: Towards Versatile Human-Human Interaction Analysis
We also equip Inter-X with versatile annotations of more than 34K fine-grained human part-level textual descriptions, semantic interaction categories, interaction order, and the relationship and personality of the subjects.
Multi-Prompts Learning with Cross-Modal Alignment for Attribute-based Person Re-Identification
Thereby, this paper explores the potential of using the generated multiple person attributes as prompts in ReID tasks with off-the-shelf (large) models for more accurate retrieval results.
EmMixformer: Mix transformer for eye movement recognition
To this end, we propose a mixed block consisting of three modules, transformer, attention Long short-term memory (attention LSTM), and Fourier transformer.
A Survey of Resource-efficient LLM and Multimodal Foundation Models
Large foundation models, including large language models (LLMs), vision transformers (ViTs), diffusion, and LLM-based multimodal models, are revolutionizing the entire machine learning lifecycle, from training to deployment.
Decentralized Zeno-Free Event-Triggered Control For Multiple Networks Subject to Stochastic Network Delays and Poisson Pulsing Attacks
By designing the decentralized time-regularized (Zeno-free) event-triggered strategies for the state-feedback control law, this paper considers the stochastic stabilization of a class of networked control systems, where two sources of randomness exist in multiple decentralized networks that operate asynchronously and independently: the communication channels are constrained by the stochastic network delays and also by Poisson pulsing denial-of-service (Pp-DoS) attacks.
Closed-Loop Unsupervised Representation Disentanglement with $β$-VAE Distillation and Diffusion Probabilistic Feedback
Representation disentanglement may help AI fundamentally understand the real world and thus benefit both discrimination and generation tasks.
An Order-Complexity Aesthetic Assessment Model for Aesthetic-aware Music Recommendation
In order to improve the quality of AI music generation and further guide computer music production, synthesis, recommendation and other tasks, we use Birkhoff's aesthetic measure to design a aesthetic model, objectively measuring the aesthetic beauty of music, and form a recommendation list according to the aesthetic feeling of music.
Large Language Models for Forecasting and Anomaly Detection: A Systematic Literature Review
This systematic literature review comprehensively examines the application of Large Language Models (LLMs) in forecasting and anomaly detection, highlighting the current state of research, inherent challenges, and prospective future directions.
MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs
Training LLMs at this scale brings unprecedented challenges to training efficiency and stability.
2023 Low-Power Computer Vision Challenge (LPCVC) Summary
This article describes the 2023 IEEE Low-Power Computer Vision Challenge (LPCVC).
ReGenNet: Towards Human Action-Reaction Synthesis
Humans constantly interact with their surrounding environments.
DreamLIP: Language-Image Pre-training with Long Captions
Motivated by this, we propose to dynamically sample sub-captions from the text label to construct multiple positive pairs, and introduce a grouping loss to match the embeddings of each sub-caption with its corresponding local image patches in a self-supervised manner.
LoongServe: Efficiently Serving Long-context Large Language Models with Elastic Sequence Parallelism
The context window of large language models (LLMs) is rapidly increasing, leading to a huge variance in resource usage between different requests as well as between different phases of the same request.
RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation
We implement RAGCache and evaluate it on vLLM, a state-of-the-art LLM inference system and Faiss, a state-of-the-art vector database.
Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
We introduce phi-3-mini, a 3. 8 billion parameter language model trained on 3. 3 trillion tokens, whose overall performance, as measured by both academic benchmarks and internal testing, rivals that of models such as Mixtral 8x7B and GPT-3. 5 (e. g., phi-3-mini achieves 69% on MMLU and 8. 38 on MT-bench), despite being small enough to be deployed on a phone.
A Reconfigurable Subarray Architecture and Hybrid Beamforming for Millimeter-Wave Dual-Function-Radar-Communication Systems
Dual-function-radar-communication (DFRC) is a promising candidate technology for next-generation networks.
