Search Results for author:
Found 368 papers, 157 papers with code
Knowledge Distillation for Detection Transformer with Consistent Distillation Points Sampling
In this paper, we focus on the compression of DETR with knowledge distillation.
Vector-quantized Image Modeling with Improved VQGAN
Motivated by this success, we explore a Vector-quantized Image Modeling (VIM) approach that involves pretraining a Transformer to predict rasterized image tokens autoregressively.
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.
Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding
Large Vision-Language Models (LVLMs) have advanced considerably, intertwining visual recognition and language understanding to generate content that is not only coherent but also contextually attuned.
Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfer
Inspired by the common painting process of drawing a draft and revising the details, we introduce a novel feed-forward method named Laplacian Pyramid Network (LapStyle).
Deep Concept-wise Temporal Convolutional Networks for Action Localization
In this paper, we empirically find that stacking more conventional temporal convolution layers actually deteriorates action classification performance, possibly ascribing to that all channels of 1D feature map, which generally are highly abstract and can be regarded as latent concepts, are excessively recombined in temporal convolution.
BMN: Boundary-Matching Network for Temporal Action Proposal Generation
To address these difficulties, we introduce the Boundary-Matching (BM) mechanism to evaluate confidence scores of densely distributed proposals, which denote a proposal as a matching pair of starting and ending boundaries and combine all densely distributed BM pairs into the BM confidence map.
Ranked #1 on
Action Recognition
on THUMOS’14
Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding
We present Video-LLaMA a multi-modal framework that empowers Large Language Models (LLMs) with the capability of understanding both visual and auditory content in the video.
Ranked #7 on
Video Question Answering
on MVBench
AIM 2022 Challenge on Super-Resolution of Compressed Image and Video: Dataset, Methods and Results
The homepage of this challenge is at https://github. com/RenYang-home/AIM22_CompressSR.
Scaling Autoregressive Models for Content-Rich Text-to-Image Generation
We present the Pathways Autoregressive Text-to-Image (Parti) model, which generates high-fidelity photorealistic images and supports content-rich synthesis involving complex compositions and world knowledge.
Ranked #1 on
Text-to-Image Generation
on LAION COCO
Paint Transformer: Feed Forward Neural Painting with Stroke Prediction
Neural painting refers to the procedure of producing a series of strokes for a given image and non-photo-realistically recreating it using neural networks.
Ranked #1 on
Object Detection
on A2D
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.
Exploiting BERT for End-to-End Aspect-based Sentiment Analysis
In this paper, we investigate the modeling power of contextualized embeddings from pre-trained language models, e. g. BERT, on the E2E-ABSA task.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+1
Drive Like a Human: Rethinking Autonomous Driving with Large Language Models
In this paper, we explore the potential of using a large language model (LLM) to understand the driving environment in a human-like manner and analyze its ability to reason, interpret, and memorize when facing complex scenarios.
DiLu: A Knowledge-Driven Approach to Autonomous Driving with Large Language Models
Recent advancements in autonomous driving have relied on data-driven approaches, which are widely adopted but face challenges including dataset bias, overfitting, and uninterpretability.
Towards Knowledge-driven Autonomous Driving
This paper explores the emerging knowledge-driven autonomous driving technologies.
UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebase
Besides, we construct the OpenPCSeg codebase, which is the largest and most comprehensive outdoor LiDAR segmentation codebase.
Ranked #2 on
3D Semantic Segmentation
on SemanticKITTI
(using extra training data)
DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Clouds
Extensive experiments on Waymo Open Dataset show our DetZero outperforms all state-of-the-art onboard and offboard 3D detection methods.
Robo3D: Towards Robust and Reliable 3D Perception against Corruptions
The robustness of 3D perception systems under natural corruptions from environments and sensors is pivotal for safety-critical applications.
A Unified Model for Opinion Target Extraction and Target Sentiment Prediction
Target-based sentiment analysis involves opinion target extraction and target sentiment classification.
Aspect-Based Sentiment Analysis (ABSA)
Sentiment Classification
On the Road with GPT-4V(ision): Early Explorations of Visual-Language Model on Autonomous Driving
This has been a significant bottleneck, particularly in the development of common sense reasoning and nuanced scene understanding necessary for safe and reliable autonomous driving.
Virtual Sparse Convolution for Multimodal 3D Object Detection
Finally, we develop a semi-supervised pipeline VirConv-S based on a pseudo-label framework.
AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer
Finally, the content feature is normalized so that they demonstrate the same local feature statistics as the calculated per-point weighted style feature statistics.
GRIP++: Enhanced Graph-based Interaction-aware Trajectory Prediction for Autonomous Driving
Despite the advancement in the technology of autonomous driving cars, the safety of a self-driving car is still a challenging problem that has not been well studied.
GRIP: Graph-based Interaction-aware Trajectory Prediction
The prediction error of GRIP is one meter shorter than existing schemes.
Multi-View Partial (MVP) Point Cloud Challenge 2021 on Completion and Registration: Methods and Results
Based on the MVP dataset, this paper reports methods and results in the Multi-View Partial Point Cloud Challenge 2021 on Completion and Registration.
SMILEtrack: SiMIlarity LEarning for Occlusion-Aware Multiple Object Tracking
Second, we develop a Similarity Matching Cascade (SMC) module with a novel GATE function for robust object matching across consecutive video frames, further enhancing MOT performance.
Ranked #1 on
Multi-Object Tracking
on MOT20
(using extra training data)
Partial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture Search
It prunes the architecture search space with a partial order assumption to automatically search for the architectures with the best speed and accuracy trade-off.
Transformation Networks for Target-Oriented Sentiment Classification
Between the two layers, we propose a component to generate target-specific representations of words in the sentence, meanwhile incorporate a mechanism for preserving the original contextual information from the RNN layer.
Ranked #19 on
Aspect-Based Sentiment Analysis (ABSA)
on SemEval-2014 Task-4
(Laptop (Acc) metric)
scCDCG: Efficient Deep Structural Clustering for single-cell RNA-seq via Deep Cut-informed Graph Embedding
Addressing these limitations, we introduce scCDCG (single-cell RNA-seq Clustering via Deep Cut-informed Graph), a novel framework designed for efficient and accurate clustering of scRNA-seq data that simultaneously utilizes intercellular high-order structural information.
RF-Net: An End-to-End Image Matching Network based on Receptive Field
This paper proposes a new end-to-end trainable matching network based on receptive field, RF-Net, to compute sparse correspondence between images.
NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results
The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29. 00dB on DIV2K validation set.
LSOTB-TIR:A Large-Scale High-Diversity Thermal Infrared Object Tracking Benchmark
We evaluate and analyze more than 30 trackers on LSOTB-TIR to provide a series of baselines, and the results show that deep trackers achieve promising performance.
Thermal Infrared Object Tracking
Vocal Bursts Intensity Prediction
nnMobileNet: Rethinking CNN for Retinopathy Research
Over the past few decades, convolutional neural networks (CNNs) have been at the forefront of the detection and tracking of various retinal diseases (RD).
SeaLLMs -- Large Language Models for Southeast Asia
Despite the remarkable achievements of large language models (LLMs) in various tasks, there remains a linguistic bias that favors high-resource languages, such as English, often at the expense of low-resource and regional languages.
VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows
Different from visible cameras which record intensity images frame by frame, the biologically inspired event camera produces a stream of asynchronous and sparse events with much lower latency.
Ranked #1 on
Object Tracking
on VisEvent
Micron-BERT: BERT-based Facial Micro-Expression Recognition
By incorporating these components into an end-to-end deep network, the proposed $\mu$-BERT significantly outperforms all previous work in various micro-expression tasks.
Ranked #1 on
Micro Expression Recognition
on SMIC
Micro Expression Recognition
Micro-Expression Recognition
+1
A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challenges
More specifically, we provide a new taxonomy for ABSA which organizes existing studies from the axes of concerned sentiment elements, with an emphasis on recent advances of compound ABSA tasks.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
Video Object Segmentation with Adaptive Feature Bank and Uncertain-Region Refinement
We also design a new confidence loss and a fine-grained segmentation module to enhance the segmentation accuracy in uncertain regions.
Ranked #2 on
Semi-Supervised Video Object Segmentation
on Long Video Dataset (3X)
(using extra training data)
Towards Generative Aspect-Based Sentiment Analysis
Aspect-based sentiment analysis (ABSA) has received increasing attention recently.
Ranked #4 on
Aspect Sentiment Triplet Extraction
on ASTE-Data-V2
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+2
SCPNet: Semantic Scene Completion on Point Cloud
We propose a simple yet effective label rectification strategy, which uses off-the-shelf panoptic segmentation labels to remove the traces of dynamic objects in completion labels, greatly improving the performance of deep models especially for those moving objects.
Ranked #1 on
3D Semantic Scene Completion
on SemanticKITTI
Aspect Sentiment Quad Prediction as Paraphrase Generation
Aspect-based sentiment analysis (ABSA) has been extensively studied in recent years, which typically involves four fundamental sentiment elements, including the aspect category, aspect term, opinion term, and sentiment polarity.
Ranked #3 on
Aspect-Based Sentiment Analysis (ABSA)
on TASD
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+2
NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Results
This paper reviews the first NTIRE challenge on quality enhancement of compressed video, with a focus on the proposed methods and results.
PTB-TIR: A Thermal Infrared Pedestrian Tracking Benchmark
The ability to evaluate the TIR pedestrian tracker fairly, on a benchmark dataset, is significant for the development of this field.
Transferable End-to-End Aspect-based Sentiment Analysis with Selective Adversarial Learning
Joint extraction of aspects and sentiments can be effectively formulated as a sequence labeling problem.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+1
CLEX: Continuous Length Extrapolation for Large Language Models
We generalise the PE scaling approaches to model the continuous dynamics by ordinary differential equations over the length scaling factor, thereby overcoming the constraints of current PE scaling methods designed for specific lengths.
Deep Models with Fusion Strategies for MVP Point Cloud Registration
The main goal of point cloud registration in Multi-View Partial (MVP) Challenge 2021 is to estimate a rigid transformation to align a point cloud pair.
Constraining Depth Map Geometry for Multi-View Stereo: A Dual-Depth Approach with Saddle-shaped Depth Cells
Learning-based multi-view stereo (MVS) methods deal with predicting accurate depth maps to achieve an accurate and complete 3D representation.
GraphAdapter: Tuning Vision-Language Models With Dual Knowledge Graph
To mitigate that, we propose an effective adapter-style tuning strategy, dubbed GraphAdapter, which performs the textual adapter by explicitly modeling the dual-modality structure knowledge (i. e., the correlation of different semantics/classes in textual and visual modalities) with a dual knowledge graph.
Aspect Term Extraction with History Attention and Selective Transformation
Aspect Term Extraction (ATE), a key sub-task in Aspect-Based Sentiment Analysis, aims to extract explicit aspect expressions from online user reviews.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+2
Neural Color Operators for Sequential Image Retouching
The neural color operator mimics the behavior of traditional color operators and learns pixelwise color transformation while its strength is controlled by a scalar.
Image Inpainting by End-to-End Cascaded Refinement with Mask Awareness
Inpainting arbitrary missing regions is challenging because learning valid features for various masked regions is nontrivial.
Ranked #4 on
Image Inpainting
on CelebA-HQ
Learning Semantic Person Image Generation by Region-Adaptive Normalization
In the first stage, we predict the target semantic parsing maps to eliminate the difficulties of pose transfer and further benefit the latter translation of per-region appearance style.
JigsawNet: Shredded Image Reassembly using Convolutional Neural Network and Loop-based Composition
Existing reassembly pipelines commonly consist of a local matching stage and a global compositions stage.
Pyramid Mask Text Detector
Scene text detection, an essential step of scene text recognition system, is to locate text instances in natural scene images automatically.
Ranked #1 on
Scene Text Detection
on ICDAR 2017 MLT
NM-Net: Mining Reliable Neighbors for Robust Feature Correspondences
Feature correspondence selection is pivotal to many feature-matching based tasks in computer vision.
Image-to-Image Translation with Deep Reinforcement Learning
The key feature in the RL-I2IT framework is to decompose a monolithic learning process into small steps with a lightweight model to progressively transform a source image successively to a target image.
Exploiting Coarse-to-Fine Task Transfer for Aspect-level Sentiment Classification
Aspect-level sentiment classification (ASC) aims at identifying sentiment polarities towards aspects in a sentence, where the aspect can behave as a general Aspect Category (AC) or a specific Aspect Term (AT).
MGeo: Multi-Modal Geographic Pre-Training Method
Single-modal PTMs can barely make use of the important GC and therefore have limited performance.
Cascade Graph Neural Networks for RGB-D Salient Object Detection
Current works either simply distill prior knowledge from the corresponding depth map for handling the RGB-image or blindly fuse color and geometric information to generate the coarse depth-aware representations, hindering the performance of RGB-D saliency detectors. In this work, we introduceCascade Graph Neural Networks(Cas-Gnn), a unified framework which is capable of comprehensively distilling and reasoning the mutual benefits between these two data sources through a set of cascade graphs, to learn powerful representations for RGB-D salient object detection.
Ranked #5 on
RGB-D Salient Object Detection
on NJU2K
Mutual Graph Learning for Camouflaged Object Detection
Automatically detecting/segmenting object(s) that blend in with their surroundings is difficult for current models.
MELM: Data Augmentation with Masked Entity Language Modeling for Low-Resource NER
Data augmentation is an effective solution to data scarcity in low-resource scenarios.
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.
MixNet: Toward Accurate Detection of Challenging Scene Text in the Wild
Detecting small scene text instances in the wild is particularly challenging, where the influence of irregular positions and nonideal lighting often leads to detection errors.
Ranked #1 on
Scene Text Detection
on SCUT-CTW1500
SeD: Semantic-Aware Discriminator for Image Super-Resolution
In particular, one discriminator is utilized to enable the SR network to learn the distribution of real-world high-quality images in an adversarial training manner.
Saliency-Associated Object Tracking
A potential limitation of such trackers is that not all patches are equally informative for tracking.
Learning Optical Flow with Adaptive Graph Reasoning
Our key idea is to decouple the context reasoning from the matching procedure, and exploit scene information to effectively assist motion estimation by learning to reason over the adaptive graph.
Learning Optical Flow With Kernel Patch Attention
Optical flow is a fundamental method used for quantitative motion estimation on the image plane.
Multi-Task Driven Feature Models for Thermal Infrared Tracking
These two feature models are learned using a multi-task matching framework and are jointly optimized on the TIR tracking task.
GAFlow: Incorporating Gaussian Attention into Optical Flow
Moreover, for reliable motion analysis, we provide a new Gaussian-Guided Attention Module (GGAM) which not only inherits properties from Gaussian distribution to instinctively revolve around the neighbor fields of each point but also is empowered to put the emphasis on contextually related regions during matching.
Detecting Multimedia Generated by Large AI Models: A Survey
The rapid advancement of Large AI Models (LAIMs), particularly diffusion models and large language models, has marked a new era where AI-generated multimedia is increasingly integrated into various aspects of daily life.
LMR: A Large-Scale Multi-Reference Dataset for Reference-based Super-Resolution
To this end, we construct a large-scale, multi-reference super-resolution dataset, named LMR.
Horizontally Fused Training Array: An Effective Hardware Utilization Squeezer for Training Novel Deep Learning Models
Driven by the tremendous effort in researching novel deep learning (DL) algorithms, the training cost of developing new models increases staggeringly in recent years.
DDGCN: A Dynamic Directed Graph Convolutional Network for Action Recognition
We propose a Dynamic Directed Graph Convolutional Network (DDGCN) to model spatial and temporal features of human actions from their skeletal representations.
CiteTracker: Correlating Image and Text for Visual Tracking
Existing visual tracking methods typically take an image patch as the reference of the target to perform tracking.
Zero-1-to-3: Domain-level Zero-shot Cognitive Diagnosis via One Batch of Early-bird Students towards Three Diagnostic Objectives
Consequently, we refine the cognitive states of cold-start students as diagnostic outcomes via virtual data, aligning with the diagnosis-oriented goal.
Uncertainty-Guided Transformer Reasoning for Camouflaged Object Detection
Spotting objects that are visually adapted to their surroundings is challenging for both humans and AI.
KVQ: Kwai Video Quality Assessment for Short-form Videos
Short-form UGC video platforms, like Kwai and TikTok, have been an emerging and irreplaceable mainstream media form, thriving on user-friendly engagement, and kaleidoscope creation, etc.
NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Results
This paper reviews the NTIRE 2024 Challenge on Shortform UGC Video Quality Assessment (S-UGC VQA), where various excellent solutions are submitted and evaluated on the collected dataset KVQ from popular short-form video platform, i. e., Kuaishou/Kwai Platform.
NomMer: Nominate Synergistic Context in Vision Transformer for Visual Recognition
For the sake of trade-off between efficiency and performance, a group of works merely perform SA operation within local patches, whereas the global contextual information is abandoned, which would be indispensable for visual recognition tasks.
CoIn: Contrastive Instance Feature Mining for Outdoor 3D Object Detection with Very Limited Annotations
Combining CoIn with an iterative training strategy, we propose a CoIn++ pipeline, which requires only 2% annotations in the KITTI dataset to achieve performance comparable to the fully supervised methods.
DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition
Various 3D-CNN based methods have been presented to tackle both the spatial and temporal dimensions in the task of video action recognition with competitive results.
Ranked #1 on
Action Recognition
on Jester (Gesture Recognition)
Low-Light Image Enhancement with Multi-Stage Residue Quantization and Brightness-Aware Attention
Deep learning-based LLIE methods focus on learning a mapping function between low-light images and normal-light images that outperforms conventional LLIE methods.
Contour Knowledge Transfer for Salient Object Detection
Our goal is to overcome this limitation by automatically converting an existing deep contour detection model into a salient object detection model without using any manual salient object masks.
COVID-MobileXpert: On-Device COVID-19 Patient Triage and Follow-up using Chest X-rays
We design and implement a novel three-player knowledge transfer and distillation (KTD) framework including a pre-trained attending physician (AP) network that extracts CXR imaging features from a large scale of lung disease CXR images, a fine-tuned resident fellow (RF) network that learns the essential CXR imaging features to discriminate COVID-19 from pneumonia and/or normal cases with a small amount of COVID-19 cases, and a trained lightweight medical student (MS) network to perform on-device COVID-19 patient triage and follow-up.
Fast Full-frame Video Stabilization with Iterative Optimization
Video stabilization refers to the problem of transforming a shaky video into a visually pleasing one.
Unsupervised Learning of Accurate Siamese Tracking
As unlimited self-supervision signals can be obtained by tracking a video along a cycle in time, we investigate evolving a Siamese tracker by tracking videos forward-backward.
SiamCorners: Siamese Corner Networks for Visual Tracking
By tracking a target as a pair of corners, we avoid the need to design the anchor boxes.
Improving Fine-grained Entity Typing with Entity Linking
Fine-grained entity typing is a challenging problem since it usually involves a relatively large tag set and may require to understand the context of the entity mention.
Face Beautification: Beyond Makeup Transfer
Inspired by the latest advances in style-based synthesis and face beauty prediction, we propose a novel framework of face beautification.
A Chinese Corpus for Fine-grained Entity Typing
In this paper, we introduce a corpus for Chinese fine-grained entity typing that contains 4, 800 mentions manually labeled through crowdsourcing.
Model Attribution of Face-swap Deepfake Videos
Then we take Deepfakes model attribution as a multiclass classification task and propose a spatial and temporal attention based method to explore the differences among Deepfakes in the new dataset.
Hierarchical Spatial-aware Siamese Network for Thermal Infrared Object Tracking
In this paper, we cast the TIR tracking problem as a similarity verification task, which is coupled well to the objective of the tracking task.
An Informative Tracking Benchmark
Along with the rapid progress of visual tracking, existing benchmarks become less informative due to redundancy of samples and weak discrimination between current trackers, making evaluations on all datasets extremely time-consuming.
Neuro-Symbolic Integration Brings Causal and Reliable Reasoning Proofs
Though prompting LLMs with various reasoning structures produces reasoning proofs along with answers, these proofs are not ensured to be causal and reliable due to the inherent defects of LLMs.
MHSA-Net: Multi-Head Self-Attention Network for Occluded Person Re-Identification
This paper presents a novel person re-identification model, named Multi-Head Self-Attention Network (MHSA-Net), to prune unimportant information and capture key local information from person images.
Towards Improving Embedding Based Models of Social Network Alignment via Pseudo Anchors
Social network alignment aims at aligning person identities across social networks.
Beyond Sole Strength: Customized Ensembles for Generalized Vision-Language Models
However, performance advancements are limited when relying solely on intricate algorithmic designs for a single model, even one exhibiting strong performance, e. g., CLIP-ViT-B/16.
Ranked #2 on
Prompt Engineering
on ImageNet
Once Upon a $\textit{Time}$ in $\textit{Graph}$: Relative-Time Pretraining for Complex Temporal Reasoning
However, the knowledge-time association is usually insufficient for the downstream tasks that require reasoning over temporal dependencies between knowledge.
Learning Deep Multi-Level Similarity for Thermal Infrared Object Tracking
These two similarities complement each other and hence enhance the discriminative capacity of the network for handling distractors.
DeepReduce: A Sparse-tensor Communication Framework for Distributed Deep Learning
This paper introduces DeepReduce, a versatile framework for the compressed communication of sparse tensors, tailored for distributed deep learning.
DeepReduce: A Sparse-tensor Communication Framework for Federated Deep Learning
DeepReduce is orthogonal to existing gradient sparsifiers and can be applied in conjunction with them, transparently to the end-user, to significantly lower the communication overhead.
ConNER: Consistency Training for Cross-lingual Named Entity Recognition
We propose ConNER as a novel consistency training framework for cross-lingual NER, which comprises of: (1) translation-based consistency training on unlabeled target-language data, and (2) dropoutbased consistency training on labeled source-language data.
No trends in spring and autumn phenology during the global warming hiatus
Phenology plays a fundamental role in regulating photosynthesis, evapotranspiration, and surface energy fluxes and is sensitive to climate change.
Rotation Invariant Point Cloud Classification: Where Local Geometry Meets Global Topology
To the best of our knowledge, this work is the first principled approach toward adaptively combining global and local information under the context of RI point cloud analysis.
A Detector-oblivious Multi-arm Network for Keypoint Matching
This paper presents a matching network to establish point correspondence between images.
Multilingual AMR Parsing with Noisy Knowledge Distillation
We study multilingual AMR parsing from the perspective of knowledge distillation, where the aim is to learn and improve a multilingual AMR parser by using an existing English parser as its teacher.
SwinIQA: Learned Swin Distance for Compressed Image Quality Assessment
In this paper, we design a full-reference image quality assessment metric SwinIQA to measure the perceptual quality of compressed images in a learned Swin distance space.
Manifold Learning of Four-dimensional Scanning Transmission Electron Microscopy
Four-dimensional scanning transmission electron microscopy (4D-STEM) of local atomic diffraction patterns is emerging as a powerful technique for probing intricate details of atomic structure and atomic electric fields.
Probabilistic Model Distillation for Semantic Correspondence
We address this problem with the use of a novel Probabilistic Model Distillation (PMD) approach which transfers knowledge learned by a probabilistic teacher model on synthetic data to a static student model with the use of unlabeled real image pairs.
Enhancing Multilingual Language Model with Massive Multilingual Knowledge Triples
In this work, we explore methods to make better use of the multilingual annotation and language agnostic property of KG triples, and present novel knowledge based multilingual language models (KMLMs) trained directly on the knowledge triples.
HST: Hierarchical Swin Transformer for Compressed Image Super-resolution
Compressed Image Super-resolution has achieved great attention in recent years, where images are degraded with compression artifacts and low-resolution artifacts.
Ranked #1 on
Compressed Image Super-resolution
on DIV2K-q40-x4
Towards Robust Low-Resource Fine-Tuning with Multi-View Compressed Representations
Due to the huge amount of parameters, fine-tuning of pretrained language models (PLMs) is prone to overfitting in the low resource scenarios.
WL-Align: Weisfeiler-Lehman Relabeling for Aligning Users across Networks via Regularized Representation Learning
Aligning users across networks using graph representation learning has been found effective where the alignment is accomplished in a low-dimensional embedding space.
Domain-adversarial Network Alignment
Network alignment is a critical task to a wide variety of fields.
Toward Tag-free Aspect Based Sentiment Analysis: A Multiple Attention Network Approach
Existing aspect based sentiment analysis (ABSA) approaches leverage various neural network models to extract the aspect sentiments via learning aspect-specific feature representations.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+1
Improving Adversarial Robustness via Probabilistically Compact Loss with Logit Constraints
This inspires us to propose a new Probabilistically Compact (PC) loss with logit constraints which can be used as a drop-in replacement for cross-entropy (CE) loss to improve CNN's adversarial robustness.
SimSR: Simple Distance-based State Representation for Deep Reinforcement Learning
This work explores how to learn robust and generalizable state representation from image-based observations with deep reinforcement learning methods.
Semantic-aware Message Broadcasting for Efficient Unsupervised Domain Adaptation
In this way, our message broadcasting encourages the group tokens to learn more informative and diverse information for effective domain alignment.
Ranked #1 on
Unsupervised Domain Adaptation
on VisDA2017
LoGoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross-Modal Fusion
Notably, LoGoNet ranks 1st on Waymo 3D object detection leaderboard and obtains 81. 02 mAPH (L2) detection performance.
SPARTAN: Self-supervised Spatiotemporal Transformers Approach to Group Activity Recognition
In this paper, we propose a new, simple, and effective Self-supervised Spatio-temporal Transformers (SPARTAN) approach to Group Activity Recognition (GAR) using unlabeled video data.
Improving Self-training for Cross-lingual Named Entity Recognition with Contrastive and Prototype Learning
In cross-lingual named entity recognition (NER), self-training is commonly used to bridge the linguistic gap by training on pseudo-labeled target-language data.
Task-driven Semantic Coding via Reinforcement Learning
However, the traditional hybrid coding framework cannot be optimized in an end-to-end manner, which makes task-driven semantic fidelity metric unable to be automatically integrated into the rate-distortion optimization process.
Retrofitting Multilingual Sentence Embeddings with Abstract Meaning Representation
Unlike most prior work that only evaluates the ability to measure semantic similarity, we present a thorough evaluation of existing multilingual sentence embeddings and our improved versions, which include a collection of five transfer tasks in different downstream applications.
RTracker: Recoverable Tracking via PN Tree Structured Memory
Upon the PN tree memory, we develop corresponding walking rules for determining the state of the target and define a set of control flows to unite the tracker and the detector in different tracking scenarios.
Compressed Sensing of Scanning Transmission Electron Microscopy (STEM) on Non-Rectangular Scans
Scanning Transmission Electron Microscopy (STEM) has become the main stay for materials characterization on atomic level, with applications ranging from visualization of localized and extended defects to mapping order parameter fields.
DAC: Data-free Automatic Acceleration of Convolutional Networks
A complex deep learning model with high accuracy runs slowly on resource-limited devices, while a light-weight model that runs much faster loses accuracy.
Probabilistic prediction of the heave motions of a semi-submersible by a deep learning problem model
In this study, we extend a deep learning (DL) model, which could predict the heave and surge motions of a floating semi-submersible 20 to 50 seconds ahead with good accuracy, to quantify its uncertainty of the predictive time series with the help of the dropout technique.
Enhancing Cross-lingual Prompting with Dual Prompt Augmentation
Prompting shows promising results in few-shot scenarios.
Behavior Prior Representation learning for Offline Reinforcement Learning
Our method, Behavior Prior Representation (BPR), learns state representations with an easy-to-integrate objective based on behavior cloning of the dataset: we first learn a state representation by mimicking actions from the dataset, and then train a policy on top of the fixed representation, using any off-the-shelf Offline RL algorithm.
From Cloze to Comprehension: Retrofitting Pre-trained Masked Language Model to Pre-trained Machine Reader
We present Pre-trained Machine Reader (PMR), a novel method for retrofitting pre-trained masked language models (MLMs) to pre-trained machine reading comprehension (MRC) models without acquiring labeled data.
mPMR: A Multilingual Pre-trained Machine Reader at Scale
mPMR aims to guide multilingual pre-trained language models (mPLMs) to perform natural language understanding (NLU) including both sequence classification and span extraction in multiple languages.
Dual-view Correlation Hybrid Attention Network for Robust Holistic Mammogram Classification
Mammogram image is important for breast cancer screening, and typically obtained in a dual-view form, i. e., cranio-caudal (CC) and mediolateral oblique (MLO), to provide complementary information.
The Algonauts Project 2023 Challenge: UARK-UAlbany Team Solution
The goal is to predict brain responses across the entire visual brain, as it is the region where the most reliable responses to images have been observed.
Can ChatGPT Detect DeepFakes? A Study of Using Multimodal Large Language Models for Media Forensics
DeepFakes, which refer to AI-generated media content, have become an increasing concern due to their use as a means for disinformation.
SBGAR: Semantics Based Group Activity Recognition
Activity recognition has become an important function in many emerging computer vision applications e. g. automatic video surveillance system, human-computer interaction application, and video recommendation system, etc.
On the Learning Property of Logistic and Softmax Losses for Deep Neural Networks
Deep convolutional neural networks (CNNs) trained with logistic and softmax losses have made significant advancement in visual recognition tasks in computer vision.
Aspect-based Sentiment Analysis in Question Answering Forums
This motivates us to investigate the task of ABSA on QA forums (ABSA-QA), aiming to jointly detect the discussed aspects and their sentiment polarities for a given QA pair.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+2
PeerDA: Data Augmentation via Modeling Peer Relation for Span Identification Tasks
Specifically, a novel Peer Data Augmentation (PeerDA) approach is proposed which employs span pairs with the PR relation as the augmentation data for training.
AQE: Argument Quadruplet Extraction via a Quad-Tagging Augmented Generative Approach
In this work, we for the first time propose a challenging argument quadruplet extraction task (AQE), which can provide an all-in-one extraction of four argumentative components, i. e., claims, evidence, evidence types, and stances.
A Real-Time Deep Network for Crowd Counting
Automatic analysis of highly crowded people has attracted extensive attention from computer vision research.
A streamlined Approach to Multimodal Few-Shot Class Incremental Learning for Fine-Grained Datasets
Few-shot Class-Incremental Learning (FSCIL) poses the challenge of retaining prior knowledge while learning from limited new data streams, all without overfitting.
On Improving Deep Reinforcement Learning for POMDPs
Deep Reinforcement Learning (RL) recently emerged as one of the most competitive approaches for learning in sequential decision making problems with fully observable environments, e. g., computer Go.
A Saliency-Guided Street View Image Inpainting Framework for Efficient Last-Meters Wayfinding
However, due to the large diversity of geographic context and acquisition conditions, the captured SVI always contains various distracting objects (e. g., pedestrians and vehicles), which will distract human visual attention from efficiently finding the destination in the last few meters.
Fusion-based Few-Shot Morphing Attack Detection and Fingerprinting
Our technical contributions include: 1) We propose a fusion-based few-shot learning (FSL) method to learn discriminative features that can generalize to unseen morphing attack types from predefined presentation attacks; 2) The proposed FSL based on the fusion of the PRNU model and Noiseprint network is extended from binary MAD to multiclass morphing attack fingerprinting (MAF).
Negative Flux Aggregation to Estimate Feature Attributions
There are increasing demands for understanding deep neural networks' (DNNs) behavior spurred by growing security and/or transparency concerns.
Federated Learning for Clinical Structured Data: A Benchmark Comparison of Engineering and Statistical Approaches
Our goal was to bridge the gap by presenting the first comprehensive comparison of FL frameworks from both engineering and statistical domains.
On the K-theory of crossed products by automorphic semigroup actions
Let P be a semigroup that admits an embedding into a group G. Assume that the embedding satisfies a certain Toeplitz condition and that the Baum-Connes conjecture holds for G. We prove a formula describing the K- theory of the reduced crossed product A \rtimes{\alpha}, r P by any automorphic action of P. This formula is obtained as a consequence of a result on the K-theory of crossed products for special actions of G on totally disconnected spaces.
Operator Algebras Dynamical Systems K-Theory and Homology 46L05, 46L80 (Primary) 20Mxx, 11R04 (Secondary)
TEAC: Intergrating Trust Region and Max Entropy Actor Critic for Continuous Control
Trust region methods and maximum entropy methods are two state-of-the-art branches used in reinforcement learning (RL) for the benefits of stability and exploration in continuous environments, respectively.
Muti-view Mouse Social Behaviour Recognition with Deep Graphical Model
To address this problem, we here propose a novel multiview latent-attention and dynamic discriminative model that jointly learns view-specific and view-shared sub-structures, where the former captures unique dynamics of each view whilst the latter encodes the interaction between the views.
Exploiting Semantic Relations for Fine-grained Entity Typing
We find that, in some cases, existing neural fine-grained entity typing models may ignore the semantic information in the context that is important for typing.
DR-GAN: Distribution Regularization for Text-to-Image Generation
This paper presents a new Text-to-Image generation model, named Distribution Regularization Generative Adversarial Network (DR-GAN), to generate images from text descriptions from improved distribution learning.
Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information
We find that contemporary representation learning techniques can fail on datasets where the noise is a complex and time dependent process, which is prevalent in practical applications.
Hyp-OW: Exploiting Hierarchical Structure Learning with Hyperbolic Distance Enhances Open World Object Detection
We argue that this contextual information should already be embedded within the known classes.
WebCiteS: Attributed Query-Focused Summarization on Chinese Web Search Results with Citations
Enhancing the attribution in large language models (LLMs) is a crucial task.
COMQ: A Backpropagation-Free Algorithm for Post-Training Quantization
Within a fixed layer, COMQ treats all the scaling factor(s) and bit-codes as the variables of the reconstruction error.
GANE: A Generative Adversarial Network Embedding
Network embedding has become a hot research topic recently which can provide low-dimensional feature representations for many machine learning applications.
On Improving Deep Reinforcement Learning for POMDPs
Deep Reinforcement Learning (RL) recently emerged as one of the most competitive approaches for learning in sequential decision making problems with fully observable environments, e. g., computer Go.
Perceptually Optimized Generative Adversarial Network for Single Image Dehazing
To overcome this weakness, we propose a direct deep learning approach toward image dehazing bypassing the step of transmission map estimation and facilitating end-to-end perceptual optimization.
Weighted Low-Rank Approximation of Matrices and Background Modeling
We primarily study a special a weighted low-rank approximation of matrices and then apply it to solve the background modeling problem.
ReHAR: Robust and Efficient Human Activity Recognition
The whole model is trained end-to-end to allow meaningful representations to be generated for the final activity recognition.
Joint Demosaicing and Denoising with Perceptual Optimization on a Generative Adversarial Network
Image demosaicing - one of the most important early stages in digital camera pipelines - addressed the problem of reconstructing a full-resolution image from so-called color-filter-arrays.
Adversarial Examples Detection in Deep Networks with Convolutional Filter Statistics
A cascade classifier was designed to efficiently detect adversarials.
Two-Level Structural Sparsity Regularization for Identifying Lattices and Defects in Noisy Images
We propose to formulate the identification of the lattice groups as a sparse group selection problem.
Learning with Rethinking: Recurrently Improving Convolutional Neural Networks through Feedback
However, most of the existing CNN models only learn features through a feedforward structure and no feedback information from top to bottom layers is exploited to enable the networks to refine themselves.
Prune the Convolutional Neural Networks with Sparse Shrink
These results have demonstrated the effectiveness of our "Sparse Shrink" algorithm.
FoveaNet: Perspective-aware Urban Scene Parsing
Thus, they suffer from heterogeneous object scales caused by perspective projection of cameras on actual scenes and inevitably encounter parsing failures on distant objects as well as other boundary and recognition errors.
Weighted Low Rank Approximation for Background Estimation Problems
Classical principal component analysis (PCA) is not robust to the presence of sparse outliers in the data.
A Batch-Incremental Video Background Estimation Model using Weighted Low-Rank Approximation of Matrices
Principal component pursuit (PCP) is a state-of-the-art approach for background estimation problems.
ESE: Efficient Speech Recognition Engine with Sparse LSTM on FPGA
Evaluated on the LSTM for speech recognition benchmark, ESE is 43x and 3x faster than Core i7 5930k CPU and Pascal Titan X GPU implementations.
Cross-scale predictive dictionaries
Sparse representations using data dictionaries provide an efficient model particularly for signals that do not enjoy alternate analytic sparsifying transformations.
Video Scene Parsing with Predictive Feature Learning
In this way, the network can effectively learn to capture video dynamics and temporal context, which are critical clues for video scene parsing, without requiring extra manual annotations.
Detecting Suicidal Ideation in Chinese Microblogs with Psychological Lexicons
Currently, we have identified 53 known suicidal cases who posted suicide notes on Weibo prior to their deaths. We explore linguistic features of these known cases using a psychological lexicon dictionary, and train an effective suicidal Weibo post detection model.
Learning Hybrid Sparsity Prior for Image Restoration: Where Deep Learning Meets Sparse Coding
State-of-the-art approaches toward image restoration can be classified into model-based and learning-based.
Superimposition-guided Facial Reconstruction from Skull
We develop a new algorithm to perform facial reconstruction from a given skull.
Deep Multi-Task Learning for Aspect Term Extraction with Memory Interaction
We propose a novel LSTM-based deep multi-task learning framework for aspect term extraction from user review sentences.
Aspect-Based Sentiment Analysis (ABSA)
Multi-Task Learning
+2
Learning Parametric Sparse Models for Image Super-Resolution
More specifically, the parametric sparse prior of the desirable high-resolution (HR) image patches are learned from both the input low-resolution (LR) image and a training image dataset.
CONet: A Cognitive Ocean Network
The Cognitive Ocean Network (CONet) will become the mainstream of future ocean science and engineering developments.
Adaptive Active Learning for Image Classification
Recently active learning has attracted a lot of attention in computer vision field, as it is time and cost consuming to prepare a good set of labeled images for vision data analysis.
Simplified Mirror-Based Camera Pose Computation via Rotation Averaging
Our theoretical contribution extends the applicability of rotation averaging to a more general case, and enables mirror-based pose estimation in closed-form under the chordal L2-metric, or in an outlier-robust way by employing iterative L1-norm averaging.
Object-Aware Dense Semantic Correspondence
To address these problems, this paper proposes an object-aware method to estimate per-pixel correspondences from semantic to low-level by learning a classifier for each selected discriminative grid cell and guiding the localization of every pixel under the semantic constraint.
Low-Rank Tensor Approximation With Laplacian Scale Mixture Modeling for Multiframe Image Denoising
Patch-based low-rank models have shown effective in exploiting spatial redundancy of natural images especially for the application of image denoising.
3D Fragment Reassembly Using Integrated Template Guidance and Fracture-Region Matching
This paper studies matching of fragmented objects to recompose their original geometry.
Semi-Supervised Zero-Shot Classification With Label Representation Learning
Most existing zero-shot learning methods require a user to first provide a set of semantic visual attributes for each class as side information before applying a two-step prediction procedure that introduces an intermediate attribute prediction problem.
Iris R-CNN: Accurate Iris Segmentation in Non-cooperative Environment
Despite the significant advances in iris segmentation, accomplishing accurate iris segmentation in non-cooperative environment remains a grand challenge.
Aligning Users Across Social Networks Using Network Embedding
Li Liu, 1 William K. Cheung, 2 Xin Li, 1⇤ and Lejian Liao1
Target-Aware Deep Tracking
Despite demonstrated successes for numerous vision tasks, the contributions of using pre-trained deep features for visual tracking are not as significant as that for object recognition.
LO-Net: Deep Real-time Lidar Odometry
We present a novel deep convolutional network pipeline, LO-Net, for real-time lidar odometry estimation.
STN-Homography: estimate homography parameters directly
In this paper, we introduce the STN-Homography model to directly estimate the homography matrix between image pair.
Vispi: Automatic Visual Perception and Interpretation of Chest X-rays
Medical imaging contains the essential information for rendering diagnostic and treatment decisions.
Reconstructing Perceived Images from Brain Activity by Visually-guided Cognitive Representation and Adversarial Learning
In addition, we introduce a novel three-stage learning approach which enables the (cognitive) encoder to gradually distill useful knowledge from the paired (visual) encoder during the learning process.
Small and Practical BERT Models for Sequence Labeling
We propose a practical scheme to train a single multilingual sequence labeling model that yields state of the art results and is small and fast enough to run on a single CPU.
Iterative Clustering with Game-Theoretic Matching for Robust Multi-consistency Correspondence
Matching corresponding features between two images is a fundamental task to computer vision with numerous applications in object recognition, robotics, and 3D reconstruction.
Spoofing and Anti-Spoofing with Wax Figure Faces
In this work, we introduce a wax figure face database (WFFD) as a novel and super-realistic 3D face presentation attack.
Automatic Lumbar Spinal CT Image Segmentation with a Dual Densely Connected U-Net
The clinical treatment of degenerative and developmental lumbar spinal stenosis (LSS) is different.
Joint Demosaicing and Super-Resolution (JDSR): Network Design and Perceptual Optimization
Image demosaicing and super-resolution are two important tasks in color imaging pipeline.
Sparse estimation via $\ell_q$ optimization method in high-dimensional linear regression
In this paper, we discuss the statistical properties of the $\ell_q$ optimization methods $(0<q\leq 1)$, including the $\ell_q$ minimization method and the $\ell_q$ regularization method, for estimating a sparse parameter from noisy observations in high-dimensional linear regression with either a deterministic or random design.
Relevance-Promoting Language Model for Short-Text Conversation
In this paper, we propose to formulate the STC task as a language modeling problem and tailor-make a training strategy to adapt a language model for response generation.
Digital Twin: Acquiring High-Fidelity 3D Avatar from a Single Image
We present an approach to generate high fidelity 3D face avatar with a high-resolution UV texture map from a single image.
