Search Results for author:
Found 388 papers, 112 papers with code
HARD-Net: Hardness-AwaRe Discrimination Network for 3D Early Activity Prediction
In this paper, we propose a novel Hardness-AwaRe Discrimination Network (HARD-Net) to specifically investigate the relationships between the similar activity pairs that are hard to be discriminated.
Ranked #3 on
Skeleton Based Action Recognition
on UAV-Human
Towards Generalizeable Semantic Product Search by Text Similarity Pre-training on Search Click Logs
Recently, semantic search has been successfully applied to E-commerce product search and the learned semantic space for query and product encoding are expected to generalize well to unseen queries or products.
Unsupervised Multi-View CNN for Salient View Selection of 3D Objects and Scenes
We present an unsupervised 3D deep learning framework based on a ubiquitously true proposition named by us view-object consistency as it states that a 3D object and its projected 2D views always belong to the same object class.
Hybrid Driven Learning for Channel Estimation in Intelligent Reflecting Surface Aided Millimeter Wave Communications
Intelligent reflecting surfaces (IRS) have been proposed in millimeter wave (mmWave) and terahertz (THz) systems to achieve both coverage and capacity enhancement, where the design of hybrid precoders, combiners, and the IRS typically relies on channel state information.
Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation
In this paper, we propose MUTR, a Multi-modal Unified Temporal transformer for Referring video object segmentation.
Referring Video Object Segmentation
Semantic Segmentation
+1
MRN: Multiplexed Routing Network for Incremental Multilingual Text Recognition
Traditional Multilingual Text Recognition (MLTR) usually targets a fixed set of languages and thus struggles to handle newly added languages or adapt to ever-changing class distributions.
MolXPT: Wrapping Molecules with Text for Generative Pre-training
Considering that text is the most important record for scientific discovery, in this paper, we propose MolXPT, a unified language model of text and molecules pre-trained on SMILES (a sequence representation of molecules) wrapped by text.
Ranked #1 on
Text-based de novo Molecule Generation
on ChEBI-20
(Validity metric)
LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model
This strategy effectively alleviates the interference between the two tasks of image-text alignment and instruction following and achieves strong multi-modal reasoning with only a small-scale image-text and instruction dataset.
STNet: Spatial and Temporal feature fusion network for change detection in remote sensing images
As an important task in remote sensing image analysis, remote sensing change detection (RSCD) aims to identify changes of interest in a region from spatially co-registered multi-temporal remote sensing images, so as to monitor the local development.
SACANet: scene-aware class attention network for semantic segmentation of remote sensing images
In this paper, we integrate both scene-aware and class attentions to propose a scene-aware class attention network (SACANet) for semantic segmentation of remote sensing images.
Road Genome: A Topology Reasoning Benchmark for Scene Understanding in Autonomous Driving
By introducing Road Genome (OpenLane-V2), we intend to shift the community's attention and take a step further beyond perception - to the task of topology reasoning for scene structure.
Network Pruning Spaces
Statistically, the structure of a winning subnetwork guarantees an approximately optimal ratio in this regime.
Frequency Decomposition to Tap the Potential of Single Domain for Generalization
Then, a new method that learns through multiple frequency domains is proposed.
Topology Reasoning for Driving Scenes
Understanding the road genome is essential to realize autonomous driving.
DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment
This paper presents DetCLIPv2, an efficient and scalable training framework that incorporates large-scale image-text pairs to achieve open-vocabulary object detection (OVD).
RSPT: Reconstruct Surroundings and Predict Trajectories for Generalizable Active Object Tracking
However, building a generalizable active tracker that works robustly across different scenarios remains a challenge, especially in unstructured environments with cluttered obstacles and diverse layouts.
HS-Pose: Hybrid Scope Feature Extraction for Category-level Object Pose Estimation
In this paper, we focus on the problem of category-level object pose estimation, which is challenging due to the large intra-category shape variation.
ByteTrackV2: 2D and 3D Multi-Object Tracking by Associating Every Detection Box
We propose a hierarchical data association strategy to mine the true objects in low-score detection boxes, which alleviates the problems of object missing and fragmented trajectories.
Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection
It employs a "divide-and-conquer" strategy and separately exploits positives for the classification and localization task, which is more robust to the assignment ambiguity.
How Does Attention Work in Vision Transformers? A Visual Analytics Attempt
Multi-head self-attentions are then applied to the sequence to learn the attention between patches.
Multi-modal Facial Affective Analysis based on Masked Autoencoder
The CVPR 2023 Competition on Affective Behavior Analysis in-the-wild (ABAW) is dedicated to providing high-quality and large-scale Aff-wild2 for the recognition of commonly used emotion representations, such as Action Units (AU), basic expression categories(EXPR), and Valence-Arousal (VA).
SpatialFormer: Semantic and Target Aware Attentions for Few-Shot Learning
Then we derive two specific attention modules, named SpatialFormer Semantic Attention (SFSA) and SpatialFormer Target Attention (SFTA), to enhance the target object regions while reduce the background distraction.
LoG-CAN: local-global Class-aware Network for semantic segmentation of remote sensing images
We present LoG-CAN, a multi-scale semantic segmentation network with a global class-aware (GCA) module and local class-aware (LCA) modules to remote sensing images.
CapDet: Unifying Dense Captioning and Open-World Detection Pretraining
Besides, our CapDet also achieves state-of-the-art performance on dense captioning tasks, e. g., 15. 44% mAP on VG V1. 2 and 13. 98% on the VG-COCO dataset.
Joint Task and Data Oriented Semantic Communications: A Deep Separate Source-channel Coding Scheme
This paper proposes a deep separate source-channel coding (DSSCC) framework for the joint task and data oriented semantic communications (JTD-SC) and utilizes the variational autoencoder approach to solve the rate-distortion problem with semantic distortion.
Entity-Level Text-Guided Image Manipulation
In the image manipulation phase, SeMani adopts a generative model to synthesize new images conditioned on the entity-irrelevant regions and target text descriptions.
RIS-Position and Orientation Estimation in MIMO-OFDM Systems with Practical Scatterers
A two-step positioning scheme is exploited, where the channel parameters are first acquired, and the position-related parameters are then estimated.
Simulation-to-reality UAV Fault Diagnosis with Deep Learning
Accurate diagnosis of propeller faults is crucial for ensuring the safe and efficient operation of quadrotors.
Language-Driven Anchors for Zero-Shot Adversarial Robustness
By leveraging the semantic consistency of the text encoders, LAAT can enhance the adversarial robustness of the image model on novel categories without additional examples.
Deep-learning-based on-chip rapid spectral imaging with high spatial resolution
Spectral imaging extends the concept of traditional color cameras to capture images across multiple spectral channels and has broad application prospects.
EPR-Net: Constructing non-equilibrium potential landscape via a variational force projection formulation
We present a novel yet simple deep learning approach, dubbed EPR-Net, for constructing the potential landscape of high-dimensional non-equilibrium steady state (NESS) systems.
Machine Learning for Large-Scale Optimization in 6G Wireless Networks
The sixth generation (6G) wireless systems are envisioned to enable the paradigm shift from "connected things" to "connected intelligence", featured by ultra high density, large-scale, dynamic heterogeneity, diversified functional requirements and machine learning capabilities, which leads to a growing need for highly efficient intelligent algorithms.
Semi-DETR: Semi-Supervised Object Detection With Detection Transformers
We analyze the DETR-based framework on semi-supervised object detection (SSOD) and observe that (1) the one-to-one assignment strategy generates incorrect matching when the pseudo ground-truth bounding box is inaccurate, leading to training inefficiency; (2) DETR-based detectors lack deterministic correspondence between the input query and its prediction output, which hinders the applicability of the consistency-based regularization widely used in current SSOD methods.
A Deep Learning Method for Real-time Bias Correction of Wind Field Forecasts in the Western North Pacific
In this study, we developed the Multi-Task-Double Encoder Trajectory Gated Recurrent Unit (MT-DETrajGRU) model, which uses an improved double-encoder forecaster architecture to model the spatiotemporal sequence of the U and V components of the wind field; we designed a multi-task learning loss function to correct wind speed and wind direction simultaneously using only one model.
Circular Accessible Depth: A Robust Traversability Representation for UGV Navigation
In this paper, we present the Circular Accessible Depth (CAD), a robust traversability representation for an unmanned ground vehicle (UGV) to learn traversability in various scenarios containing irregular obstacles.
Semantic optical fiber communication system
The current optical communication systems minimize bit or symbol errors without considering the semantic meaning behind digital bits, thus transmitting a lot of unnecessary information.
Differentiating Student Feedbacks for Knowledge Tracing
In computer-aided education and intelligent tutoring systems, knowledge tracing (KT) raises attention due to the development of data-driven learning methods, which aims to predict students' future performance given their past question response sequences to trace their knowledge states.
Adaptive Low-Precision Training for Embeddings in Click-Through Rate Prediction
To this end, we formulate a novel quantization training paradigm to compress the embeddings from the training stage, termed low-precision training (LPT).
Low-rank Tensor Assisted K-space Generative Model for Parallel Imaging Reconstruction
Although recent deep learning methods, especially generative models, have shown good performance in fast magnetic resonance imaging, there is still much room for improvement in high-dimensional generation.
Matrix Profile XXVII: A Novel Distance Measure for Comparing Long Time Series
PRCIS is a distance measure for long time series, which exploits recent progress in our ability to summarize time series with dictionaries.
G-MAP: General Memory-Augmented Pre-trained Language Model for Domain Tasks
Recently, domain-specific PLMs have been proposed to boost the task performance of specific domains (e. g., biomedical and computer science) by continuing to pre-train general PLMs with domain-specific corpora.
Dynamic Graph Node Classification via Time Augmentation
Node classification on dynamic graphs is challenging for two reasons.
FlowFace: Semantic Flow-guided Shape-aware Face Swapping
Unlike most previous methods that focus on transferring the source inner facial features but neglect facial contours, our FlowFace can transfer both of them to a target face, thus leading to more realistic face swapping.
Quantized Wasserstein Procrustes Alignment of Word Embedding Spaces
Optimal Transport (OT) provides a useful geometric framework to estimate the permutation matrix under unsupervised cross-lingual word embedding (CLWE) models that pose the alignment task as a Wasserstein-Procrustes problem.
3D-TOGO: Towards Text-Guided Cross-Category 3D Object Generation
Here, we make the first attempt to achieve generic text-guided cross-category 3D object generation via a new 3D-TOGO model, which integrates a text-to-views generation module and a views-to-3D generation module.
Global Meets Local: Effective Multi-Label Image Classification via Category-Aware Weak Supervision
This paper builds a unified framework to perform effective noisy-proposal suppression and to interact between global and local features for robust feature learning.
RIS-Assisted Self-Interference Mitigation for In-Band Full-Duplex Transceivers
The wireless in-band full-duplex (IBFD) technology can in theory double the system capacity over the conventional frequency division duplex (FDD) or time-division duplex (TDD) alternatives.
LVOS: A Benchmark for Long-term Video Object Segmentation
The videos in our LVOS last 1. 59 minutes on average, which is 20 times longer than videos in existing VOS datasets.
Leveraging the Hints: Adaptive Bidding in Repeated First-Price Auctions
In the past four years, a particularly important development in the digital advertising industry is the shift from second-price auctions to first-price auctions for online display ads.
Rethinking the Metric in Few-shot Learning: From an Adaptive Multi-Distance Perspective
In this paper, for the first time, we investigate the contributions of different distance metrics, and propose an adaptive fusion scheme, bringing significant improvements in few-shot classification.
Facial Action Unit Detection and Intensity Estimation from Self-supervised Representation
As a fine-grained and local expression behavior measurement, facial action unit (FAU) analysis (e. g., detection and intensity estimation) has been documented for its time-consuming, labor-intensive, and error-prone annotation.
Global-to-local Expression-aware Embeddings for Facial Action Unit Detection
Then, AU feature maps and their corresponding AU masks are multiplied to generate AU masked features focusing on local facial region.
Facial Action Units Detection Aided by Global-Local Expression Embedding
We find that AUs and facial expressions are highly associated, and existing facial expression datasets often contain a large number of identities.
HAM: Hierarchical Attention Model with High Performance for 3D Visual Grounding
To simplify the pipeline, we carefully investigate 3D visual grounding and summarize three fundamental problems about how to develop an end-to-end model with high performance for this task.
Slippage-robust Gaze Tracking for Near-eye Display
In recent years, head-mounted near-eye display devices have become the key hardware foundation for virtual reality and augmented reality.
ISTA-Inspired Network for Image Super-Resolution
Inspired by the mathematical analysis, the ISTA block is developed to conduct the optimization in an end-to-end manner.
Repainting and Imitating Learning for Lane Detection
In this paper, we target at finding an enhanced feature space where the lane features are distinctive while maintaining a similar distribution of lanes in the wild.
SoccerNet 2022 Challenges Results
The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team.
Collaboration of Pre-trained Models Makes Better Few-shot Learner
In this paper, we propose CoMo, a Collaboration of pre-trained Models that incorporates diverse prior knowledge from various pre-training paradigms for better few-shot learning.
DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection
We further design a concept dictionary~(with descriptions) from various online sources and detection datasets to provide prior knowledge for each concept.
Provably Uncertainty-Guided Universal Domain Adaptation
It fully utilizes the relationship between a target sample and its neighbors in the source domain to avoid the influence of domain misalignment.
SENDER: SEmi-Nonlinear Deep Efficient Reconstructor for Extraction Canonical, Meta, and Sub Functional Connectivity in the Human Brain
Deep Linear and Nonlinear learning methods have already been vital machine learning methods for investigating the hierarchical features such as functional connectivity in the human brain via functional Magnetic Resonance signals; however, there are three major shortcomings: 1).
A detail-enhanced sampling strategy in Hadamard single-pixel imaging
Hadamard single-pixel imaging (HSI) is an appealing imaging technique due to its features of low hardware complexity and industrial cost.
A Circular Window-based Cascade Transformer for Online Action Detection
In this paper, we advocate a novel and efficient principle for online action detection.
Dual Representation Learning for One-Step Clustering of Multi-View Data
Meanwhile, to make the representation learning more specific to the clustering task, a one-step learning framework is proposed to integrate representation learning and clustering partition as a whole.
Robustness to Unbounded Smoothness of Generalized SignSGD
We also compare these algorithms with popular optimizers on a set of deep learning tasks, observing that we can match the performance of Adam while beating the others.
Joint Localization and Information Transfer for Reconfigurable Intelligent Surface Aided Full-Duplex Systems
A grid based parametric model is constructed and the joint estimation problem is formulated as a compressive sensing problem.
SFF-DA: Sptialtemporal Feature Fusion for Detecting Anxiety Nonintrusively
To address these issues, we propose a framework with spatiotemporal feature fusion for detecting anxiety nonintrusively.
Embedding Compression with Hashing for Efficient Representation Learning in Large-Scale Graph
Graph neural networks (GNNs) are deep learning models designed specifically for graph data, and they typically rely on node features as the input to the first layer.
Multi-View Pre-Trained Model for Code Vulnerability Identification
Vulnerability identification is crucial for cyber security in the software-related industry.
Exploiting Inter-Sample Affinity for Knowability-Aware Universal Domain Adaptation
Specifically, we introduce a knowability-based labeling scheme which can be divided into two steps: 1) Knowability-guided detection of known and unknown samples based on the intrinsic structure of the neighborhoods of samples, where we leverage the first singular vectors of the affinity matrices to obtain the knowability of every target sample.
Weakly Supervised Video Salient Object Detection via Point Supervision
Several works attempt to use scribble annotations to mitigate this problem, but point supervision as a more labor-saving annotation method (even the most labor-saving method among manual annotation methods for dense prediction), has not been explored.
Effective Few-Shot Named Entity Linking by Meta-Learning
In this paper, we endeavor to solve the problem of few-shot entity linking, which only requires a minimal amount of in-domain labeled data and is more practical in real situations.
Consecutive Pretraining: A Knowledge Transfer Learning Strategy with Relevant Unlabeled Data for Remote Sensing Domain
Currently, under supervised learning, a model pretrained by a large-scale nature scene dataset and then fine-tuned on a few specific task labeling data is the paradigm that has dominated the knowledge transfer learning.
Unsupervised Recurrent Federated Learning for Edge Popularity Prediction in Privacy-Preserving Mobile Edge Computing Networks
In this article, we propose an unsupervised and privacy-preserving popularity prediction framework for MEC-enabled IIoT.
Network Amplification With Efficient MACs Allocation
In particular, the proposed method is used to enlarge models sourced by GhostNet, we achieve state-of-the-art 80. 9% and 84. 3% ImageNet top-1 accuracies under the setting of 600M and 4. 4B MACs, respectively.
Video2StyleGAN: Encoding Video in Latent Space for Manipulation
To this end, we propose a novel network to encode face videos into the latent space of StyleGAN for semantic face video manipulation.
SADAM: Stochastic Adam, A Stochastic Operator for First-Order Gradient-based Optimizer
In this work, to efficiently help escape the stationary and saddle points, we propose, analyze, and generalize a stochastic strategy performed as an operator for a first-order gradient descent algorithm in order to increase the target accuracy and reduce time consumption.
DEMAND: Deep Matrix Approximately Nonlinear Decomposition to Identify Meta, Canonical, and Sub-Spatial Pattern of functional Magnetic Resonance Imaging in the Human Brain
At first, the proposed DEMAND employs a non-fully connected and multilayer-stacked architecture that is easier to be optimized compared with canonical DNNs; furthermore, due to the efficient architecture, training DEMAND can avoid overfitting and enables the recognition of individual/minor features based on a small dataset such as an individual data; finally, a novel rank estimator technique is introduced to tune all hyperparameters of DEMAND automatically.
DELMAR: Deep Linear Matrix Approximately Reconstruction to Extract Hierarchical Functional Connectivity in the Human Brain
Moreover, the theoretical analyses indicate that DELMAR can converge to the unique fixed point and even enable the accurate approximation of original input as DNNs.
Joint OAM Radar-Communication Systems: Target Recognition and Beam Optimization
In details, we first propose an OAM-based three-dimensional (3-D) super-resolution position estimation and rotation velocity detection method, which can accurately estimate the 3-D position and rotation velocity of multiple targets.
Intelligent Reflecting Surface Configurations for Smart Radio Using Deep Reinforcement Learning
Intelligent reflecting surface (IRS) is envisioned to change the paradigm of wireless communications from "adapting to wireless channels" to "changing wireless channels".
A Practical Two-stage Ranking Framework for Cross-market Recommendation
The proposed solution of our team WSDM_Coggle_ is selected as the second place submission.
Data-Efficient Backdoor Attacks
Recent studies have proven that deep neural networks are vulnerable to backdoor attacks.
Reconfigurable Intelligent Surface for Near Field Communications: Beamforming and Sensing
However, the conventional continuous aperture RIS is designed to convert the incoming planar waves into the outgoing planar waves, which is not the optimal reflecting scheme when the receiver is not a planar array and is located in the near field of the RIS.
Towards Generalizable Semantic Product Search by Text Similarity Pre-training on Search Click Logs
Recently, semantic search has been successfully applied to e-commerce product search and the learned semantic space(s) for query and product encoding are expected to generalize to unseen queries or products.
Point2Seq: Detecting 3D Objects as Sequences
We further propose a lightweight scene-to-sequence decoder that can auto-regressively generate words conditioned on features from a 3D scene as well as cues from the preceding words.
Beam Training and Alignment for RIS-Assisted Millimeter Wave Systems:State of the Art and Beyond
The deployment of RIS, however, complicates the system architecture and poses a significant challenge for beam training (BT)/ beam alignment (BA), a process that is required to establish a reliable link between the transmitter and the receiver.
Transformer-based Multimodal Information Fusion for Facial Expression Analysis
Then, we introduce a transformer-based fusion module that integrates the static vision features and the dynamic multimodal features.
Weakly-Supervised Salient Object Detection Using Point Supervision
Then we develop a transformer-based point-supervised saliency detection model to produce the first round of saliency maps.
Compression of Generative Pre-trained Language Models via Quantization
We find that previous quantization methods fail on generative tasks due to the \textit{homogeneous word embeddings} caused by reduced capacity, and \textit{varied distribution of weights}.
FERV39k: A Large-Scale Multi-Scene Dataset for Facial Expression Recognition in Videos
Current benchmarks for facial expression recognition (FER) mainly focus on static images, while there are limited datasets for FER in videos.
CODA: A Real-World Road Corner Case Dataset for Object Detection in Autonomous Driving
One main reason that impedes the development of truly reliably self-driving systems is the lack of public datasets for evaluating the performance of object detectors on corner cases.
Bilinear Systems Induced by Proper Lie Group Actions
In the study of induced bilinear systems, the classical Lie algebra rank condition (LARC) is known to be impractical since it requires computing the rank everywhere.
Visualizing and Understanding Patch Interactions in Vision Transformer
Vision Transformer (ViT) has become a leading tool in various computer vision tasks, owing to its unique self-attention mechanism that learns visual representations explicitly through cross-patch information interactions.
Amplitude-Constrained Constellation and Reflection Pattern Designs for Directional Backscatter Communications Using Programmable Metasurface
For the constellation design, we adopt the amplitude and phase-shift keying (APSK) constellation and optimize the parameters of APSK such as ring number, ring radius, and inter-ring phase difference.
A Large-scale Comprehensive Dataset and Copy-overlap Aware Evaluation Protocol for Segment-level Video Copy Detection
In this paper, we introduce VCSL (Video Copy Segment Localization), a new comprehensive segment-level annotated video copy dataset.
Freeform Body Motion Generation from Speech
Motivated by studies in linguistics, we decompose the co-speech motion into two complementary parts: pose modes and rhythmic dynamics.
Class-Aware Contrastive Semi-Supervised Learning
Pseudo-label-based semi-supervised learning (SSL) has achieved great success on raw data utilization.
PKGM: A Pre-trained Knowledge Graph Model for E-commerce Application
On the one hand, it could provide item knowledge services in a uniform way with service vectors for embedding-based and item-knowledge-related task models without accessing triple data.
Prediction of Depression Severity Based on the Prosodic and Semantic Features with Bidirectional LSTM and Time Distributed CNN
For the text modality, we use global vectors for word representation (GloVe) to perform word embeddings and the embeddings are fed into the Bi-LSTM network.
High-order Correlation Preserved Incomplete Multi-view Subspace Clustering
Specifically, multiple affinity matrices constructed from the incomplete multi-view data are treated as a thirdorder low rank tensor with a tensor factorization regularization which preserves the high-order view correlation and sample correlation.
Incomplete multi-view clustering
Multi-view Subspace Clustering
+1
Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark
Experiments show that Wukong can serve as a promising Chinese pre-training dataset and benchmark for different cross-modal learning methods.
Ranked #6 on
Zero-shot Image Retrieval
on COCO-CN
Model-Based Neural Network and Its Application to Line Spectral Estimation
Owing to the same layered form as an ANN, a MNN can also be optimized using the back-propagation (BP) algorithm.
A comprehensive benchmark analysis for sand dust image reconstruction
In this paper, we presented a comprehensive perceptual study and analysis of real-world sand dust images, then constructed a Sand-dust Image Reconstruction Benchmark (SIRB) for training Convolutional Neural Networks (CNNs) and evaluating algorithms performance.
PowerGear: Early-Stage Power Estimation in FPGA HLS via Heterogeneous Edge-Centric GNNs
Specifically, in the graph construction flow, we introduce buffer insertion, datapath merging, graph trimming and feature annotation techniques to transform HLS designs into graph-structured data, which encode both intra-operation micro-architectures and inter-operation interconnects annotated with switching activities.
Learning-From-Disagreement: A Model Comparison and Visual Analytics Framework
With these metrics, one can easily identify meta-features with the most complementary behaviors in two classifiers, and use them to better ensemble the classifiers.
Multi-Scale Adaptive Graph Neural Network for Multivariate Time Series Forecasting
Given the multi-scale feature representations and scale-specific inter-variable dependencies, a multi-scale temporal graph neural network is introduced to jointly model intra-variable dependencies and inter-variable dependencies.
New volatility evolution model after extreme events
Empirical study of the evolutionary behaviors of volatility after endogenous and exogenous events further demonstrates the descriptive power of our new model.
What Hinders Perceptual Quality of PSNR-oriented Methods?
E. g, in EDSR, our proposed method achieves 3. 60$\times$ faster learning speed compared to a GAN-based method with a subtle degradation in visual quality.
ISDNet: Integrating Shallow and Deep Networks for Efficient Ultra-High Resolution Segmentation
The huge burden of computation and memory are two obstacles in ultra-high resolution image segmentation.
Data-Free Knowledge Transfer: A Survey
In this paper, we provide a comprehensive survey on data-free knowledge transfer from the perspectives of knowledge distillation and unsupervised domain adaptation, to help readers have a better understanding of the current research status and ideas.
Responsive Listening Head Generation: A Benchmark Dataset and Baseline
Automatically synthesizing listening behavior that actively responds to a talking head, is critical to applications such as digital human, virtual agents and social robots.
Error-bounded Approximate Time Series Joins using Compact Dictionary Representations of Time Series
The matrix profile is an effective data mining tool that provides similarity join functionality for time series data.
LCTR: On Awakening the Local Continuity of Transformer for Weakly Supervised Object Localization
In this paper, we propose a novel framework built upon the transformer, termed LCTR (Local Continuity TRansformer), which targets at enhancing the local perception capability of global features among long-range feature dependencies.
PointCLIP: Point Cloud Understanding by CLIP
On top of that, we design an inter-view adapter to better extract the global feature and adaptively fuse the few-shot knowledge learned from 3D into CLIP pre-trained in 2D.
Ranked #3 on
Training-free 3D Part Segmentation
on ShapeNet-Part
(using extra training data)
Multi-Domain Transformer-Based Counterfactual Augmentation for Earnings Call Analysis
Earnings call (EC), as a periodic teleconference of a publicly-traded company, has been extensively studied as an essential market indicator because of its high analytical value in corporate fundamentals.
Loss Landscape Dependent Self-Adjusting Learning Rates in Decentralized Stochastic Gradient Descent
We conduct extensive studies over 18 state-of-the-art DL models/tasks and demonstrate that DPSGD often converges in cases where SSGD diverges for large learning rates in the large batch setting.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Optimizing for In-memory Deep Learning with Emerging Memory Technology
In-memory deep learning has already demonstrated orders of magnitude higher performance density and energy efficiency.
Using Reconfigurable Intelligent Surfaces for UE Positioning in mmWave MIMO Systems
We develop a RIS-aided positioning framework to locate a UE in environments where the LOS path may or may not be available.
Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling
To further enhance CLIP's few-shot capability, CLIP-Adapter proposed to fine-tune a lightweight residual feature adapter and significantly improves the performance for few-shot classification.
ViDA-MAN: Visual Dialog with Digital Humans
We demonstrate ViDA-MAN, a digital-human agent for multi-modal interaction, which offers realtime audio-visual responses to instant speech inquiries.
Directional Self-supervised Learning for Heavy Image Augmentations
Specifically, we adapt heavy augmentation policies after the views lightly augmented by standard augmentations, to generate harder view (HV).
IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning
Also, we develop a strong IconQA baseline Patch-TRM that applies a pyramid cross-modal Transformer with input diagram embeddings pre-trained on the icon dataset.
Ranked #1 on
Visual Question Answering (VQA)
on IconQA
Asynchronous Decentralized Distributed Training of Acoustic Models
Specifically, we study three variants of asynchronous decentralized parallel SGD (ADPSGD), namely, fixed and randomized communication patterns on a ring as well as a delay-by-one scheme.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Sensoring and Application of Multimodal Data for the Detection of Freezing of Gait in Parkinson's Disease
The accurate and reliable detection or prediction of freezing of gaits (FOG) is important for fall prevention in Parkinson's Disease (PD) and studying the physiological transitions during the occurrence of FOG.
TSK Fuzzy System Towards Few Labeled Incomplete Multi-View Data Classification
The proposed method has the following distinctive characteristics: 1) it can deal with the incomplete and few labeled multi-view data simultaneously; 2) it integrates the missing view imputation and model learning as a single process, which is more efficient than the traditional two-step strategy; 3) attributed to the interpretable fuzzy inference rules, this method is more interpretable.
A transformer-based deep learning approach for classifying brain metastases into primary organ sites using clinical whole brain MRI
Treatment decisions for brain metastatic disease rely on knowledge of the primary organ site, and currently made with biopsy and histology.
Video Temporal Relationship Mining for Data-Efficient Person Re-identification
This paper is a technical report to our submission to the ICCV 2021 VIPriors Re-identification Challenge.
Scalable Rule-Based Representation Learning for Interpretable Classification
Rule-based models, e. g., decision trees, are widely used in scenarios demanding high model interpretability for their transparent inner structures and good model expressivity.
Embedding Compression with Hashing for Efficient Representation Learning in Graph
When applying such type of networks on graph without node feature, one can extract simple graph-based node features (e. g., number of degrees) or learn the input node representation (i. e., embeddings) when training the network.
MC$^2$-SF: Slow-Fast Learning for Mobile-Cloud Collaborative Recommendation
With the hardware development of mobile devices, it is possible to build the recommendation models on the mobile side to utilize the fine-grained features and the real-time feedbacks.
Learning Dual Dynamic Representations on Time-Sliced User-Item Interaction Graphs for Sequential Recommendation
Sequential Recommendation aims to recommend items that a target user will interact with in the near future based on the historically interacted items.
Bayesian Optimization with Clustering and Rollback for CNN Auto Pruning
Subsequently, a rollback algorithm is proposed to recover the high-dimensional design space so that higher pruning accuracy can be obtained.
Online Multi-horizon Transaction Metric Estimation with Multi-modal Learning in Payment Networks
In this work, we study the problem of multivariate time series prediction for estimating transaction metrics associated with entities in the payment transaction database.
OMPQ: Orthogonal Mixed Precision Quantization
Instead of solving a problem of the original integer programming, we propose to optimize a proxy metric, the concept of network orthogonality, which is highly correlated with the loss of the integer programming but also easy to optimize with linear programming.
Deep Person Generation: A Survey from the Perspective of Face, Pose and Cloth Synthesis
Deep person generation has attracted extensive research attention due to its wide applications in virtual agents, video conferencing, online shopping and art/movie production.
How Does Adversarial Fine-Tuning Benefit BERT?
Adversarial training (AT) is one of the most reliable methods for defending against adversarial attacks in machine learning.
4-bit Quantization of LSTM-based Speech Recognition Models
We investigate the impact of aggressive low-precision representations of weights and activations in two families of large LSTM-based architectures for Automatic Speech Recognition (ASR): hybrid Deep Bidirectional LSTM - Hidden Markov Models (DBLSTM-HMMs) and Recurrent Neural Network - Transducers (RNN-Ts).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
ARShoe: Real-Time Augmented Reality Shoe Try-on System on Smartphones
To this concern, this work proposes a real-time augmented reality virtual shoe try-on system for smartphones, namely ARShoe.
G-DetKD: Towards General Distillation Framework for Object Detectors via Contrastive and Semantic-guided Feature Imitation
In this paper, we investigate the knowledge distillation (KD) strategy for object detection and propose an effective framework applicable to both homogeneous and heterogeneous student-teacher pairs.
Box-Aware Feature Enhancement for Single Object Tracking on Point Clouds
Current 3D single object tracking approaches track the target based on a feature comparison between the target template and the search area.
Ranked #2 on
Object Tracking
on KITTI
Binary Complex Neural Network Acceleration on FPGA
Deep complex networks (DCN), in contrast, can learn from complex data, but have high computational costs; therefore, they cannot satisfy the instant decision-making requirements of many deployable systems dealing with short observations or short signal bursts.
Weakly-Supervised Spatio-Temporal Anomaly Detection in Surveillance Video
In this paper, we introduce a novel task, referred to as Weakly-Supervised Spatio-Temporal Anomaly Detection (WSSTAD) in surveillance video.
On Sample Based Explanation Methods for NLP: Faithfulness, Efficiency and Semantic Evaluation
In the recent advances of natural language processing, the scale of the state-of-the-art models and datasets is usually extensive, which challenges the application of sample-based explanation methods in many aspects, such as explanation interpretability, efficiency, and faithfulness.
Performance assessment and tuning of PID control using TLBO: the single-loop case and PI/P cascade case
Minimum output variance (MOV) is used as a benchmark for CPA of PID, but it is difficult to be found due to the associated non-convex optimization problem.
Greedy Network Enlarging
Recent studies on deep convolutional neural networks present a simple paradigm of architecture design, i. e., models with more MACs typically achieve better accuracy, such as EfficientNet and RegNet.
Augmentation Pathways Network for Visual Recognition
Experimental results on ImageNet demonstrate the compatibility and effectiveness on a much wider range of augmentations, while consuming fewer parameters and lower computational costs at inference time.
Boosting the Convergence of Reinforcement Learning-based Auto-pruning Using Historical Data
Reinforcement learning (RL)-based auto-pruning has been further proposed to automate the DNN pruning process to avoid expensive hand-crafted work.
Prior Aided Streaming Network for Multi-task Affective Recognitionat the 2nd ABAW2 Competition
Automatic affective recognition has been an important research topic in human computer interaction (HCI) area.
SODA10M: A Large-Scale 2D Self/Semi-Supervised Object Detection Dataset for Autonomous Driving
Experiments show that SODA10M can serve as a promising pre-training dataset for different self-supervised learning methods, which gives superior performance when fine-tuning with different downstream tasks (i. e., detection, semantic/instance segmentation) in autonomous driving domain.
One Million Scenes for Autonomous Driving: ONCE Dataset
To facilitate future research on exploiting unlabeled data for 3D detection, we additionally provide a benchmark in which we reproduce and evaluate a variety of self-supervised and semi-supervised methods on the ONCE dataset.
Mesh Saliency: An Independent Perceptual Measure or a Derivative of Image Saliency?
While mesh saliency aims to predict regional importance of 3D surfaces in agreement with human visual perception and is well researched in computer vision and graphics, latest work with eye-tracking experiments shows that state-of-the-art mesh saliency methods remain poor at predicting human fixations.
Discrimination-Aware Mechanism for Fine-Grained Representation Learning
Therefore, there is a need for a training mechanism that enforces the discriminativeness of all the elements in the feature to capture more the subtle visual cues.
LPSNet: A Lightweight Solution for Fast Panoptic Segmentation
Panoptic segmentation is a challenging task aiming to simultaneously segment objects (things) at instance level and background contents (stuff) at semantic level.
Learning a Facial Expression Embedding Disentangled From Identity
The facial expression analysis requires a compact and identity-ignored expression representation.
Tensor-Based Multi-View Block-Diagonal Structure Diffusion for Clustering Incomplete Multi-View Data
In this paper, we propose a novel incomplete multi-view clustering method, in which a tensor nuclear norm regularizer elegantly diffuses the information of multi-view block-diagonal structure across different views.
On Sample Based Explanation Methods for NLP:Efficiency, Faithfulness, and Semantic Evaluation
In the recent advances of natural language processing, the scale of the state-of-the-art models and datasets is usually extensive, which challenges the application of sample-based explanation methods in many aspects, such as explanation interpretability, efficiency, and faithfulness.
Joint Channel Estimation and Mixed-ADCs Allocation for Massive MIMO via Deep Learning
Instead of randomly assigning the mixed-ADCs, we then design a novel antenna selection network for mixed-ADCs allocation to further improve the channel estimation accuracy.
Model Aided Deep Learning Based MIMO OFDM Receiver With Nonlinear Power Amplifiers
Multi-input multi-output orthogonal frequency division multiplexing (MIMO OFDM) is a key technology for mobile communication systems.