Search Results for author:
Found 304 papers, 134 papers with code
Deep Learning with Differential Privacy
Machine learning techniques based on neural networks are achieving remarkable results in a wide variety of domains.
MoViNets: Mobile Video Networks for Efficient Video Recognition
We present Mobile Video Networks (MoViNets), a family of computation and memory efficient video networks that can operate on streaming video for online inference.
Ranked #3 on
Action Classification
on Charades
Data Interpreter: An LLM Agent For Data Science
Large Language Model (LLM)-based agents have demonstrated remarkable effectiveness.
Neural Collaborative Filtering vs. Matrix Factorization Revisited
This approach is often referred to as neural collaborative filtering (NCF).
Ranked #6 on
Link Prediction
on Yelp
Revisiting the Performance of iALS on Item Recommendation Benchmarks
Matrix factorization learned by implicit alternating least squares (iALS) is a popular baseline in recommender system research publications.
iALS++: Speeding up Matrix Factorization with Subspace Optimization
However, iALS does not scale well with large embedding dimensions, d, due to its cubic runtime dependency on d. Coordinate descent variations, iCD, have been proposed to lower the complexity to quadratic in d. In this work, we show that iCD approaches are not well suited for modern processors and can be an order of magnitude slower than a careful iALS implementation for small to mid scale embedding sizes (d ~ 100) and only perform better than iALS on large embeddings d ~ 1000.
The NPU System for the 2020 Personalized Voice Trigger Challenge
This paper describes the system developed by the NPU team for the 2020 personalized voice trigger challenge.
Improving Semantic Segmentation via Decoupled Body and Edge Supervision
Our insight is that appealing performance of semantic segmentation requires \textit{explicitly} modeling the object \textit{body} and \textit{edge}, which correspond to the high and low frequency of the image.
Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
In this paper, we aim to provide an alternative perspective by treating semantic segmentation as a sequence-to-sequence prediction task.
Ranked #2 on
Semantic Segmentation
on FoodSeg103
(using extra training data)
Robust and Accurate Object Detection via Adversarial Learning
Data augmentation has become a de facto component for training high-performance deep image classifiers, but its potential is under-explored for object detection.
Ranked #17 on
Object Detection
on COCO-O
InternLM2 Technical Report
The evolution of Large Language Models (LLMs) like ChatGPT and GPT-4 has sparked discussions on the advent of Artificial General Intelligence (AGI).
Ranked #5 on
Long-Context Understanding
on Ada-LEval (BestAnswer)
RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose
Recent studies on 2D pose estimation have achieved excellent performance on public benchmarks, yet its application in the industrial community still suffers from heavy model parameters and high latency.
Ranked #3 on
Pose Estimation
on OCHuman
(using extra training data)
Fast Online Object Tracking and Segmentation: A Unifying Approach
In this paper we illustrate how to perform both visual object tracking and semi-supervised video object segmentation, in real-time, with a single simple approach.
Ranked #3 on
Visual Object Tracking
on YouTube-VOS 2018
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models.
Rényi Differential Privacy of the Sampled Gaussian Mechanism
The Sampled Gaussian Mechanism (SGM)---a composition of subsampling and the additive Gaussian noise---has been successfully used in a number of machine learning applications.
On the Difficulty of Evaluating Baselines: A Study on Recommender Systems
Numerical evaluations with comparisons to baselines play a central role when judging research in recommender systems.
Ranked #1 on
Recommendation Systems
on MovieLens 10M
Learning to Compare: Relation Network for Few-Shot Learning
Once trained, a RN is able to classify images of new classes by computing relation scores between query images and the few examples of each new class without further updating the network.
Vision Transformers: From Semantic Segmentation to Dense Prediction
In this work, for the first time we explore the global context learning potentials of ViTs for dense visual prediction (e. g., semantic segmentation).
IBM Deep Learning Service
Deep learning driven by large neural network models is overtaking traditional machine learning methods for understanding unstructured and perceptual data domains such as speech, text, and vision.
Distributed, Parallel, and Cluster Computing
Improving Text-to-SQL Evaluation Methodology
Second, we show that the current division of data into training and test sets measures robustness to variations in the way questions are asked, but only partially tests how well systems generalize to new queries; therefore, we propose a complementary dataset split for evaluation of future work.
Ranked #1 on
SQL Parsing
on IMDb
Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting
Reconstructing dynamic 3D scenes from 2D images and generating diverse views over time is challenging due to scene complexity and temporal dynamics.
ONCE-3DLanes: Building Monocular 3D Lane Detection
We present ONCE-3DLanes, a real-world autonomous driving dataset with lane layout annotation in 3D space.
Strip Pooling: Rethinking Spatial Pooling for Scene Parsing
Spatial pooling has been proven highly effective in capturing long-range contextual information for pixel-wise prediction tasks, such as scene parsing.
Ranked #32 on
Semantic Segmentation
on Cityscapes test
BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training
Multiple datasets and open challenges for object detection have been introduced in recent years.
Ranked #1 on
Object Detection
on BigDetection val
CelebV-HQ: A Large-Scale Video Facial Attributes Dataset
Large-scale datasets have played indispensable roles in the recent success of face generation/editing and significantly facilitated the advances of emerging research fields.
Ranked #1 on
Unconditional Video Generation
on CelebV-HQ
Towards Efficient Scene Understanding via Squeeze Reasoning
Instead of propagating information on the spatial map, we first learn to squeeze the input feature into a channel-wise global vector and perform reasoning within the single vector where the computation cost can be significantly reduced.
Dual Graph Convolutional Network for Semantic Segmentation
Exploiting long-range contextual information is key for pixel-wise prediction tasks such as semantic segmentation.
Ranked #32 on
Semantic Segmentation
on Cityscapes test
Global Aggregation then Local Distribution in Fully Convolutional Networks
GALD is end-to-end trainable and can be easily plugged into existing FCNs with various global aggregation modules for a wide range of vision tasks, and consistently improves the performance of state-of-the-art object detection and instance segmentation approaches.
Ranked #1 on
Semantic Segmentation
on PASCAL VOC 2007
Global Aggregation then Local Distribution for Scene Parsing
Modelling long-range contextual relationships is critical for pixel-wise prediction tasks such as semantic segmentation.
SOFT: Softmax-free Transformer with Linear Complexity
Crucially, with a linear complexity, much longer token sequences are permitted in SOFT, resulting in superior trade-off between accuracy and complexity.
Softmax-free Linear Transformers
With linear complexity, much longer token sequences are permitted by SOFT, resulting in superior trade-off between accuracy and complexity.
Spatially Adaptive Computation Time for Residual Networks
This paper proposes a deep learning architecture based on Residual Network that dynamically adjusts the number of executed layers for the regions of the image.
SeaFormer: Squeeze-enhanced Axial Transformer for Mobile Semantic Segmentation
Coupled with a light segmentation head, we achieve the best trade-off between segmentation accuracy and latency on the ARM-based mobile devices on the ADE20K and Cityscapes datasets.
XingGAN for Person Image Generation
We propose a novel Generative Adversarial Network (XingGAN or CrossingGAN) for person image generation tasks, i. e., translating the pose of a given person to a desired one.
Ranked #1 on
Pose Transfer
on Market-1501
(IS metric)
DeepInteraction: 3D Object Detection via Modality Interaction
Existing top-performance 3D object detectors typically rely on the multi-modal fusion strategy.
Generative Semantic Segmentation
To that end, the segmentation mask is expressed with a special type of image (dubbed as maskige).
Learning a Deep Embedding Model for Zero-Shot Learning
In this paper we argue that the key to make deep ZSL models succeed is to choose the right embedding space.
Ranked #14 on
Zero-Shot Action Recognition
on Kinetics
PolarFormer: Multi-camera 3D Object Detection with Polar Transformer
3D object detection in autonomous driving aims to reason "what" and "where" the objects of interest present in a 3D world.
Ranked #2 on
Robust Camera Only 3D Object Detection
on nuScenes-C
Faithful Chain-of-Thought Reasoning
While Chain-of-Thought (CoT) prompting boosts Language Models' (LM) performance on a gamut of complex reasoning tasks, the generated reasoning chain does not necessarily reflect how the model arrives at the answer (aka.
Large Language Models Illuminate a Progressive Pathway to Artificial Healthcare Assistant: A Review
This has sparked significant interest in applying LLMs to enhance various aspects of healthcare, ranging from medical education to clinical decision support.
A Survey of Resource-efficient LLM and Multimodal Foundation Models
Large foundation models, including large language models (LLMs), vision transformers (ViTs), diffusion, and LLM-based multimodal models, are revolutionizing the entire machine learning lifecycle, from training to deployment.
Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer
A few-shot semantic segmentation model is typically composed of a CNN encoder, a CNN decoder and a simple classifier (separating foreground and background pixels).
CAMixerSR: Only Details Need More "Attention"
To satisfy the rapidly increasing demands on the large image (2K-8K) super-resolution (SR), prevailing methods follow two independent tracks: 1) accelerate existing networks by content-aware routing, and 2) design better super-resolution networks via token mixer refining.
SAMUS: Adapting Segment Anything Model for Clinically-Friendly and Generalizable Ultrasound Image Segmentation
Segment anything model (SAM), an eminent universal image segmentation model, has recently gathered considerable attention within the domain of medical image segmentation.
CrossMoDA 2021 challenge: Benchmark of Cross-Modality Domain Adaptation techniques for Vestibular Schwannoma and Cochlea Segmentation
The aim was to automatically perform unilateral VS and bilateral cochlea segmentation on hrT2 as provided in the testing set (N=137).
Learning Ego 3D Representation as Ray Tracing
A self-driving perception model aims to extract 3D semantic representations from multiple cameras collectively into the bird's-eye-view (BEV) coordinate frame of the ego car in order to ground downstream planner.
DrugChat: Towards Enabling ChatGPT-Like Capabilities on Drug Molecule Graphs
The DrugChat system consists of a graph neural network (GNN), a large language model (LLM), and an adaptor.
Learning Differentially Private Recurrent Language Models
We demonstrate that it is possible to train large recurrent language models with user-level differential privacy guarantees with only a negligible cost in predictive accuracy.
Instance Credibility Inference for Few-Shot Learning
To measure the credibility of each pseudo-labeled instance, we then propose to solve another linear regression hypothesis by increasing the sparsity of the incidental parameters and rank the pseudo-labeled instances with their sparsity degree.
How to trust unlabeled data? Instance Credibility Inference for Few-Shot Learning
We rank the credibility of pseudo-labeled instances along the regularization path of their corresponding incidental parameters, and the most trustworthy pseudo-labeled examples are preserved as the augmented labeled instances.
Style Normalization and Restitution for Generalizable Person Re-identification
Existing fully-supervised person re-identification (ReID) methods usually suffer from poor generalization capability caused by domain gaps.
Ranked #8 on
Unsupervised Domain Adaptation
on Market to Duke
SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling
By relating masked modeling to manifold learning, SimMTM proposes to recover masked time points by the weighted aggregation of multiple neighbors outside the manifold, which eases the reconstruction task by assembling ruined but complementary temporal variations from multiple masked series.
WoVoGen: World Volume-aware Diffusion for Controllable Multi-camera Driving Scene Generation
Generating multi-camera street-view videos is critical for augmenting autonomous driving datasets, addressing the urgent demand for extensive and varied data.
Progressive Coordinate Transforms for Monocular 3D Object Detection
Recognizing and localizing objects in the 3D space is a crucial ability for an AI agent to perceive its surrounding environment.
Private Empirical Risk Minimization Beyond the Worst Case: The Effect of the Constraint Set Geometry
In addition, we show that when the loss function is Lipschitz with respect to the $\ell_1$ norm and $\mathcal{C}$ is $\ell_1$-bounded, a differentially private version of the Frank-Wolfe algorithm gives error bounds of the form $\tilde{O}(n^{-2/3})$.
Enhancing High-Resolution 3D Generation through Pixel-wise Gradient Clipping
In this framework, a significant challenge arises: To compute gradients for individual image pixels, it is necessary to backpropagate gradients from the designated latent space through the frozen components of the image model, such as the VAE encoder used within LDM.
Harnessing Diffusion Models for Visual Perception with Meta Prompts
Our key insight is to introduce learnable embeddings (meta prompts) to the pre-trained diffusion models to extract proper features for perception.
Ranked #2 on
Semantic Segmentation
on Cityscapes test
(using extra training data)
Reason2Drive: Towards Interpretable and Chain-based Reasoning for Autonomous Driving
Large vision-language models (VLMs) have garnered increasing interest in autonomous driving areas, due to their advanced capabilities in complex reasoning tasks essential for highly autonomous vehicle behavior.
Accelerating Score-based Generative Models with Preconditioned Diffusion Sampling
However, a fundamental limitation is that their inference is very slow due to a need for many (e. g., 2000) iterations of sequential computations.
Preconditioned Score-based Generative Models
Compared with the latest generative models (\eg, CLD-SGM, DDIM, and Analytic-DDIM), PDS can achieve the best sampling quality on CIFAR-10 at a FID score of 1. 99.
FashionViL: Fashion-Focused Vision-and-Language Representation Learning
We thus propose a Multi-View Contrastive Learning task for pulling closer the visual representation of one image to the compositional multimodal representation of another image+text.
LaneGraph2Seq: Lane Topology Extraction with Language Model via Vertex-Edge Encoding and Connectivity Enhancement
Accurate extraction of lane graphs relies on precisely estimating vertex and edge information within the DAG.
Translating Images to Road Network:A Non-Autoregressive Sequence-to-Sequence Approach
Instead, our work establishes a unified representation of both types of data domain by projecting both Euclidean and non-Euclidean data into an integer series called RoadNet Sequence.
Reversing the cycle: self-supervised deep stereo through enhanced monocular distillation
In many fields, self-supervised learning solutions are rapidly evolving and filling the gap with supervised approaches.
CoachLM: Automatic Instruction Revisions Improve the Data Quality in LLM Instruction Tuning
Instruction tuning is crucial for enabling Language Learning Models (LLMs) in responding to human instructions.
FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks
In the fashion domain, there exists a variety of vision-and-language (V+L) tasks, including cross-modal retrieval, text-guided image retrieval, multi-modal classification, and image captioning.
Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognition
Humans can easily recognize actions with only a few examples given, while the existing video recognition models still heavily rely on the large-scale labeled data inputs.
Ranked #1 on
Few Shot Action Recognition
on Kinetics-100
Efficient Semantic Scene Completion Network with Spatial Group Convolution
We introduce Spatial Group Convolution (SGC) for accelerating the computation of 3D dense prediction tasks.
Ranked #9 on
3D Semantic Scene Completion
on SemanticKITTI
NeRF-LiDAR: Generating Realistic LiDAR Point Clouds with Neural Radiance Fields
We verify the effectiveness of our NeRF-LiDAR by training different 3D segmentation models on the generated LiDAR point clouds.
Text-Based Person Search with Limited Data
Firstly, to fully utilize the existing small-scale benchmarking datasets for more discriminative feature learning, we introduce a cross-modal momentum contrastive learning framework to enrich the training data for a given mini-batch.
Ranked #10 on
Text based Person Retrieval
on CUHK-PEDES
(using extra training data)
Few-shot Action Recognition with Prototype-centered Attentive Learning
Extensive experiments on four standard few-shot action benchmarks show that our method clearly outperforms previous state-of-the-art methods, with the improvement particularly significant (10+\%) on the most challenging fine-grained action recognition benchmark.
Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation
The second step involves preserving dataset diversity through a clustering process. In our experiment, CaR selected a subset containing only 1. 96% of Alpaca's IT data, yet the underlying AlpaCaR model trained on this subset outperforms Alpaca by an average of 32. 1% in GPT-4 evaluations.
CholecTriplet2021: A benchmark challenge for surgical action triplet recognition
In this paper, we present the challenge setup and assessment of the state-of-the-art deep learning methods proposed by the participants during the challenge.
Ranked #1 on
Action Triplet Recognition
on CholecT50 (Challenge)
(using extra training data)
Language Models are Drummers: Drum Composition with Natural Language Pre-Training
Automatic music generation with artificial intelligence typically requires a large amount of data which is hard to obtain for many less common genres and musical instruments.
A Closed-form Solution to Universal Style Transfer
Although plenty of methods have been proposed, a theoretical analysis of feature transform is still missing.
Reasoning about Goals, Steps, and Temporal Ordering with WikiHow
We propose a suite of reasoning tasks on two types of relations between procedural events: goal-step relations ("learn poses" is a step in the larger goal of "doing yoga") and step-step temporal relations ("buy a yoga mat" typically precedes "learn poses").
Self-Asymmetric Invertible Network for Compression-Aware Image Rescaling
In this paper, we propose the Self-Asymmetric Invertible Network (SAIN) for compression-aware image rescaling.
Dynamic Graph Message Passing Networks
We propose a dynamic graph message passing network, that significantly reduces the computational complexity compared to related works modelling a fully-connected graph.
Dynamic Graph Message Passing Networks for Visual Recognition
A fully-connected graph, such as the self-attention operation in Transformers, is beneficial for such modelling, however, its computational overhead is prohibitive.
What Deep CNNs Benefit from Global Covariance Pooling: An Optimization Perspective
Recent works have demonstrated that global covariance pooling (GCP) has the ability to improve performance of deep convolutional neural networks (CNNs) on visual classification task.
Bidirectional Self-Training with Multiple Anisotropic Prototypes for Domain Adaptive Semantic Segmentation
A thriving trend for domain adaptive segmentation endeavors to generate the high-quality pseudo labels for target domain and retrain the segmentor on them.
Direct Speech-to-image Translation
In this paper, we attempt to translate the speech signals into the image signals without the transcription stage.
Multimedia Sound Audio and Speech Processing
QVRF: A Quantization-error-aware Variable Rate Framework for Learned Image Compression
In this paper, we present a Quantization-error-aware Variable Rate Framework (QVRF) that utilizes a univariate quantization regulator a to achieve wide-range variable rates within a single model.
Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection
The objective of this paper is to learn context- and depth-aware feature representation to solve the problem of monocular 3D object detection.
Ranked #13 on
Monocular 3D Object Detection
on KITTI Cars Moderate
Learning Dynamic Alignment via Meta-filter for Few-shot Learning
Our insight is that these methods would lead to poor adaptation with redundant matching, and leveraging channel-wise adjustment is the key to well adapting the learned knowledge to new classes.
Universal Adversarial Perturbations Generative Network for Speaker Recognition
Attacking deep learning based biometric systems has drawn more and more attention with the wide deployment of fingerprint/face/speaker recognition systems, given the fact that the neural networks are vulnerable to the adversarial examples, which have been intentionally perturbed to remain almost imperceptible for human.
SGM3D: Stereo Guided Monocular 3D Object Detection
Monocular 3D object detection aims to predict the object location, dimension and orientation in 3D space alongside the object category given only a monocular image.
UIGR: Unified Interactive Garment Retrieval
In this paper, we propose a Unified Interactive Garment Retrieval (UIGR) framework to unify TGR and VCR.
Diffusion$^2$: Dynamic 3D Content Generation via Score Composition of Orthogonal Diffusion Models
Recent advancements in 3D generation are predominantly propelled by improvements in 3D-aware image diffusion models which are pretrained on Internet-scale image data and fine-tuned on massive 3D data, offering the capability of producing highly consistent multi-view images.
PGU-net+: Progressive Growing of U-net+ for Automated Cervical Nuclei Segmentation
The experimental results show that the PGU-net+ has superior accuracy than the previous state-of-the-art methods on cervical nuclei segmentation.
OpenPI2.0: An Improved Dataset for Entity Tracking in Texts
An earlier dataset, OpenPI, provided crowdsourced annotations of entity state changes in text.
What Makes for Automatic Reconstruction of Pulmonary Segments
The automatic reconstruction of pulmonary segments by ImPulSe is accurate in metrics and visually appealing.
S-Agents: Self-organizing Agents in Open-ended Environments
Leveraging large language models (LLMs), autonomous agents have significantly improved, gaining the ability to handle a variety of tasks.
MVB: A Large-Scale Dataset for Baggage Re-Identification and Merged Siamese Networks
Second, all baggage images are captured by specially-designed multi-view camera system to handle pose variation and occlusion, in order to obtain the 3D information of baggage surface as complete as possible.
Region-Aware Metric Learning for Open World Semantic Segmentation via Meta-Channel Aggregation
Therefore, we propose a method called region-aware metric learning (RAML), which first separates the regions of the images and generates region-aware features for further metric learning.
Multi-Depth Branch Network for Efficient Image Super-Resolution
We visualize this process using feature maps, and further demonstrate the rationality and effectiveness of this design using proposed novel Fourier spectral analysis methods.
Show Me More Details: Discovering Hierarchies of Procedures from Semi-structured Web Data
To this end, we develop a simple and efficient method that links steps (e. g., "purchase a camera") in an article to other articles with similar goals (e. g., "how to choose a camera"), recursively constructing the KB.
Model-Guided Multi-Contrast Deep Unfolding Network for MRI Super-resolution Reconstruction
Interpretable neural network models are of significant interest since they enhance the trustworthiness required in clinical practice when dealing with medical images.
Causal Reasoning of Entities and Events in Procedural Texts
By injecting the causal relations between entities and events as intermediate reasoning steps in our representation, we further boost the performance to . 67 F1.
Learn to Interpret Atari Agents
Deep reinforcement learning (DeepRL) agents surpass human-level performance in many tasks.
Boundary-sensitive Pre-training for Temporal Localization in Videos
However, most existing models developed for these tasks are pre-trained on general video action classification tasks.
Ranked #23 on
Temporal Action Localization
on ActivityNet-1.3
Visual Goal-Step Inference using wikiHow
Understanding what sequence of steps are needed to complete a goal can help artificial intelligence systems reason about human activities.
Ranked #1 on
VGSI
on wikiHow-image
Learning to fool the speaker recognition
Due to the widespread deployment of fingerprint/face/speaker recognition systems, attacking deep learning based biometric systems has drawn more and more attention.
Audio and Speech Processing Cryptography and Security Sound
Intent Detection with WikiHow
Modern task-oriented dialog systems need to reliably understand users' intents.
EEGMatch: Learning with Incomplete Labels for Semi-Supervised EEG-based Cross-Subject Emotion Recognition
The results show the proposed EEGmatch performs better than the state-of-the-art methods under different incomplete label conditions (with 6. 89% improvement on SEED and 1. 44% improvement on SEED-IV), which demonstrates the effectiveness of the proposed EEGMatch in dealing with the label scarcity problem in emotion recognition using EEG signals.
Graph Node-Feature Convolution for Representation Learning
Graph convolutional network (GCN) is an emerging neural network approach.
Improving Weakly-supervised Object Localization via Causal Intervention
The recent emerged weakly supervised object localization (WSOL) methods can learn to localize an object in the image only using image-level labels.
DGDNN: Decoupled Graph Diffusion Neural Network for Stock Movement Prediction
Moreover, the ablation study and sensitivity study further illustrate the effectiveness of the proposed method in modeling the time-evolving inter-stock and intra-stock dynamics.
Automated Segmentation of Cervical Nuclei in Pap Smear Images using Deformable Multi-path Ensemble Model
Pap smear testing has been widely used for detecting cervical cancers based on the morphology properties of cell nuclei in microscopic image.
Goal-Oriented Script Construction
The knowledge of scripts, common chains of events in stereotypical scenarios, is a valuable asset for task-oriented natural language understanding systems.
Multi-Scale Context-Guided Lumbar Spine Disease Identification with Coarse-to-fine Localization and Classification
Accurate and efficient lumbar spine disease identification is crucial for clinical diagnosis.
Nonlinear Intensity, Scale and Rotation Invariant Matching for Multimodal Images
We present an effective method for the matching of multimodal images.
PARTNER: Level up the Polar Representation for LiDAR 3D Object Detection
Recently, polar-based representation has shown promising properties in perceptual tasks.
Few-shot Action Recognition with Permutation-invariant Attention
Such encoded blocks are aggregated by permutation-invariant pooling to make our approach robust to varying action lengths and long-range temporal dependencies whose patterns are unlikely to repeat even in clips of the same class.
Ranked #6 on
Few Shot Action Recognition
on Kinetics-100
Is "My Favorite New Movie" My Favorite Movie? Probing the Understanding of Recursive Noun Phrases
We introduce the Recursive Noun Phrase Challenge (RNPC), a dataset of three textual inference tasks involving textual entailment and event plausibility comparison, precisely targeting the understanding of recursive NPs.
Improved Dense Nested Attention Network Based on Transformer for Infrared Small Target Detection
To address this issue, we propose a novel method for detecting infrared small targets called improved dense nested attention network (IDNANet), which is based on the transformer architecture.
Towards Optimal Filter Pruning with Balanced Performance and Pruning Speed
In this paper, we propose a balanced filter pruning method for both performance and pruning speed.
Probabilistic computation and uncertainty quantification with emerging covariance
Building robust, interpretable, and secure AI system requires quantifying and representing uncertainty under a probabilistic perspective to mimic human cognitive abilities.
Scale-aware Test-time Click Adaptation for Pulmonary Nodule and Mass Segmentation
Extensive experiments on both open-source and in-house datasets consistently demonstrate the effectiveness of the proposed method over some CNN and Transformer-based segmentation methods.
Automatically detecting the conflicts between software requirements based on finer semantic analysis
Besides, our approach is capable of transforming the natural language functional requirements into eight semantic tuples, which is useful not only the detection of the conflicts between requirements but also some other tasks such as constructing the association between requirements and so on.
Label Definitions Improve Semantic Role Labeling
Given a sentence and the predicate, a semantic role label is assigned to each argument of the predicate.
Spatial Language Representation with Multi-Level Geocoding
We present a multi-level geocoding model (MLG) that learns to associate texts to geographic locations.
In-Orbit Instrument Performance Study and Calibration for POLAR Polarization Measurements
POLAR is a compact space-borne detector designed to perform reliable measurements of the polarization for transient sources like Gamma-Ray Bursts in the energy range 50-500keV.
Instrumentation and Methods for Astrophysics High Energy Physics - Experiment Instrumentation and Detectors
Semantic Discord: Finding Unusual Local Patterns for Time Series
Finding anomalous subsequence in a long time series is a very important but difficult problem.
Analyze Gauss: Optimal Bounds for Privacy-Preserving Principal Component Analysis
We show that the well-known, but misnamed, randomized response algorithm, with properly tuned parameters, provides a nearly optimal additive quality gap compared to the best possible singular subspace of A.
Modular Blind Video Quality Assessment
Blind video quality assessment (BVQA) plays a pivotal role in evaluating and improving the viewing experience of end-users across a wide range of video-based platforms and services.
Generalizable and Stable Finetuning of Pretrained Language Models on Low-Resource Texts
Pretrained Language Models (PLMs) have advanced Natural Language Processing (NLP) tasks significantly, but finetuning PLMs on low-resource datasets poses significant challenges such as instability and overfitting.
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.
Persistent Animal Identification Leveraging Non-Visual Markers
Our objective is to locate and provide a unique identifier for each mouse in a cluttered home-cage environment through time, as a precursor to automated behaviour recognition for biological research.
Exploring the Curious Case of Code Prompts
Furthermore, we show that the style of code prompt has a large effect on performance for some but not all tasks and that fine-tuning on text instructions leads to better relative performance of code prompts.
Multi-Label Transfer Learning for Multi-Relational Semantic Similarity
Multi-relational semantic similarity datasets define the semantic relations between two short texts in multiple ways, e. g., similarity, relatedness, and so on.
Direct Network Transfer: Transfer Learning of Sentence Embeddings for Semantic Similarity
Sentence encoders, which produce sentence embeddings using neural networks, are typically evaluated by how well they transfer to downstream tasks.
Cascaded multi-scale and multi-dimension convolutional neural network for stereo matching
Firstly, we propose a new multi-scale matching cost computation sub-network, in which two different sizes of receptive fields are implemented parallelly.
Algorithmic Collusion in Cournot Duopoly Market: Evidence from Experimental Economics
In application, we hope, the frameworks, the algorithm design as well as the experiment environment illustrated in this work, can be an incubator or a test bed for researchers and policymakers to handle the emerging algorithmic collusion.
Actor-Critic Sequence Training for Image Captioning
Generating natural language descriptions of images is an important capability for a robot or other visual-intelligence driven AI agent that may need to communicate with human users about what it is seeing.
GaDei: On Scale-up Training As A Service For Deep Learning
By evaluating the NLC workloads, we show that only the conservative hyper-parameter setup (e. g., small mini-batch size and small learning rate) can guarantee acceptable model accuracy for a wide range of customers.
On the Protection of Private Information in Machine Learning Systems: Two Recent Approaches
The recent, remarkable growth of machine learning has led to intense interest in the privacy of the data on which machine learning relies, and to new techniques for preserving privacy.
Motion Feature Augmented Recurrent Neural Network for Skeleton-based Dynamic Hand Gesture Recognition
Dynamic hand gesture recognition has attracted increasing interests because of its importance for human computer interaction.
Ranked #6 on
Hand Gesture Recognition
on DHG-28
TAPAS: Two-pass Approximate Adaptive Sampling for Softmax
TAPAS is a novel adaptive sampling method for the softmax model.
Physics Inspired Optimization on Semantic Transfer Features: An Alternative Method for Room Layout Estimation
In this paper, we propose an alternative method to estimate room layouts of cluttered indoor scenes.
Learning to Learn: Meta-Critic Networks for Sample Efficient Learning
We propose a novel and flexible approach to meta-learning for learning-to-learn from only a few examples.
Classification of Neurological Gait Disorders Using Multi-task Feature Learning
An advanced machine learning method, multi-task feature learning (MTFL), is used to jointly train classification models of a subject's gait in three classes, post-stroke, PD and healthy gait.
Real-Time Visual Tracking: Promoting the Robustness of Correlation Filter Learning
By exploiting the anisotropy of the filter response, three sparsity related loss functions are proposed to alleviate the overfitting issue of previous methods and improve the overall tracking performance.
Tracking Completion
A fundamental component of modern trackers is an online learned tracking model, which is typically modeled either globally or locally.
Learning a Discriminative Null Space for Person Re-identification
Most existing person re-identification (re-id) methods focus on learning the optimal distance metrics across camera views.
Ranked #116 on
Person Re-Identification
on Market-1501
Differentially Private False Discovery Rate Control
Differential privacy provides a rigorous framework for privacy-preserving data analysis.
Efficient Training on Very Large Corpora via Gramian Estimation
We study the problem of learning similarity functions over very large corpora using neural network embedding models.
Automated segmentaiton and classification of arterioles and venules using Cascading Dilated Convolutional Neural Networks
The change of retinal vasculature is an early sign of many vascular and systematic diseases, such as diabetes and hypertension.
Nearly Optimal Private LASSO
In addition, we show that this error bound is nearly optimal amongst all differentially private algorithms.
CAN: Constrained Attention Networks for Multi-Aspect Sentiment Analysis
Aspect level sentiment classification is a fine-grained sentiment analysis task.
Depth creates no more spurious local minima
We show that for any convex differentiable loss, a deep linear network has no spurious local minima as long as it is true for the two layer case.
Exemplar-Based Face Parsing
Given a test image, our algorithm first selects a subset of exemplar images from the database, Our algorithm then computes a nonrigid warp for each exemplar image to align it with the test image.
Nonparametric Context Modeling of Local Appearance for Pose- and Expression-Robust Facial Landmark Localization
We propose a data-driven approach to facial landmark localization that models the correlations between each landmark and its surrounding appearance features.
Discriminative Low-Rank Tracking
Good tracking performance is in general attributed to accurate representation over previously obtained targets or reliable discrimination between the target and the surrounding background.
Decoder Network Over Lightweight Reconstructed Feature for Fast Semantic Style Transfer
Our method decomposes the semantic style transfer problem into feature reconstruction part and feature decoder part.
Field-aware Neural Factorization Machine for Click-Through Rate Prediction
This model can have strong second order feature interactive learning ability like Field-aware Factorization Machine, on this basis, deep neural network is used for higher-order feature combination learning.
Monte Carlo Neural Fictitious Self-Play: Approach to Approximate Nash equilibrium of Imperfect-Information Games
Experimentally, we demonstrate that the proposed Monte Carlo Neural Fictitious Self Play can converge to approximate Nash equilibrium in games with large-scale search depth while the Neural Fictitious Self Play can't.
Deep Learning based Pedestrian Detection at Distance in Smart Cities
Generative adversarial networks (GANs) have been promising for many computer vision problems due to their powerful capabilities to enhance the data for training and test.
Hierarchical method for cataract grading based on retinal images using improved Haar wavelet
In this paper, a feature extraction-based method for grading cataract severity using retinal images is proposed.
Automated Segmentation of Pulmonary Lobes using Coordination-Guided Deep Neural Networks
The proposed model is trained and evaluated on a few publicly available datasets and has achieved the state-of-the-art accuracy with a mean Dice coefficient index of 0. 947 $\pm$ 0. 044.
Jointly Learning Structured Analysis Discriminative Dictionary and Analysis Multiclass Classifier
Then we compute a linear classifier based on the approximated sparse codes by an analysis mechanism to simultaneously consider the classification and representation powers.
Distant Pedestrian Detection in the Wild using Single Shot Detector with Deep Convolutional Generative Adversarial Networks
In our work, GAN has been trained intensively on low resolution images, in order to neutralize the challenges of the pedestrian detection in the wild, and considered humans, and few other classes for detection in smart cities.
End-to-End Learning of Multi-scale Convolutional Neural Network for Stereo Matching
To tackle this problem, we propose a network for disparity estimation based on abundant contextual details and semantic information, called Multi-scale Features Network (MSFNet).
ASCNet: Adaptive-Scale Convolutional Neural Networks for Multi-Scale Feature Learning
Such pixel-level dilation rates produce optimal receptive fields so that the information of objects with different sizes can be extracted at the corresponding scale.
Multi-level Domain Adaptive learning for Cross-Domain Detection
In recent years, object detection has shown impressive results using supervised deep learning, but it remains challenging in a cross-domain environment.
Annotation-Free Cardiac Vessel Segmentation via Knowledge Transfer from Retinal Images
Segmenting coronary arteries is challenging, as classic unsupervised methods fail to produce satisfactory results and modern supervised learning (deep learning) requires manual annotation which is often time-consuming and can some time be infeasible.
A cascaded dual-domain deep learning reconstruction method for sparsely spaced multidetector helical CT
This step is to suppress helical artifacts and reduce the following computational cost.
Large-scale Gastric Cancer Screening and Localization Using Multi-task Deep Neural Network
Gastric cancer is one of the most common cancers, which ranks third among the leading causes of cancer death.
Discriminative Local Sparse Representation by Robust Adaptive Dictionary Pair Learning
In this paper, we propose a structured Robust Adaptive Dic-tionary Pair Learning (RA-DPL) framework for the discrim-inative sparse representation learning.
Unsupervised Learnable Sinogram Inpainting Network (SIN) for Limited Angle CT reconstruction
In this paper, we propose a sinogram inpainting network (SIN) to solve limited-angle CT reconstruction problem, which is a very challenging ill-posed issue and of great interest for several clinical applications.
Medical Physics Image and Video Processing
Deep Self-representative Concept Factorization Network for Representation Learning
In this paper, we investigate the unsupervised deep representation learning issue and technically propose a novel framework called Deep Self-representative Concept Factorization Network (DSCF-Net), for clustering deep features.
Automatic marker-free registration of tree point-cloud data based on rotating projection
In coarse registration, point clouds produced by each scan are projected onto a spherical surface to generate a series of two-dimensional (2D) images, which are used to estimate the initial positions of multiple scans.
Selective Convolutional Network: An Efficient Object Detector with Ignoring Background
It is well known that attention mechanisms can effectively improve the performance of many CNNs including object detectors.
Superbloom: Bloom filter meets Transformer
We extend the idea of word pieces in natural language models to machine learning tasks on opaque ids.
Feedback Graph Convolutional Network for Skeleton-based Action Recognition
It transmits the high-level semantic features to the low-level layers and flows temporal information stage by stage to progressively model global spatial-temporal features for action recognition; (3) The FGCN model provides early predictions.
Ranked #34 on
Skeleton Based Action Recognition
on NTU RGB+D 120
In-Vehicle Object Detection in the Wild for Driverless Vehicles
In-vehicle human object identification plays an important role in vision-based automated vehicle driving systems while objects such as pedestrians and vehicles on roads or streets are the primary targets to protect from driverless vehicles.
3D Printed Brain-Controlled Robot-Arm Prosthetic via Embedded Deep Learning from sEMG Sensors
In this paper, we present our work on developing robot arm prosthetic via deep learning.
A Survey on Deep Learning for Neuroimaging-based Brain Disorder Analysis
Deep learning has been recently used for the analysis of neuroimages, such as structural magnetic resonance imaging (MRI), functional MRI, and positron emission tomography (PET), and has achieved significant performance improvements over traditional machine learning in computer-aided diagnosis of brain disorders.
SentPWNet: A Unified Sentence Pair Weighting Network for Task-specific Sentence Embedding
Our model, SentPWNet, exploits the neighboring spatial distribution of each sentence as locality weight to indicate the informative level of sentence pair.
Long-Term Cloth-Changing Person Re-identification
Specifically, we consider that under cloth-changes, soft-biometrics such as body shape would be more reliable.
Self-supervised Video Object Segmentation
The objective of this paper is self-supervised representation learning, with the goal of solving semi-supervised video object segmentation (a. k. a.
Egocentric Action Recognition by Video Attention and Temporal Context
In this challenge, action recognition is posed as the problem of simultaneously predicting a single `verb' and `noun' class label given an input trimmed video clip.
A novel deep learning-based method for monochromatic image synthesis from spectral CT using photon-counting detectors
To solve this problem, in this paper, we proposed a novel deep learning-based monochromatic image synthesis method working in sinogram domain.
Learning-based Computer-aided Prescription Model for Parkinson's Disease: A Data-driven Perspective
Then, we build a novel computer-aided prescription model by learning the relation between observed symptoms and prescription drug.
A Survey on Concept Factorization: From Shallow to Deep Representation Learning
In this paper, we therefore survey the recent advances on CF methodologies and the potential benchmarks by categorizing and summarizing the current methods.
PriceAggregator: An Intelligent System for Hotel Price Fetching
The major challenge is that each supplier only allows Agoda to fetch for the hotel price with a limited amount of Queries Per Second (QPS).
Zero-Shot Heterogeneous Transfer Learning from Recommender Systems to Cold-Start Search Retrieval
In light of these problems, we observed that most online content platforms have both a search and a recommender system that, while having heterogeneous input spaces, can be connected through their common output item space and a shared semantic representation.
Dual-constrained Deep Semi-Supervised Coupled Factorization Network with Enriched Prior
Nonnegative matrix factorization is usually powerful for learning the "shallow" parts-based representation, but it clearly fails to discover deep hierarchical information within both the basis and representation spaces.
Small but Mighty: New Benchmarks for Split and Rephrase
Split and Rephrase is a text simplification task of rewriting a complex sentence into simpler ones.
Holistic Grid Fusion Based Stop Line Estimation
Intersection scenarios provide the most complex traffic situations in Autonomous Driving and Driving Assistance Systems.
LID 2020: The Learning from Imperfect Data Challenge Results
The purpose of the Learning from Imperfect Data (LID) workshop is to inspire and facilitate the research in developing novel approaches that would harness the imperfect data and improve the data-efficiency during training.
Skin disease diagnosis with deep learning: a review
As an important part of this article, we then review the literature involving deep learning methods for skin disease diagnosis from several aspects according to the specific tasks.
Rankmax: An Adaptive Projection Alternative to the Softmax Function
Several machine learning models involve mapping a score vector to a probability vector.
Direct Classification of Emotional Intensity
In this paper, we present a model that can directly predict emotion intensity score from video inputs, instead of deriving from action units.
Searching for Quasi-Periodic Modulations in $γ$-ray Active Galactic Nuclei
We perform a systematic search of quasi-periodic variabilities in $\gamma$-ray active galactic nuclei (AGNs) in the third \emph{Fermi} Large Area Telescope source catalog (3FGL).
High Energy Astrophysical Phenomena
A Systematic Literature Review on Federated Learning: From A Model Quality Perspective
In this process, the server uses an incentive mechanism to encourage clients to contribute high-quality and large-volume data to improve the global model.
Hop-Hop Relation-aware Graph Neural Networks
Graph Neural Networks (GNNs) are widely used in graph representation learning.
Unifying Homophily and Heterophily Network Transformation via Motifs
Because H2NT can sparsify networks with motif structures, it can also improve the computational efficiency of existing network embedding methods when integrated.
