Search Results for author:
Found 99 papers, 31 papers with code
End-to-End Image Super-Resolution via Deep and Shallow Convolutional Networks
In this paper, we seek an alternative and propose a new image SR method, which jointly learns the feature extraction, upsampling and HR reconstruction modules, yielding a completely end-to-end trainable deep CNN.
(2,2) Superconformal Bootstrap in Two Dimensions
We find a simple relation between two-dimensional BPS N=2 superconformal blocks and bosonic Virasoro conformal blocks, which allows us to analyze the crossing equations for BPS 4-point functions in unitary (2, 2) superconformal theories numerically with semidefinite programming.
High Energy Physics - Theory
Learning to Detect Salient Objects With Image-Level Supervision
In the second stage, FIN is fine-tuned with its predicted saliency maps as ground truth.
MarrNet: 3D Shape Reconstruction via 2.5D Sketches
First, compared to full 3D shape, 2. 5D sketches are much easier to be recovered from a 2D image; models that recover 2. 5D sketches are also more likely to transfer from synthetic to real data.
Ranked #2 on
3D Shape Classification
on Pix3D
3D Object Reconstruction From A Single Image
3D Reconstruction
+3
Identifying Outlier Arms in Multi-Armed Bandit
Outlier detection is a powerful method to narrow down the attention to a few objects after the data for them are collected.
A Fully Progressive Approach to Single-Image Super-Resolution
Recent deep learning approaches to single image super-resolution have achieved impressive results in terms of traditional error measures and perceptual quality.
Ranked #14 on
Image Super-Resolution
on BSD100 - 4x upscaling
CAVBench: A Benchmark Suite for Connected and Autonomous Vehicles
Meanwhile, several pioneer efforts have focused on the edge computing system and architecture design for the CAVs scenario and provided various heterogeneous platform prototypes for CAVs.
Distributed, Parallel, and Cluster Computing Performance
Modeling and Predicting Citation Count via Recurrent Neural Network with Long Short-Term Memory
The rapid evolution of scientific research has been creating a huge volume of publications every year.
Digital Libraries Physics and Society
Dual Principal Component Pursuit: Improved Analysis and Efficient Algorithms
However, its geometric analysis is based on quantities that are difficult to interpret and are not amenable to statistical analysis.
Dual Principal Component Pursuit: Probability Analysis and Efficient Algorithms
However, its geometric analysis is based on quantities that are difficult to interpret and are not amenable to statistical analysis.
Session-based Social Recommendation via Dynamic Graph Attention Networks
However, recommendation in online communities is a challenging problem: 1) users' interests are dynamic, and 2) users are influenced by their friends.
Ranked #1 on
Recommendation Systems
on Douban
(NDCG metric)
OpenEI: An Open Framework for Edge Intelligence
At the same time, we have witnessed the proliferation of AI algorithms and models which accelerate the successful deployment of intelligence mainly in cloud services.
pCAMP: Performance Comparison of Machine Learning Packages on the Edges
However, little research has been done to evaluate these packages on the edges, making it difficult for end users to select an appropriate pair of software and hardware.
PointHop++: A Lightweight Learning Model on Point Sets for 3D Classification
The PointHop method was recently proposed by Zhang et al. for 3D point cloud classification with unsupervised feature extraction.
Attention: to Better Stand on the Shoulders of Giants
In the progress of science, the previously discovered knowledge principally inspires new scientific ideas, and citation is a reasonably good reflection of this cumulative nature of scientific research.
Learning to Parse Wireframes in Images of Man-Made Environments
To this end, we have built a very large new dataset of over 5, 000 images with wireframes thoroughly labelled by humans.
People as Scene Probes
By analyzing the motion of people and other objects in a scene, we demonstrate how to infer depth, occlusion, lighting, and shadow information from video taken from a single camera viewpoint.
FaceHop: A Light-Weight Low-Resolution Face Gender Classification Method
For gray-scale face images of resolution $32 \times 32$ in the LFW and the CMU Multi-PIE datasets, FaceHop achieves correct gender classification rates of 94. 63% and 95. 12% with model sizes of 16. 9K and 17. 6K parameters, respectively.
VC-Net: Deep Volume-Composition Networks for Segmentation and Visualization of Highly Sparse and Noisy Image Data
A multi-stream convolutional neural network is proposed to learn the 3D volume and 2D MIP features respectively and then explore their inter-dependencies in a joint volume-composition embedding space by unprojecting the MIP features into 3D volume embedding space.
Low-Resolution Face Recognition In Resource-Constrained Environments
A non-parametric low-resolution face recognition model for resource-constrained environments with limited networking and computing is proposed in this work.
Surface Defect, Anomalies and $b$-Extremization
The $b$-theorem states that $b$ must monotonically decrease under defect RG flows and was proven by coupling to a spurious defect dilaton.
High Energy Physics - Theory
Anomalous Symmetries End at the Boundary
We then recast the problem in terms of symmetry defects and find the same conclusions for anomalies of discrete and orientation-reversing global symmetries, up to the conjecture that global gravitational anomalies, which may not be associated with any diffeomorphism symmetry, also forbid the existence of boundary conditions.
High Energy Physics - Theory Strongly Correlated Electrons
Can Scale-Consistent Monocular Depth Be Learned in a Self-Supervised Scale-Invariant Manner?
The integration of SAG loss and two-stream network enables more consistent scale inference and more accurate relative depth estimation.
Defect $a$-Theorem and $a$-Maximization
We derive the anomaly multiplet relations that express the defect $a$- and $c$-anomalies in terms of the defect (mixed) 't Hooft anomalies for this $U(1)_R$ symmetry.
High Energy Physics - Theory
Repopulating Street Scenes
We present a framework for automatically reconfiguring images of street scenes by populating, depopulating, or repopulating them with objects such as pedestrians or vehicles.
DynOcc: Learning Single-View Depth from Dynamic Occlusion Cues
Recently, significant progress has been made in single-view depth estimation thanks to increasingly large and diverse depth datasets.
SGG: Learning to Select, Guide, and Generate for Keyphrase Generation
Keyphrases, that concisely summarize the high-level topics discussed in a document, can be categorized into present keyphrase which explicitly appears in the source text, and absent keyphrase which does not match any contiguous subsequence but is highly semantically related to the source.
DisenHAN: Disentangled Heterogeneous Graph Attention Network for Recommendation
In this paper, we propose a novel disentangled heterogeneous graph attention network DisenHAN for top-$N$ recommendation, which learns disentangled user/item representations from different aspects in a heterogeneous information network.
CUSTOM: Aspect-Oriented Product Summarization for E-Commerce
To address the problem, we propose CUSTOM, aspect-oriented product summarization for e-commerce, which generates diverse and controllable summaries towards different product aspects.
RoR: Read-over-Read for Long Document Machine Reading Comprehension
To address this problem, we propose RoR, a read-over-read method, which expands the reading field from chunk to document.
Advances in Neural Rendering
The reconstruction of such a scene representation from observations using differentiable rendering losses is known as inverse graphics or inverse rendering.
Multi-Source Uncertainty Mining for Deep Unsupervised Saliency Detection
We design an Uncertainty Mining Network (UMNet) which consists of multiple Merge-and-Split (MS) modules to recursively analyze the commonality and difference among multiple noisy labels and infer pixel-wise uncertainty map for each label.
MuSCLe: A Multi-Strategy Contrastive Learning Framework for Weakly Supervised Semantic Segmentation
Weakly supervised semantic segmentation (WSSS) has gained significant popularity since it relies only on weak labels such as image level annotations rather than pixel level annotations required by supervised semantic segmentation (SSS) methods.
Multiscale Convolutional Transformer with Center Mask Pretraining for Hyperspectral Image Classification
However, CNN-based methods are difficult to capture long-range dependencies, and also require a large amount of labeled data for model training. Besides, most of the self-supervised training methods in the field of HSI classification are based on the reconstruction of input samples, and it is difficult to achieve effective use of unlabeled samples.
Back to Reality: Weakly-supervised 3D Object Detection with Shape-guided Label Enhancement
In this paper, we propose a weakly-supervised approach for 3D object detection, which makes it possible to train a strong 3D detector with position-level annotations (i. e. annotations of object centers).
Fine- and Coarse-Granularity Hybrid Self-Attention for Efficient BERT
To confront this, we propose FCA, a fine- and coarse-granularity hybrid self-attention that reduces the computation cost through progressively shortening the computational sequence length in self-attention.
SunStage: Portrait Reconstruction and Relighting using the Sun as a Light Stage
Our method only requires the user to capture a selfie video outdoors, rotating in place, and uses the varying angles between the sun and the face as guidance in joint reconstruction of facial geometry, reflectance, camera pose, and lighting parameters.
A Survey on Efficient Processing of Similarity Queries over Neural Embeddings
Embedding techniques work by representing the raw data objects as vectors (so called "embeddings" or "neural embeddings" since they are mostly generated by neural network models) that expose the hidden semantics of the raw data, based on which embeddings do show outstanding effectiveness on capturing data similarities, making it one of the most widely used and studied techniques in the state-of-the-art similarity query processing research.
OPERA:Operation-Pivoted Discrete Reasoning over Text
To inherit the advantages of these two types of methods, we propose OPERA, an operation-pivoted discrete reasoning framework, where lightweight symbolic operations (compared with logical forms) as neural modules are utilized to facilitate the reasoning ability and interpretability.
LIDER: An Efficient High-dimensional Learned Index for Large-scale Dense Passage Retrieval
As the basic unit of LIDER to index and search data, a core model includes an adapted recursive model index (RMI) and a dimension reduction component which consists of an extended SortingKeys-LSH (SK-LSH) and a key re-scaling module.
LUNA: Learning Slot-Turn Alignment for Dialogue State Tracking
Dialogue state tracking (DST) aims to predict the current dialogue state given the dialogue history.
Learnability of Competitive Threshold Models
Modeling the spread of social contagions is central to various applications in social computing.
A Survey on the Fairness of Recommender Systems
First, we summarize fairness definitions in the recommendation and provide several views to classify fairness issues.
Vertical GaN Diode BV Maximization through Rapid TCAD Simulation and ML-enabled Surrogate Model
In this paper, two methodologies are used to speed up the maximization of the breakdown volt-age (BV) of a vertical GaN diode that has a theoretical maximum BV of ~2100V.
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.
A Knowledge Distillation-Based Backdoor Attack in Federated Learning
With knowledge distillation, we can reduce the abnormal characteristics in model result from the label flipping, thus the model can bypass the defenses.
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.
Learning the Propagation of Worms in Wireless Sensor Networks
Wireless sensor networks (WSNs) are composed of spatially distributed sensors and are considered vulnerable to attacks by worms and their variants.
Deep-Steiner: Learning to Solve the Euclidean Steiner Tree Problem
The Euclidean Steiner tree problem seeks the min-cost network to connect a collection of target locations, and it underlies many applications of wireless networks.
Lightweight Image Codec via Multi-Grid Multi-Block-Size Vector Quantization (MGBVQ)
The fundamental idea of image coding is to remove correlations among pixels before quantization and entropy coding, e. g., the discrete cosine transform (DCT) and intra predictions, adopted by modern image coding standards.
Kernel-based Substructure Exploration for Next POI Recommendation
To tackle the above issues, we propose a Kernel-Based Graph Neural Network (KBGNN) for next POI recommendation, which combines the characteristics of both geographical and sequential influences in a collaborative way.
P$^3$LM: Probabilistically Permuted Prophet Language Modeling for Generative Pre-Training
Conventional autoregressive left-to-right (L2R) sequence generation faces two issues during decoding: limited to unidirectional target sequence modeling, and constrained on strong local dependencies.
DisenPOI: Disentangling Sequential and Geographical Influence for Point-of-Interest Recommendation
Point-of-Interest (POI) recommendation plays a vital role in various location-aware services.
Bandit Algorithms for Prophet Inequality and Pandora's Box
The goal is to minimize the regret, which is the difference over $T$ rounds in the total value of the optimal algorithm that knows the distributions vs. the total value of our algorithm that learns the distributions from the partial feedback.
Controlling Styles in Neural Machine Translation with Activation Prompt
Controlling styles in neural machine translation (NMT) has attracted wide attention, as it is crucial for enhancing user experience.
Automatic Generation of German Drama Texts Using Fine Tuned GPT-2 Models
The input for the neural model comprises two datasets: the German Drama Corpus (GerDraCor) and German Text Archive (Deutsches Textarchiv or DTA).
Unsupervised Mandarin-Cantonese Machine Translation
Advancements in unsupervised machine translation have enabled the development of machine translation systems that can translate between languages for which there is not an abundance of parallel data available.
Learned Accelerator Framework for Angular-Distance-Based High-Dimensional DBSCAN
In this paper, we propose LAF, a generic learned accelerator framework to speed up the original DBSCAN and the sampling-based variants of DBSCAN on high-dimensional data with angular distance metric.
A Comprehensive Survey on Deep Graph Representation Learning
Graph representation learning aims to effectively encode high-dimensional sparse graph-structured data into low-dimensional dense vectors, which is a fundamental task that has been widely studied in a range of fields, including machine learning and data mining.
TGNN: A Joint Semi-supervised Framework for Graph-level Classification
The two twin modules collaborate with each other by exchanging instance similarity knowledge to fully explore the structure information of both labeled and unlabeled data.
LumiGAN: Unconditional Generation of Relightable 3D Human Faces
Unsupervised learning of 3D human faces from unstructured 2D image data is an active research area.
VTPNet for 3D deep learning on point cloud
Recently, Transformer-based methods for point cloud learning have achieved good results on various point cloud learning benchmarks.
Joint Channel Estimation and Turbo Equalization of Single-Carrier Systems over Time-Varying Channels
Block transmission systems have been proven successful over frequency-selective channels.
BEV-IO: Enhancing Bird's-Eye-View 3D Detection with Instance Occupancy
At the core of our method is the newly-designed instance occupancy prediction (IOP) module, which aims to infer point-level occupancy status for each instance in the frustum space.
Incorporating Distributions of Discourse Structure for Long Document Abstractive Summarization
For text summarization, the role of discourse structure is pivotal in discerning the core content of a text.
NeuS-PIR: Learning Relightable Neural Surface using Pre-Integrated Rendering
This paper presents a method, namely NeuS-PIR, for recovering relightable neural surfaces using pre-integrated rendering from multi-view images or video.
Detector-Free Structure from Motion
We propose a new detector-free SfM framework to draw benefits from the recent success of detector-free matchers to avoid the early determination of keypoints, while solving the multi-view inconsistency issue of detector-free matchers.
Unbiased Delayed Feedback Label Correction for Conversion Rate Prediction
To directly introduce the correct feedback label information, we propose an Unbiased delayed feedback Label Correction framework (ULC), which uses an auxiliary model to correct labels for observed negative feedback samples.
Towards Deeply Unified Depth-aware Panoptic Segmentation with Bi-directional Guidance Learning
Our method sets the new state of the art for depth-aware panoptic segmentation on both Cityscapes-DVPS and SemKITTI-DVPS datasets.
New Interaction Paradigm for Complex EDA Software Leveraging GPT
In the rapidly growing field of electronic design automation (EDA), professional software such as KiCad, Cadence , and Altium Designer provide increasingly extensive design functionalities.
Isomer: Isomerous Transformer for Zero-shot Video Object Segmentation
Recent leading zero-shot video object segmentation (ZVOS) works devote to integrating appearance and motion information by elaborately designing feature fusion modules and identically applying them in multiple feature stages.
Neural Gradient Regularizer
NGR is applicable to various image types and different image processing tasks, functioning in a zero-shot learning fashion, making it a versatile and plug-and-play regularizer.
VEATIC: Video-based Emotion and Affect Tracking in Context Dataset
Along with the dataset, we propose a new computer vision task to infer the affect of the selected character via both context and character information in each video frame.
Eliminating Reasoning via Inferring with Planning: A New Framework to Guide LLMs' Non-linear Thinking
Chain-of-Thought(CoT) prompting and its variants explore equipping large language models (LLMs) with high-level reasoning abilities by emulating human-like linear cognition and logic.
FormalGeo: An Extensible Formalized Framework for Olympiad Geometric Problem Solving
In this paper, we have constructed a consistent formal plane geometry system.
Hint-enhanced In-Context Learning wakes Large Language Models up for knowledge-intensive tasks
In-context learning (ICL) ability has emerged with the increasing scale of large language models (LLMs), enabling them to learn input-label mappings from demonstrations and perform well on downstream tasks.
Hyb-NeRF: A Multiresolution Hybrid Encoding for Neural Radiance Fields
To address these issues, we present Hyb-NeRF, a novel neural radiance field with a multi-resolution hybrid encoding that achieves efficient neural modeling and fast rendering, which also allows for high-quality novel view synthesis.
PointMoment:Mixed-Moment-based Self-Supervised Representation Learning for 3D Point Clouds
Large and rich data is a prerequisite for effective training of deep neural networks.
PointJEM: Self-supervised Point Cloud Understanding for Reducing Feature Redundancy via Joint Entropy Maximization
To reduce redundant information in the features, PointJEM maximizes the joint entropy between the different parts, thereby rendering the learned feature variables pairwise independent.
CrossBind: Collaborative Cross-Modal Identification of Protein Nucleic-Acid-Binding Residues
Accurate identification of protein nucleic-acid-binding residues poses a significant challenge with important implications for various biological processes and drug design.
Bandit Sequential Posted Pricing via Half-Concavity
To overcome this assumption, we study sequential posted pricing in the bandit learning model, where the seller interacts with $n$ buyers over $T$ rounds: In each round the seller posts $n$ prices for the $n$ buyers and the first buyer with a valuation higher than the price takes the item.
Token-Level Contrastive Learning with Modality-Aware Prompting for Multimodal Intent Recognition
To establish an optimal multimodal semantic environment for text modality, we develop a modality-aware prompting module (MAP), which effectively aligns and fuses features from text, video and audio modalities with similarity-based modality alignment and cross-modality attention mechanism.
Ranked #2 on
Multimodal Intent Recognition
on MIntRec
EEGFormer: Towards Transferable and Interpretable Large-Scale EEG Foundation Model
Self-supervised learning has emerged as a highly effective approach in the fields of natural language processing and computer vision.
PepHarmony: A Multi-View Contrastive Learning Framework for Integrated Sequence and Structure-Based Peptide Encoding
This study introduces a novel multi-view contrastive learning framework PepHarmony for the sequence-based peptide encoding task.
A Survey of Data-Efficient Graph Learning
Graph-structured data, prevalent in domains ranging from social networks to biochemical analysis, serve as the foundation for diverse real-world systems.
Intersectional Two-sided Fairness in Recommendation
Fairness of recommender systems (RS) has attracted increasing attention recently.
A Thorough Examination of Decoding Methods in the Era of LLMs
Decoding methods play an indispensable role in converting language models from next-token predictors into practical task solvers.
Xling: A Learned Filter Framework for Accelerating High-Dimensional Approximate Similarity Join
In this paper, we propose Xling, a generic framework to build a learning-based metric space filter with any existing regression model, aiming at accurately predicting whether a query point has enough number of neighbors.
Multi-modal Instruction Tuned LLMs with Fine-grained Visual Perception
Multimodal Large Language Model (MLLMs) leverages Large Language Models as a cognitive framework for diverse visual-language tasks.
Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed
Furthermore, we find spatial variance exists in LoFTR's fine correlation module, which is adverse to matching accuracy.
A Survey of Graph Neural Networks in Real world: Imbalance, Noise, Privacy and OOD Challenges
To tackle these issues, substantial efforts have been devoted to improving the performance of GNN models in practical real-world scenarios, as well as enhancing their reliability and robustness.
InsCL: A Data-efficient Continual Learning Paradigm for Fine-tuning Large Language Models with Instructions
Instruction tuning effectively optimizes Large Language Models (LLMs) for downstream tasks.
No more optimization rules: LLM-enabled policy-based multi-modal query optimizer
As a critical (or could even be the most important) step that significantly impacts the execution performance of the query plan, such analysis and attempts should not be missed.
TC4D: Trajectory-Conditioned Text-to-4D Generation
We learn local deformations that conform to the global trajectory using supervision from a text-to-video model.
SciNews: From Scholarly Complexities to Public Narratives -- A Dataset for Scientific News Report Generation
Scientific news reports serve as a bridge, adeptly translating complex research articles into reports that resonate with the broader public.
DRE: Generating Recommendation Explanations by Aligning Large Language Models at Data-level
Recommendation systems play a crucial role in various domains, suggesting items based on user behavior. However, the lack of transparency in presenting recommendations can lead to user confusion.
Collaborative-Enhanced Prediction of Spending on Newly Downloaded Mobile Games under Consumption Uncertainty
In summary, our contributions underscore the importance of stable model training frameworks and the efficacy of collaborative-enhanced models in predicting user spending behavior in mobile gaming.
CLIFFNet for Monocular Depth Estimation with Hierarchical Embedding Loss
This paper proposes a hierarchical loss for monocular depth estimation, which measures the differences between the prediction and ground truth in hierarchical embedding spaces of depth maps.
OPERA: Operation-Pivoted Discrete Reasoning over Text
To inherit the advantages of these two types of methods, we propose OPERA, an operation-pivoted discrete reasoning framework, where lightweight symbolic operations (compared with logical forms) as neural modules are utilized to facilitate the reasoning ability and interpretability.
