Search Results for author:
Found 71 papers, 30 papers with code
Attention-based Extraction of Structured Information from Street View Imagery
We present a neural network model - based on CNNs, RNNs and a novel attention mechanism - which achieves 84. 2% accuracy on the challenging French Street Name Signs (FSNS) dataset, significantly outperforming the previous state of the art (Smith'16), which achieved 72. 46%.
Ranked #1 on
Optical Character Recognition (OCR)
on FSNS - Test
DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Models
Even though trained mainly on images, we discover that pretrained diffusion models show impressive power in guiding sketch synthesis.
Multi-view Aggregation Network for Dichotomous Image Segmentation
Dichotomous Image Segmentation (DIS) has recently emerged towards high-precision object segmentation from high-resolution natural images.
SketchyScene: Richly-Annotated Scene Sketches
We contribute the first large-scale dataset of scene sketches, SketchyScene, with the goal of advancing research on sketch understanding at both the object and scene level.
SVGDreamer: Text Guided SVG Generation with Diffusion Model
However, existing text-to-SVG generation methods lack editability and struggle with visual quality and result diversity.
Orthogonal Annotation Benefits Barely-supervised Medical Image Segmentation
Subsequently, by introducing unlabeled volumes, we propose a dual-network paradigm named Dense-Sparse Co-training (DeSCO) that exploits dense pseudo labels in early stage and sparse labels in later stage and meanwhile forces consistent output of two networks.
Human-centric Spatio-Temporal Video Grounding With Visual Transformers
HC-STVG is a video grounding task that requires both spatial (where) and temporal (when) localization.
HiNet: Novel Multi-Scenario & Multi-Task Learning with Hierarchical Information Extraction
Multi-scenario & multi-task learning has been widely applied to many recommendation systems in industrial applications, wherein an effective and practical approach is to carry out multi-scenario transfer learning on the basis of the Mixture-of-Expert (MoE) architecture.
LiDAR-Camera Panoptic Segmentation via Geometry-Consistent and Semantic-Aware Alignment
3D panoptic segmentation is a challenging perception task that requires both semantic segmentation and instance segmentation.
Inconsistency-aware Uncertainty Estimation for Semi-supervised Medical Image Segmentation
In semi-supervised medical image segmentation, most previous works draw on the common assumption that higher entropy means higher uncertainty.
Unsupervised Sketch-to-Photo Synthesis
Humans can envision a realistic photo given a free-hand sketch that is not only spatially imprecise and geometrically distorted but also without colors and visual details.
3D Shape Reconstruction from Free-Hand Sketches
Additionally, we propose a sketch standardization module to handle different sketch distortions and styles.
Feature Decomposition for Reducing Negative Transfer: A Novel Multi-task Learning Method for Recommender System
In recent years, thanks to the rapid development of deep learning (DL), DL-based multi-task learning (MTL) has made significant progress, and it has been successfully applied to recommendation systems (RS).
APE: Argument Pair Extraction from Peer Review and Rebuttal via Multi-task Learning
Peer review and rebuttal, with rich interactions and argumentative discussions in between, are naturally a good resource to mine arguments.
Ranked #3 on
Argument Pair Extraction (APE)
on RR
Sketch-a-Net that Beats Humans
We propose a multi-scale multi-channel deep neural network framework that, for the first time, yields sketch recognition performance surpassing that of humans.
Diffusion Model is Secretly a Training-free Open Vocabulary Semantic Segmenter
The pre-trained text-image discriminative models, such as CLIP, has been explored for open-vocabulary semantic segmentation with unsatisfactory results due to the loss of crucial localization information and awareness of object shapes.
IAM: A Comprehensive and Large-Scale Dataset for Integrated Argument Mining Tasks
Traditionally, a debate usually requires a manual preparation process, including reading plenty of articles, selecting the claims, identifying the stances of the claims, seeking the evidence for the claims, etc.
Claim-Evidence Pair Extraction (CEPE)
Claim Extraction with Stance Classification (CESC)
+1
SketchSampler: Sketch-based 3D Reconstruction via View-dependent Depth Sampling
Reconstructing a 3D shape based on a single sketch image is challenging due to the large domain gap between a sparse, irregular sketch and a regular, dense 3D shape.
3D Medical Image Segmentation with Sparse Annotation via Cross-Teaching between 3D and 2D Networks
Our experimental results on the MMWHS dataset demonstrate that our method outperforms the state-of-the-art (SOTA) semi-supervised segmentation methods.
Inversion-by-Inversion: Exemplar-based Sketch-to-Photo Synthesis via Stochastic Differential Equations without Training
In the full-control inversion process, we propose an appearance-energy function to control the color and texture of the final generated photo. Importantly, our Inversion-by-Inversion pipeline is training-free and can accept different types of exemplars for color and texture control.
Unsupervised Cross-Domain Image Retrieval via Prototypical Optimal Transport
This paper introduces ProtoOT, a novel Optimal Transport formulation explicitly tailored for UCIR, which integrates intra-domain feature representation learning and cross-domain alignment into a unified framework.
Crosslink-Net: Double-branch Encoder Segmentation Network via Fusing Vertical and Horizontal Convolutions
Together, the above two schemes give rise to a novel double-branch encoder segmentation framework for medical image segmentation, namely Crosslink-Net.
Towards Automatic Power Battery Detection: New Challenge, Benchmark Dataset and Baseline
We conduct a comprehensive study on a new task named power battery detection (PBD), which aims to localize the dense cathode and anode plates endpoints from X-ray images to evaluate the quality of power batteries.
PLN: Parasitic-Like Network for Barely Supervised Medical Image Segmentation
In this paper, by introducing an extremely sparse annotation way of labeling only one slice per 3D image, we investigate a novel barely-supervised segmentation setting with only a few sparsely-labeled images along with a large amount of unlabeled images.
Rethinking Large-scale Pre-ranking System: Entire-chain Cross-domain Models
Industrial systems such as recommender systems and online advertising, have been widely equipped with multi-stage architectures, which are divided into several cascaded modules, including matching, pre-ranking, ranking and re-ranking.
Concatenate, Fine-tuning, Re-training: A SAM-enabled Framework for Semi-supervised 3D Medical Image Segmentation
Segment Anything Model (SAM) fine-tuning has shown remarkable performance in medical image segmentation in a fully supervised manner, but requires precise annotations.
Polynomial Codes: an Optimal Design for High-Dimensional Coded Matrix Multiplication
We consider a large-scale matrix multiplication problem where the computation is carried out using a distributed system with a master node and multiple worker nodes, where each worker can store parts of the input matrices.
Information Theory Distributed, Parallel, and Cluster Computing Information Theory
Constructing and Exploring Intermediate Domains in Mixed Domain Semi-supervised Medical Image Segmentation
To fully utilize the information within the intermediate domain, we propose a symmetric Guidance training strategy (SymGD), which additionally offers direct guidance to unlabeled data by merging pseudo labels from intermediate samples.
Lagrange Coded Computing: Optimal Design for Resiliency, Security and Privacy
We consider a scenario involving computations over a massive dataset stored distributedly across multiple workers, which is at the core of distributed learning algorithms.
Polynomially Coded Regression: Optimal Straggler Mitigation via Data Encoding
In particular, PCR requires a recovery threshold that scales inversely proportionally with the amount of computation/storage available at each worker.
Crossbar-Net: A Novel Convolutional Network for Kidney Tumor Segmentation in CT Images
Due to the irregular motion, similar appearance and diverse shape, accurate segmentation of kidney tumor in CT images is a difficult and challenging task.
Network Transplanting
This paper focuses on a new task, i. e., transplanting a category-and-task-specific neural network to a generic, modular network without strong supervision.
Large Scale Scene Text Verification with Guided Attention
In this work, we propose a new framework that learns this task in an end-to-end way.
The Devil is in the Middle: Exploiting Mid-level Representations for Cross-Domain Instance Matching
Many vision problems require matching images of object instances across different domains.
Coded Fourier Transform
We consider the problem of computing the Fourier transform of high-dimensional vectors, distributedly over a cluster of machines consisting of a master node and multiple worker nodes, where the worker nodes can only store and process a fraction of the inputs.
Large Scale Business Discovery from Street Level Imagery
Precise business store front detection enables accurate geo-location of businesses, and further provides input for business categorization, listing generation, etc.
Understanding Boltzmann Machine and Deep Learning via A Confident Information First Principle
Typical dimensionality reduction methods focus on directly reducing the number of random variables while retaining maximal variations in the data.
Responding E-commerce Product Questions via Exploiting QA Collections and Reviews
Providing instant responses for product questions in E-commerce sites can significantly improve satisfaction of potential consumers.
Network Transplanting (extended abstract)
This paper focuses on a new task, i. e., transplanting a category-and-task-specific neural network to a generic, modular network without strong supervision.
Recognizing Activities via Bag of Words for Attribute Dynamics
A video sequence is decomposed into short-term segments, which are characterized by the dynamics of their attributes.
Pedestrian Detection in Low-resolution Imagery by Learning Multi-scale Intrinsic Motion Structures (MIMS)
In this paper, we give a comparative evaluation of the proposed method and demonstrate that MIMS outperforms the state of the art approaches in identifying pedestrians from low resolution airborne videos.
Ontological Supervision for Fine Grained Classification of Street View Storefronts
Modern search engines receive large numbers of business related, local aware queries.
Sketch Me That Shoe
We investigate the problem of fine-grained sketch-based image retrieval (SBIR), where free-hand human sketches are used as queries to perform instance-level retrieval of images.
Ranked #3 on
Sketch-Based Image Retrieval
on Chairs
Deep Spatial-Semantic Attention for Fine-Grained Sketch-Based Image Retrieval
Human sketches are unique in being able to capture both the spatial topology of a visual object, as well as its subtle appearance details.
Ranked #2 on
Sketch-Based Image Retrieval
on Handbags
Building Information Modeling and Classification by Visual Learning At A City Scale
In the first case, a machine learning-assisted framework, BRAILS, is proposed for city-scale building information modeling.
Minimax Regret of Switching-Constrained Online Convex Optimization: No Phase Transition
To establish the dimension-independent upper bound, we next show that a mini-batching algorithm provides an $ O(\frac{T}{\sqrt{K}}) $ upper bound, and therefore conclude that the minimax regret of switching-constrained OCO is $ \Theta(\frac{T}{\sqrt{K}}) $ for any $K$.
Review-based Question Generation with Adaptive Instance Transfer and Augmentation
We propose an iterative learning framework for handling this challenge via adaptive transfer and augmentation of the training instances with the help of the available user-posed question-answer data.
Crossover-Net: Leveraging the Vertical-Horizontal Crossover Relation for Robust Segmentation
Robust segmentation for non-elongated tissues in medical images is hard to realize due to the large variation of the shape, size, and appearance of these tissues in different patients.
Deep Symmetric Adaptation Network for Cross-modality Medical Image Segmentation
These typical methods usually utilize a translation network to transform images from the source domain to target domain or train the pixel-level classifier merely using translated source images and original target images.
Answering Product-related Questions with Heterogeneous Information
Providing instant response for product-related questions in E-commerce question answering platforms can greatly improve users{'} online shopping experience.
Feature Cross Search via Submodular Optimization
First, we show that it is not possible to provide an $n^{1/\log\log n}$-approximation algorithm for this problem unless the exponential time hypothesis fails.
LightSecAgg: a Lightweight and Versatile Design for Secure Aggregation in Federated Learning
We also demonstrate that, unlike existing schemes, LightSecAgg can be applied to secure aggregation in the asynchronous FL setting.
Action based Network for Conversation Question Reformulation
Conversation question answering requires the ability to interpret a question correctly.
Alleviating Cold-start Problem in CTR Prediction with A Variational Embedding Learning Framework
We propose a general Variational Embedding Learning Framework (VELF) for alleviating the severe cold-start problem in CTR prediction.
Gating-adapted Wavelet Multiresolution Analysis for Exposure Sequence Modeling in CTR prediction
The exposure sequence is being actively studied for user interest modeling in Click-Through Rate (CTR) prediction.
A Simple Test-Time Method for Out-of-Distribution Detection
In contrast, this paper proposes a simple Test-time Linear Training (ETLT) method for OOD detection.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Slow Motion Matters: A Slow Motion Enhanced Network for Weakly Supervised Temporal Action Localization
Weakly supervised temporal action localization (WTAL) aims to localize actions in untrimmed videos with only weak supervision information (e. g. video-level labels).
Weakly-supervised Temporal Action Localization
Weakly Supervised Temporal Action Localization
The Strategy Evolution in Double Auction Based on the Experience-Weighted Attraction Learning Model
The double auction is a widely applicable trading mechanism used to converge to competitive equilibrium in different markets from which multiple equilibriums and incomplete information may arise.
Product Question Answering in E-Commerce: A Survey
Product question answering (PQA), aiming to automatically provide instant responses to customer's questions in E-Commerce platforms, has drawn increasing attention in recent years.
Decoder-Only or Encoder-Decoder? Interpreting Language Model as a Regularized Encoder-Decoder
Grounded on our analysis, we propose a novel partial attention language model to solve the attention degeneration problem.
Sample Complexity for Quadratic Bandits: Hessian Dependent Bounds and Optimal Algorithms
We consider a fundamental setting in which the objective function is quadratic, and provide the first tight characterization of the optimal Hessian-dependent sample complexity.
DCRNN: A Deep Cross approach based on RNN for Partial Parameter Sharing in Multi-task Learning
The model has three innovations: 1) It adopts the idea of cross network and uses RNN network to cross-process the features, thereby effectively improves the expressive ability of the model; 2) It innovatively proposes the structure of partial parameter sharing; 3) It can effectively capture the potential correlation between different tasks to optimize the efficiency and methods for learning different tasks.
Data Contamination Issues in Brain-to-Text Decoding
Decoding non-invasive cognitive signals to natural language has long been the goal of building practical brain-computer interfaces (BCIs).
An Incremental Update Framework for Online Recommenders with Data-Driven Prior
To address the aforementioned issue, we propose an incremental update framework for online recommenders with Data-Driven Prior (DDP), which is composed of Feature Prior (FP) and Model Prior (MP).
Multi-modality Affinity Inference for Weakly Supervised 3D Semantic Segmentation
The point affinity proposed in this paper is characterized by features from multiple modalities (e. g., point cloud and RGB), and is further refined by normalizing the classifier weights to alleviate the detrimental effects of long-tailed distribution without the need of the prior of category distribution.
Data-Free Generalized Zero-Shot Learning
Firstly, to recover the virtual features of the base data, we model the CLIP features of base class images as samples from a von Mises-Fisher (vMF) distribution based on the pre-trained classifier.
GenesisTex: Adapting Image Denoising Diffusion to Texture Space
We present GenesisTex, a novel method for synthesizing textures for 3D geometries from text descriptions.
